farion1231/cc-switchPublic

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode,DeepSeek Harness and more. Only official website: ccswitch.io

AI summary: Centralized manager for toggling configurations across Claude Code, Claude Desktop, and Codex workflows.

Stars
156K
+15 today
Forks
10.2K
Watchers
282
Open issues
507
Open PRs
365
Contributors
~357
Commits
3.8K
Branches
140

RustMITCreated Aug 4, 2025Last push todayLatest release v4.0.35+1.6K stars this week+8.4K this month

Quick answers

What is cc-switch?
Centralized manager for toggling configurations across Claude Code, Claude Desktop, and Codex workflows.
What does cc-switch do?
CC Switch acts as a unified configuration layer that intercepts and routes environment variables for multiple AI coding assistants. It manipulates local configuration files dynamically, allowing developers to switch between different model endpoints and API keys without manual editing. The tool monitors active processes and restarts necessary background services automatically when configuration states change. It provides a structured CLI interface to manage complex credential sets across isolated project environments. By preventing configuration drift, it ensures consistent AI agent behavior across diverse development tasks.
Who is cc-switch for?
Software developers juggling multiple AI coding assistants and API providers across different projects. Familiarity with basic CLI operations is expected.
How do I get started with cc-switch?
https://github.com/farion1231/cc-switch
How popular is cc-switch on GitHub?
farion1231/cc-switch has 156,042 stars and 10,197 forks on GitHub, and gained 1,616 stars in the last 7 days.
What license does cc-switch use?
farion1231/cc-switch is released under the MIT license.

Star history

since Jul 29, 2026
050K100K150KJul 2026Sep 2026Oct 2026Nov 2026
156K stars as of Nov 21, 2026. Measured daily since Jul 29, 2026; GitHub no longer exposes earlier star timestamps.

Update history

7 recorded
  • Nov 19, 2026New release v4.0.35 (previously v4.0.29).
  • Nov 11, 2026New release v4.0.29 (previously v4.0.25).
  • Nov 3, 2026New release v4.0.25 (previously v4.0.20).
  • Oct 30, 2026Description changed from "A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Onl" to "A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode,DeepSeek Harness and more. Only official ".
  • Oct 25, 2026New release v4.0.20 (previously v4.0.15).
  • Oct 17, 2026New release v4.0.15 (previously v4.0.6).
  • Oct 9, 2026New release v4.0.6 (previously v3.20.4).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-23: 0 commits2025-11-24: 7 commits2025-11-25: 12 commits2025-11-26: 8 commits2025-11-27: 11 commits2025-11-28: 13 commits2025-11-29: 11 commits2025-11-30: 3 commits2025-12-01: 5 commits2025-12-02: 2 commits2025-12-03: 1 commit2025-12-04: 2 commits2025-12-05: 3 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 2 commits2025-12-09: 3 commits2025-12-10: 3 commits2025-12-11: 12 commits2025-12-12: 2 commits2025-12-13: 1 commit2025-12-14: 2 commits2025-12-15: 7 commits2025-12-16: 5 commits2025-12-17: 5 commits2025-12-18: 8 commits2025-12-19: 3 commits2025-12-20: 14 commits2025-12-21: 7 commits2025-12-22: 4 commits2025-12-23: 4 commits2025-12-24: 1 commit2025-12-25: 5 commits2025-12-26: 2 commits2025-12-27: 3 commits2025-12-28: 2 commits2025-12-29: 8 commits2025-12-30: 4 commits2025-12-31: 2 commits2026-01-01: 0 commits2026-01-02: 8 commits2026-01-03: 8 commits2026-01-04: 8 commits2026-01-05: 6 commits2026-01-06: 1 commit2026-01-07: 2 commits2026-01-08: 7 commits2026-01-09: 11 commits2026-01-10: 3 commits2026-01-11: 5 commits2026-01-12: 4 commits2026-01-13: 3 commits2026-01-14: 2 commits2026-01-15: 15 commits2026-01-16: 9 commits2026-01-17: 14 commits2026-01-18: 2 commits2026-01-19: 4 commits2026-01-20: 9 commits2026-01-21: 6 commits2026-01-22: 9 commits2026-01-23: 9 commits2026-01-24: 4 commits2026-01-25: 3 commits2026-01-26: 5 commits2026-01-27: 4 commits2026-01-28: 5 commits2026-01-29: 4 commits2026-01-30: 8 commits2026-01-31: 7 commits2026-02-01: 13 commits2026-02-02: 7 commits2026-02-03: 2 commits2026-02-04: 6 commits2026-02-05: 8 commits2026-02-06: 9 commits2026-02-07: 9 commits2026-02-08: 9 commits2026-02-09: 6 commits2026-02-10: 0 commits2026-02-11: 0 commits2026-02-12: 3 commits2026-02-13: 3 commits2026-02-14: 3 commits2026-02-15: 4 commits2026-02-16: 4 commits2026-02-17: 1 commit2026-02-18: 2 commits2026-02-19: 5 commits2026-02-20: 8 commits2026-02-21: 11 commits2026-02-22: 2 commits2026-02-23: 3 commits2026-02-24: 8 commits2026-02-25: 3 commits2026-02-26: 19 commits2026-02-27: 3 commits2026-02-28: 6 commits2026-03-01: 0 commits2026-03-02: 3 commits2026-03-03: 10 commits2026-03-04: 7 commits2026-03-05: 3 commits2026-03-06: 6 commits2026-03-07: 7 commits2026-03-08: 12 commits2026-03-09: 13 commits2026-03-10: 10 commits2026-03-11: 8 commits2026-03-12: 7 commits2026-03-13: 0 commits2026-03-14: 6 commits2026-03-15: 9 commits2026-03-16: 3 commits2026-03-17: 1 commit2026-03-18: 0 commits2026-03-19: 1 commit2026-03-20: 5 commits2026-03-21: 3 commits2026-03-22: 1 commit2026-03-23: 3 commits2026-03-24: 7 commits2026-03-25: 3 commits2026-03-26: 0 commits2026-03-27: 0 commits2026-03-28: 1 commit2026-03-29: 5 commits2026-03-30: 2 commits2026-03-31: 4 commits2026-04-01: 3 commits2026-04-02: 17 commits2026-04-03: 11 commits2026-04-04: 7 commits2026-04-05: 17 commits2026-04-06: 10 commits2026-04-07: 7 commits2026-04-08: 14 commits2026-04-09: 11 commits2026-04-10: 27 commits2026-04-11: 2 commits2026-04-12: 4 commits2026-04-13: 8 commits2026-04-14: 15 commits2026-04-15: 16 commits2026-04-16: 6 commits2026-04-17: 4 commits2026-04-18: 4 commits2026-04-19: 12 commits2026-04-20: 18 commits2026-04-21: 10 commits2026-04-22: 8 commits2026-04-23: 13 commits2026-04-24: 7 commits2026-04-25: 3 commits2026-04-26: 1 commit2026-04-27: 1 commit2026-04-28: 4 commits2026-04-29: 3 commits2026-04-30: 13 commits2026-05-01: 8 commits2026-05-02: 12 commits2026-05-03: 0 commits2026-05-04: 0 commits2026-05-05: 0 commits2026-05-06: 1 commit2026-05-07: 2 commits2026-05-08: 10 commits2026-05-09: 3 commits2026-05-10: 5 commits2026-05-11: 9 commits2026-05-12: 7 commits2026-05-13: 14 commits2026-05-14: 17 commits2026-05-15: 9 commits2026-05-16: 8 commits2026-05-17: 0 commits2026-05-18: 11 commits2026-05-19: 8 commits2026-05-20: 7 commits2026-05-21: 13 commits2026-05-22: 9 commits2026-05-23: 5 commits2026-05-24: 2 commits2026-05-25: 7 commits2026-05-26: 5 commits2026-05-27: 7 commits2026-05-28: 6 commits2026-05-29: 15 commits2026-05-30: 11 commits2026-05-31: 8 commits2026-06-01: 8 commits2026-06-02: 3 commits2026-06-03: 9 commits2026-06-04: 10 commits2026-06-05: 6 commits2026-06-06: 3 commits2026-06-07: 8 commits2026-06-08: 5 commits2026-06-09: 7 commits2026-06-10: 11 commits2026-06-11: 14 commits2026-06-12: 4 commits2026-06-13: 9 commits2026-06-14: 12 commits2026-06-15: 2 commits2026-06-16: 10 commits2026-06-17: 3 commits2026-06-18: 2 commits2026-06-19: 6 commits2026-06-20: 0 commits2026-06-21: 1 commit2026-06-22: 4 commits2026-06-23: 8 commits2026-06-24: 5 commits2026-06-25: 2 commits2026-06-26: 9 commits2026-06-27: 8 commits2026-06-28: 8 commits2026-06-29: 5 commits2026-06-30: 12 commits2026-07-01: 12 commits2026-07-02: 1 commit2026-07-03: 0 commits2026-07-04: 12 commits2026-07-05: 2 commits2026-07-06: 1 commit2026-07-07: 7 commits2026-07-08: 14 commits2026-07-09: 3 commits2026-07-10: 6 commits2026-07-11: 8 commits2026-07-12: 10 commits2026-07-13: 7 commits2026-07-14: 5 commits2026-07-15: 3 commits2026-07-16: 2 commits2026-07-17: 10 commits2026-07-18: 0 commits2026-07-19: 5 commits2026-07-20: 11 commits2026-07-21: 18 commits2026-07-22: 3 commits2026-07-23: 4 commits2026-07-24: 3 commits2026-07-25: 0 commits2026-07-26: 6 commits2026-07-27: 3 commits2026-07-28: 9 commits2026-07-29: 9 commits2026-07-30: 7 commits2026-07-31: 11 commits2026-08-01: 3 commits2026-08-02: 1 commit2026-08-03: 9 commits2026-08-04: 9 commits2026-08-05: 2 commits2026-08-06: 3 commits2026-08-07: 0 commits2026-08-08: 0 commits2026-08-09: 0 commits2026-08-10: 12 commits2026-08-11: 8 commits2026-08-12: 7 commits2026-08-13: 10 commits2026-08-14: 4 commits2026-08-15: 9 commits2026-08-16: 7 commits2026-08-17: 8 commits2026-08-18: 7 commits2026-08-19: 0 commits2026-08-20: 0 commits2026-08-21: 1 commit2026-08-22: 0 commits2026-08-23: 0 commits2026-08-24: 1 commit2026-08-25: 9 commits2026-08-26: 8 commits2026-08-27: 9 commits2026-08-28: 5 commits2026-08-29: 1 commit2026-08-30: 5 commits2026-08-31: 3 commits2026-09-01: 5 commits2026-09-02: 4 commits2026-09-03: 1 commit2026-09-04: 3 commits2026-09-05: 1 commit2026-09-06: 5 commits2026-09-07: 20 commits2026-09-08: 0 commits2026-09-09: 3 commits2026-09-10: 10 commits2026-09-11: 11 commits2026-09-12: 1 commit2026-09-13: 6 commits2026-09-14: 2 commits2026-09-15: 6 commits2026-09-16: 0 commits2026-09-17: 0 commits2026-09-18: 0 commits2026-09-19: 0 commits2026-09-20: 9 commits2026-09-21: 5 commits2026-09-22: 20 commits2026-09-23: 5 commits2026-09-24: 2 commits2026-09-25: 9 commits2026-09-26: 8 commits2026-09-27: 16 commits2026-09-28: 5 commits2026-09-29: 5 commits2026-09-30: 17 commits2026-10-01: 10 commits2026-10-02: 33 commits2026-10-03: 71 commits2026-10-04: 27 commits2026-10-05: 29 commits2026-10-06: 37 commits2026-10-07: 10 commits2026-10-08: 15 commits2026-10-09: 25 commits2026-10-10: 29 commits2026-10-11: 35 commits2026-10-12: 30 commits2026-10-13: 23 commits2026-10-14: 52 commits2026-10-15: 26 commits2026-10-16: 44 commits2026-10-17: 24 commits2026-10-18: 18 commits2026-10-19: 26 commits2026-10-20: 18 commits2026-10-21: 37 commits2026-10-22: 9 commits2026-10-23: 39 commits2026-10-24: 39 commits2026-10-25: 16 commits2026-10-26: 39 commits2026-10-27: 12 commits2026-10-28: 8 commits2026-10-29: 27 commits2026-10-30: 21 commits2026-10-31: 21 commits2026-11-01: 12 commits2026-11-02: 32 commits2026-11-03: 10 commits2026-11-04: 10 commits2026-11-05: 20 commits2026-11-06: 21 commits2026-11-07: 18 commits2026-11-08: 22 commits2026-11-09: 14 commits2026-11-10: 15 commits2026-11-11: 31 commits2026-11-12: 25 commits2026-11-13: 6 commits2026-11-14: 19 commits2026-11-15: 26 commits2026-11-16: 47 commits2026-11-17: 35 commits2026-11-18: 9 commits2026-11-19: 4 commits2026-11-20: 0 commits2026-11-21: 0 commits
3,096 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Landmark project

    156,042 stars

  • Very active

    3,096 commits in 52 weeks

  • Community-driven

    ~357 contributors

  • Well documented

    High community health score

  • Permissive license

    MIT

  • Continuous integration

    Automated checks passing

  • Repeat trending

    67 trending appearances

  • Top 10% tracked

    Rank 38 of 1243

What cc-switch does

CC Switch acts as a unified configuration layer that intercepts and routes environment variables for multiple AI coding assistants. It manipulates local configuration files dynamically, allowing developers to switch between different model endpoints and API keys without manual editing. The tool monitors active processes and restarts necessary background services automatically when configuration states change. It provides a structured CLI interface to manage complex credential sets across isolated project environments. By preventing configuration drift, it ensures consistent AI agent behavior across diverse development tasks.

Software developers juggling multiple AI coding assistants and API providers across different projects. Familiarity with basic CLI operations is expected.

  • Configuration routing: Intercepts and directs environment variables to the correct AI assistant seamlessly.
  • Dynamic toggling: Switches active API endpoints and model parameters without requiring manual file edits.
  • Service management: Restarts relevant background processes automatically when configuration states are modified.
  • Credential isolation: Manages distinct API keys and settings for separate, sandboxed project environments.
  • Unified interface: Controls Claude Code, Claude Desktop, and Codex parameters from a single command-line tool.

Where teams use it

Manage multiple projects

Switch between different client API keys rapidly without manually editing dotfiles.

Test varied models

Toggle execution environments instantly to compare code generation quality across different providers.

Automate service restarts

Apply configuration changes reliably without needing to manually hunt down background processes.

Standardize agent setups

Enforce consistent tool configurations across a team of developers using shared profiles.

Getting started: https://github.com/farion1231/cc-switch

README

main branch

CC Switch

The All-in-One Manager for Claude Code, Claude Desktop, Codex, Gemini CLI, Grok Build, OpenCode, OpenClaw, Hermes Agent, Pi, MiniMax Code, Kimi Code & Oh My Pi

Switch API providers in one click and manage MCP, Skills, and Prompts in one place — no more hand-editing JSON / TOML / YAML config files.

Version Platform Built with Tauri Downloads

farion1231%2Fcc-switch | Trendshift Star History Rank

farion1231%2Fcc-switch | Trendshift farion1231%2Fcc-switch | Trendshift farion1231%2Fcc-switch | Trendshift

🌐 The Only Official Website: ccswitch.io

English | 简体中文 | 繁體中文 | 日本語 | 한국어 | Türkçe | Русский | Deutsch | Changelog

Download · Quick Start · Features · FAQ · User Manual

❤️Sponsor

Want to appear here?

Click to collapse

Kimi K3.1 Pro

Kimi K3.1 Pro is Moonshot AI's most capable 3T-class open-weight model to date, with a 1-million-token context window. Built on Kimi K3 with substantially larger post-training compute, it delivers consistent gains across coding, agentic workflows, 3D creation, and reasoning. CC Switch makes it easy to configure and switch to Kimi K3.1 Pro across agentic tools.

Try a Kimi Code plan (中文站 | Global), or use the API through the Kimi Open Platform (中文站 | Global).

New user top-up bonus: register and complete your first top-up via the API links above to receive 10% of the amount as bonus API credit, up to CNY ¥1,000.


AICodeMirror Thanks to AICodeMirror for sponsoring this project! AICodeMirror provides official high-stability relay services for Claude Code / Codex / Gemini CLI, with enterprise-grade concurrency, fast invoicing, and 24/7 dedicated technical support. Claude Code / Codex / Gemini official channels at 38% / 2% / 9% of original price, with extra discounts on top-ups! AICodeMirror offers special benefits for CC Switch users: register via this link to enjoy 20% off your first top-up, and enterprise customers can get up to 25% off!
PackyCode Thanks to PackyCode for sponsoring this project! PackyCode is a reliable and efficient API relay service provider, offering relay services for Claude Code, Codex, Gemini, and more. PackyCode provides special discounts for our software users: register using this link and enter the "cc-switch" promo code during first recharge to get 10% off.
APINebula Thanks to APINEBULA for sponsoring this project! APINEBULA, an enterprise-grade AI aggregation platform under Galaxy Video Bureau, leverages extensive platform resources to provide developers, teams, and enterprises with stable, cost-effective access to large language model APIs. The platform integrates leading, full-powered models like Claude, GPT, and Gemini, allowing you to connect to the world's top AI models through a single API, with prices starting as low as 10% of the original cost. Designed for AI programming, Agent development, and business system integration, APINEBULA supports enterprise-grade high concurrency, formal contracts, corporate bank transfers, and invoicing services. APINEBULA provides special discounts for our software users: register using this link and enter the "ccswitch" promo code during your first recharge to get 10% off.
PatewayAI Thanks to PatewayAI for sponsoring this project! PatewayAI is an API relay service provider for experienced AI developers, with full support for Claude, the GPT series, and a wide range of mainstream Chinese models. All models come from official high-quality channels — never diluted, never faked — with transparent, verifiable billing details. The economy mode goes as low as 5% of the original price. Register via this link to get a free $1 trial credit, and join occasional promotions for more free credit. The platform also supports enterprise-grade concurrency, a dedicated admin console, formal contracts and invoices, and offers a two-way referral top-up bonus of up to $150.
hao.ai Thanks to hao.ai for sponsoring this project! hao.ai is a fast, stable unified LLM API gateway for developers and teams. With one API key and a unified interface, you can access GPT, Claude, xAI Grok, and other leading models, compatible with common protocols and SDKs such as OpenAI and Anthropic. The platform offers model routing, failover, team management, and complete request logs, with model prices as low as 15% of official reference prices, making it simpler, more stable, and cheaper to build AI applications. hao.ai offers CC Switch users a special perk: register via this link to get 5% bonus credit on your first order!
Fenno.ai Thanks to Fenno.ai for sponsoring this project! Fenno.ai is a stable and efficient API relay service provider, currently focused on Codex relay. It is compatible with the OpenAI and Anthropic protocols and can be flexibly used from Codex, Claude Code, OpenCode, and other mainstream coding tools. It reliably supports enterprise-grade workloads of hundreds of billions of tokens per day, with corporate (B2B) settlement and invoicing for both domestic and overseas entities. Fenno.ai offers an exclusive benefit for CC Switch users: subscribe via this link to the $1.99 Trial Plan worth $50 in credits (valid for 7 days), and earn up to 20% in referral rewards — invite more, earn more!
OpenModel Thanks to OpenModel for sponsoring this project! OpenModel offers client-specific discounts of up to 90% for Codex and 60% for Claude Code across supported models, helping developers cut API costs without changing how they work. Just connect your OpenModel API key and keep using Codex or Claude Code as usual — supported clients are detected automatically and discounted routes are applied with no extra parameters or manual routing required. You can also configure fallback behavior per API key, choosing whether to continue at standard pricing or stop when a discounted route is temporarily unavailable. CC Switch users can register via this link and use promo code "cc-switch" to get 10% off their first top-up.
GrooRoute Pro Thanks to GrooRoute Pro for sponsoring this project! GrooRoute Pro is a reliable, smooth AI API relay platform with access to OpenAI, Claude, DeepSeek, and other mainstream models. Deployed on overseas servers, it lets you choose your own pricing-multiplier tier and offers both pay-as-you-go billing and subscription plans, so you can use it however suits you best — with stable routes and fast responses that make calling all kinds of AI capabilities easier. Exclusive benefit for CC Switch users: register via this link to get ¥5 in free trial credit!
BuyToken Thanks to BuyToken for sponsoring this project! BuyToken offers relay services for Claude Code, Codex, DeepSeek, and more, with enterprise-grade concurrency and fast invoicing — built to be a stable, long-running service. BuyToken also offers CC Switch users a special deal: register via this link to get ¥3 in trial credit, plus 10% off your first top-up!
V-API Thanks to V-API for sponsoring this project! V-API is a three-year-old brand dedicated to providing individuals, developers, and businesses with a stable, fast, and secure platform for high-quality LLM API services, with support for formal contracts and official invoices (general / special VAT). V-API offers CC Switch users a special deal: register via this link to get ¥2 off plus 10% off your first order!
FluxA TokenPlan Thanks to FluxA & Baidu AI Cloud for sponsoring this project! FluxA and Baidu AI Cloud jointly launched AgenticPlan, which gives AI agents the ability to buy, manage and use models, APIs and tools on their own. It includes Baidu Qianfan TokenPlan at up to 40% off, with access to flagship models such as DeepSeek V4, GLM 5.2 and Kimi, plus bonus FluxA AgentMarket API credits that unlock 13,000+ paid APIs for search, data scraping, social media, finance, crypto, image generation, video and more.
With the user's authorization, an AI agent can also pay with the official Visa card to procure resources on its own, manage API keys, monitor usage and plan renewals — taking agents from "completing tasks autonomously" to genuinely "planning their own budget and completing tasks". Buy via this link!
AIGoCode Thanks to AIGoCode for sponsoring this project! AIGoCode is a subscription-based AI coding platform, not just pay-per-token. One account, one monthly plan for Claude Code, Codex and Gemini, with direct connection on the mainland and fast responses. Subscribe via this link to get an extra 10% credits!
TeamoRouter Thanks to TeamoRouter for sponsoring this project! TeamoRouter is an enterprise-grade Agentic LLM gateway built for developers, AI teams, and businesses. Without requiring any subscriptions, it lets you access Claude Code, Codex, Gemini CLI, OpenAI Codex, and other popular AI agents through a single unified API, while offering API pricing at discounts of up to 90%. Unlike typical API relay services, TeamoRouter aggregates hundreds of official model providers and trusted infrastructure partners, including OpenAI, Anthropic, Vertex, Azure, and AWS bedrock. Every provider is verified for 100% Agent protocol compatibility, cache performance, and request traceability, ensuring stable quality instead of reverse-engineered or diluted endpoints. The platform delivers near-official TTFT, 99.6% SLA, enterprise-scale throughput up to 5,000 QPM, and industry-leading cache hit rates that dramatically reduce token costs for long-running agent workflows. TeamoRouter also offers enterprise features including centralized billing, team management, BYOK, smart routing, usage analytics, dynamic provider optimization, and dedicated support. For an even simpler experience, Teamo Desktop lets you use Claude Code, Codex, Gemini CLI, and other popular AI agents with one-click setup—no API key management or manual gateway configuration required. Register via this link as a new user to receive 10% off your first top-up.
AICoding Thanks to AICoding for sponsoring this project! AICoding — Global AI Model API Relay Service at Unbeatable Prices! Claude Code at 19% of original price, GPT at just 1%! Trusted by hundreds of enterprises for cost-effective AI services. Supports Claude Code, GPT, Gemini and major domestic models, with enterprise-grade high concurrency, fast invoicing, and 24/7 dedicated technical support. CC Switch users who register via this link get 10% off their first top-up!
SubRouter Thanks to SubRouter for sponsoring this project! SubRouter is a marketplace and smart routing platform for AI service operators. Merchants can launch operating sites, publish packages, manage users, models, and pricing, while users discover services and access reliable AI models through one unified API. Register via this link!
RunAPI Thanks to RunAPI for sponsoring this project! RunAPI is a high-performance and reliable AI model API gateway — one API key gives you access to 150+ mainstream models including OpenAI, Claude, Gemini, DeepSeek, and Grok, with prices as low as 10% of the official rate and excellent stability. It works seamlessly with Claude Code, OpenClaw, and other tools. Exclusive benefit for CC Switch users: register via this link and enjoy a 10% discount on your first top-up!
OspreyAI Thanks to OspreyAI for sponsoring this project! ACS OspreyAI is a one-stop multi-model API platform for developers and businesses. A single API key gives you access to leading Chinese and international models, including Claude, Gemini, GPT, GLM, Kimi, Qwen, DeepSeek, and Tencent Hunyuan. The platform is compatible with OpenAI, Anthropic, and other mainstream API protocols, and works with popular AI tools such as Claude Code, Codex, OpenCode, Pi, and Hermes. International models cost 20–40% less than official prices, and Chinese models 30–50% less. Unified top-ups, unified billing, usage tracking, and flexible model switching make it a fit for AI app development, content production, and automated workflows. Create an account via this link to get a discount and quickly connect to leading models from China and abroad.
Shengsuanyun Thanks to Shengsuanyun for sponsoring this project! Shengsuanyun is a super factory serving AI Native Teams — an industrial-grade AI task parallel execution platform. Its model marketplace aggregates Claude, ChatGPT, Gemini, and other domestic and international LLM and multimedia model capabilities with direct supply. Absolutely no reverse engineering or dilution — platform-wide model SLA availability reaches 99.7%, with monitoring dashboards showing green across the board. It also offers enterprise-grade custom gateways for fine-grained team cost and permission management, smart routing, security protection, and BYOK (Bring Your Own Key) hosting. The platform charges on a pay-per-use and tokens plan (coming soon) basis, with invoicing available. Register via this link as a new user to receive ¥10 in credits plus a 10% bonus on your first top-up.
88API Thanks to 88API Token Aggregation Platform for sponsoring this project! 88API is a one-stop multi-model API platform operated by a Hong Kong company, built mainly for developers, creators and AI application users. A unified interface gives access to text, image, speech and video models, covering common workflows such as AI coding, smart translation, content creation, voice-over, image generation and video generation. You can add it as a provider and switch to it right inside CC Switch. 88API supports major international payment methods, can issue invoices, and provides enterprise-grade stable service. Register via this link to receive exclusive bonus credits!
APIKEY.FUN Thanks to APIKEY.FUN for sponsoring this project! APIKEY.FUN is a professional enterprise-grade AI relay platform dedicated to providing stable, efficient, and low-cost AI model API access for enterprises and individual developers. The platform supports popular mainstream models such as Claude, OpenAI, and Gemini, with prices as low as 7% of official rates. Register through this project's exclusive link to enjoy an exclusive offer of up to permanent 5% off top-ups.
9527CODE Thanks to 9527CODE for sponsoring this project! 9527 CODE is an enterprise-grade, full-capability AI relay platform focused on stability and service quality, providing fast, stable, and high-quality relay services for Claude Code, Codex, and other mainstream AI models. It places greater emphasis on long-term stability, route quality, and sustained availability, offering enterprises and heavy AI users a stable and efficient one-stop model access solution. With one year of continuous operation, 99.9% service stability, and 7×24 human technical support. Register through this project's exclusive link; new users can contact customer service to receive trial credit, and referral cashback is unlimited!
PPIO Thanks to PPIO for sponsoring this project! PPIO is a leading independent Agentic Cloud provider in China, co-founded in 2018 by PPTV founder Yao Xin and former PPTV chief architect Wang Wenyu. A single API key gives you access to every flagship open-source model, including DeepSeek-V4-Flash, Kimi-K3, GLM-5.2, and MiniMax-M3; the enterprise Token Plan is available at up to 40% off and supports 200 seats, and the Fusion blended model matches Fable5 at one-tenth of the price. Register via this link and complete identity verification to receive a ¥10 credit voucher — invite friends to top up and earn up to 15% cashback on their spend.
new-api Thanks to the open-source AI infrastructure project new-api for its strong support of this project! new-api is an open-source AI infrastructure project from QuantumNous and one of the leading unified LLM access-and-distribution projects by activity and adoption, focused on helping developers, teams, and enterprises build manageable, scalable AI service platforms at lower cost. As a fellow project rooted in the open-source ecosystem, new-api hopes to sponsor and support the continued growth of more outstanding open-source projects. 🌟 Star new-api to show your support: https://github.com/QuantumNous/new-api. Website: https://www.newapi.ai/.
ClaudeCN Thanks to ClaudeCN for sponsoring this project! ClaudeCN is an enterprise-grade AI gateway platform operated by a registered company. It delivers high-availability commercial API access to popular models including Claude, GPT, and DeepSeek, and is built around formal enterprise procurement workflows — corporate bank transfers, signed contracts, and full compliance. Register via this link!
BytePlus Thanks to Dola seed for sponsoring this project! Dola Seed 2.0 is a full‑modal general large model independently developed by ByteDance for the global market. Built on a unified multimodal architecture, it supports joint understanding and generation of text, images, audio, and video. It natively enables agent collaboration, with strong reasoning, long‑task execution, tool integration, and coding capabilities. It is widely applicable to smart cockpits, personal assistants, education, customer support, marketing, retail, and other scenarios. It excels in multimodal perception, end‑to‑end complex task delivery, stable interaction, and data security, and is readily accessible and deployable via the ModelArk platform. Register via this link to get 500,000 tokens of free inference quota per model. >>中国大陆地区的开发者请点击这里
SiliconFlow Thanks to SiliconFlow for sponsoring this project! SiliconFlow is a high-performance AI infrastructure and model API platform, providing fast and reliable access to language, speech, image, and video models in one place. With pay-as-you-go billing, broad multimodal model support, high-speed inference, and enterprise-grade stability, SiliconFlow helps developers and teams build and scale AI applications more efficiently. Register via this link and complete real-name verification to receive ¥16 in bonus credit, usable across models on the platform. SiliconFlow is also now compatible with OpenClaw, allowing users to connect a SiliconFlow API key and call major AI models for free.
A6API Thanks to A6API for sponsoring this project! A6API is a one-stop AI model API aggregation platform covering Claude, GPT, Gemini, Codex, and other mainstream models. Multiple vendors can list their supply on the platform, so the same model can be quoted competitively by several upstream providers. Smart routing automatically picks the more stable, lower-priced route available and fails over automatically, helping you reduce failed requests, cut costs, and improve stability. Whether you are an individual developer, an AI product team, or a studio, you can integrate quickly through a unified interface — compatible with all formats, with low migration cost. New users who register via this link receive free trial credits: try it first, then use it at a low price.
Compshare Thanks to Compshare for sponsoring this project! Compshare is UCloud's AI cloud platform, providing stable and comprehensive domestic and international model APIs with just one key. Featuring cost-effective monthly and per-use domestic-model Coding Plan packages, alongside stable officially-relayed overseas models. Supports Claude Code, Codex, and API access. Enterprise-grade high concurrency, 24/7 technical support, and self-service invoicing. Users who register via this link will receive a free 5 CNY platform trial credit!
SSSAiCode Thanks to SSSAiCode for sponsoring this project! SSSAiCode is a stable and reliable API relay service, dedicated to providing stable, reliable, and affordable Claude and Codex model services, with same-day fast invoicing. SSSAiCode offers a special deal for CC Switch users: register via this link to enjoy $10 extra credit on every top-up!
SoleAPI Thanks to SoleAPI for supporting this project! SoleAPI is an AI model gateway for developers and enterprises: one API key gives you access to 30+ leading models including Claude, GPT and Gemini. It is natively compatible with the OpenAI and Anthropic protocols, so Claude Code, Codex, Cursor and your existing SDKs work by simply changing the Base URL. Requests are routed in real time by latency and upstream health, with millisecond-level automatic failover to backup channels, 99.99% service availability and 24/7 technical support. Every call lands on a single bill with per-request token and cost breakdowns you can inspect at any time. Sign up through this project's referral link to receive free trial credits, and earn ongoing cashback by inviting friends who top up!
Micu Thanks to Micu API for sponsoring this project! Micu API is a global LLM relay service provider dedicated to delivering the best cost-performance ratio with high stability. Backed by a registered enterprise for core assurance, eliminating any risk of service discontinuation, with fast official invoicing support! We champion "zero cost to try": top up from as low as ¥1 with no minimum, and get fee-free refunds anytime! Micu API offers an exclusive deal for CC Switch users: register via this link and enter promo code "ccswitch" when topping up to enjoy a 10% discount!
RightCode Thank you to Right Code for sponsoring this project! Right Code reliably provides routing services for models such as Claude Code, Codex, and Gemini, with both pay-as-you-go and monthly subscription billing options available. Invoices are available upon top-up, and enterprise and team users can receive dedicated one-on-one support. Right Code also offers an exclusive discount for CC Switch users: register via this link, and with every top-up you will receive pay-as-you-go credit equivalent to 5% of the amount paid.
Cubence Thanks to Cubence for sponsoring this project! Cubence is a reliable and efficient API relay service provider, offering relay services for Claude Code, Codex, Gemini, and more with flexible billing options including pay-as-you-go and monthly plans. Cubence provides special discounts for CC Switch users: register using this link and enter the "CCSWITCH" promo code during recharge to get 10% off every top-up!
Crazyrouter Thanks to Crazyrouter for sponsoring this project! Crazyrouter is a high-performance AI API aggregation platform — one API key for 300+ models including Claude Code, Codex, Gemini CLI, and more. All models at 55% of official pricing with auto-failover, smart routing, and unlimited concurrency. Crazyrouter offers an exclusive deal for CC Switch users: register via this link and contact customer support to claim $2 free credit, plus enter promo code `CCSWITCH` on your first top-up for an extra 30% bonus credit!
DMXAPI Thanks to DMXAPI for sponsoring this project! DMXAPI provides global large model API services to 200+ enterprise users. One API key for all global models. Features include: instant invoicing, unlimited concurrency, starting from $0.15, 24/7 technical support. GPT/Claude/Gemini all at 32% off, domestic models 20-50% off, Claude Code exclusive models at 66% off! Register here

Why CC Switch?

AI coding tools like Claude Code, Codex, and Gemini CLI each have their own configuration format. Switching API providers means hand-editing JSON, TOML, YAML, or .env files, and MCP, Skills, and prompts have to be maintained separately in every tool.

CC Switch brings all of this into a single desktop app: pick a preset, enter your key, and switch in one click. Switching replaces only the connection details — endpoint, key, and model — so plugins, hooks, MCP, and comments you added yourself stay as they are.

  • One App, Twelve Tools — Claude Code, Claude Desktop, Codex, Gemini CLI, Grok Build, OpenCode, OpenClaw, Hermes, Pi, MiniMax Code, Kimi Code, and Oh My Pi
  • No More Manual Editing — 90+ provider presets including AWS Bedrock, NVIDIA NIM, and community relays
  • Direct, Routing, or Aggregation — Your Choice — Direct connects the tool straight to the provider; Routing forwards requests through your machine, converting API formats and failing over automatically, so you can use GPT in Claude Code and Claude in Codex; Aggregation puts models from several providers into one model list in Claude Code or Codex, and each request goes to the provider of the model you pick
  • Centralized MCP, Skills & Prompts — Add MCP servers and Skills once, then choose which tools to sync them to; prompts are maintained separately for each tool
  • Sessions You Can Read — Turns each tool's session logs into a reading view: what each turn did, which files changed, and which step failed, all at a glance
  • Usage & Quotas at a Glance — Track token usage and spending even without local routing; remaining subscription quota and account balances show right on provider cards and in the tray
  • Cross-Platform — Native desktop app for Windows, macOS, and Linux, built with Tauri 2

Screenshots

Main interface: sidebar, Direct / Routing / Aggregation tabs, and provider cards
Main Interface
Apps page: versions, installation, and upgrades for every AI coding tool in one place
Apps Page
Aggregation mode: one default provider plus several added providers
Aggregation Mode
Codex's model picker listing models from several providers
Aggregated Model List in Codex
Session reading view: step summaries, tool call details, and conversation outline
Session Reading View
Usage: heatmap and request logs
Usage

Download & Installation

System Requirements

  • Windows: Windows 10 and above
  • macOS: macOS 12 (Monterey) and above
  • Linux: x86_64 or ARM64 with glibc 2.35+ and WebKitGTK 4.1 — e.g. Ubuntu 22.04+, Debian 12+, and recent Fedora releases; RHEL / Rocky / Alma 8–9 are not supported yet

Windows Users

Download the latest CC-Switch-v{version}-Windows.msi installer or CC-Switch-v{version}-Windows-Portable.zip portable version from the Releases page. On Windows on ARM, download CC-Switch-v{version}-Windows-arm64.msi or CC-Switch-v{version}-Windows-arm64-Portable.zip.

macOS Users

Method 1: Install via Homebrew (Recommended)

brew install --cask cc-switch

Update:

brew upgrade --cask cc-switch

Method 2: Manual Download

Download CC-Switch-v{version}-macOS.dmg (recommended) or .zip from the Releases page. It's a Universal build that runs natively on both Apple Silicon and Intel Macs.

Note: CC Switch for macOS is code-signed and notarized by Apple. You can install and open it directly.

Arch Linux Users

Install via paru (Recommended)

paru -S cc-switch-bin

Linux Users

Download the latest Linux build from the Releases page:

  • CC-Switch-v{version}-Linux-x86_64.deb / -Linux-arm64.deb (Debian/Ubuntu)
  • CC-Switch-v{version}-Linux-x86_64.rpm / -Linux-arm64.rpm (Fedora and other RPM distros that ship WebKitGTK 4.1)
  • CC-Switch-v{version}-Linux-x86_64.AppImage / -Linux-arm64.AppImage (any distro meeting the requirements above)

Flatpak: Not included in official releases. You can build it yourself from the .deb — see flatpak/README.md for instructions.

Quick Start

Basic Usage

  1. Add Provider: Select the tool you want to manage in the sidebar, then click "+" (Add Provider) in the top-right corner of the page → Choose a preset or create a custom configuration
  2. Switch Provider:
    • Main UI: Select provider → Click "Enable" (for OpenCode, OpenClaw, Hermes, MiniMax Code, and Kimi Code the button is "Add", and for Pi and Oh My Pi it's "Enable" / "Remove"; these seven are coexist-mode tools, so you can add several providers at once)
    • System Tray: One row per tool showing "name · mode · provider · quota"; click a provider name in its submenu to switch (Claude Code, Claude Desktop, Codex, Gemini CLI, and Grok Build)
  3. Takes Effect: Claude Code needs no restart; for Codex, Gemini CLI, and Grok Build, restart your terminal or the CLI tool; for Claude Desktop, restart the app itself (see FAQ)
  4. Back to Official Login: Switch to the built-in official provider in the list (e.g. "Claude Official"), restart the tool, then follow its login/OAuth flow
  5. Routing & Aggregation (optional): The Claude Code, Codex, Gemini CLI, and Grok Build pages have "Direct" / "Routing" tabs at the top, and Claude Code and Codex also have "Aggregation". Clicking a tab only changes what you're looking at and doesn't touch your configuration; to actually switch, click "Start routing" or "Switch to Aggregation" on the page, and click "Back to direct" to return. Use Routing to use OpenAI- or Gemini-format providers in Claude Code, or Claude in Codex; use Aggregation to mix models from several providers in one model list
  6. Manage Tools: The "Apps" page in the sidebar shows each AI coding tool's version, install location, and source in one place; you can install, upgrade, or upgrade all, and choose which tools appear in the sidebar

MCP, Prompts, Skills, Projects & Sessions

  • MCP: Click "MCP" in the sidebar → Add servers via templates or custom config (or "Import Existing") → Toggle sync for each tool
  • Prompts: Click "Prompts" in the sidebar → Create prompts with the Markdown editor → Enable one to write it to that tool's prompt file
  • Skills: Click "Skills" in the sidebar → "Discover Skills" → Search skills.sh or browse GitHub repos → One-click install to supported tools
  • Projects: First turn on "Show project switcher" in "Settings → General", then on the Claude Code, Claude Desktop, or Codex page, open the project switcher at the top → "New project" to save the current configuration; later, pick it from the switcher to switch the whole setup at once
  • Sessions: Click "Sessions" in the sidebar → Browse and search conversation history, open the reading view, or restore each tool's sessions
  • Accounts: Click "Accounts" in the sidebar to sign in to GitHub Copilot, ChatGPT, xAI (Grok), and Kimi Code accounts and use your subscriptions as providers. Kimi Code supports multiple official accounts, each with separate credentials and a native provider; the first login uses Kimi's native default credential slot. Manage sign-in, reauthentication and sign-out here. Official Kimi OAuth nodes still present in the native configuration are protected on the provider page; saved profiles can be deleted after their native nodes are removed.

Note: On first launch, CC Switch automatically imports your existing Claude Code, Codex, Gemini CLI, and Grok Build configuration as a provider named default and adds an official provider for each of these tools and Claude Desktop, so nothing you had configured is lost.

For detailed guides on every feature, check out the User Manual, covering provider management, MCP/Prompts/Skills, local routing & failover, and more.

Features

Full Changelog | v4.0 Release Notes

Supported Features by Tool

Tool Providers Local Routing Aggregation Tray Switching MCP Skills Prompts Sessions Usage Stats
Claude Code Switch ✓ ✓ ✓ ✓ ✓ CLAUDE.md ✓ ✓
Claude Desktop Switch Model Mapping only – ✓ – – – – Model Mapping only
Codex Switch ✓ ✓ ✓ ✓ ✓ AGENTS.md ✓ ✓
Gemini CLI Switch ✓ – ✓ ✓ ✓ GEMINI.md ✓ ✓
Grok Build Switch ✓ – ✓ ✓ ✓ AGENTS.md ✓ ✓
OpenCode Coexist – – – ✓ ✓ AGENTS.md ✓ ✓
OpenClaw Coexist – – – – – Workspace editor ✓ –
Hermes Coexist – – – ✓ ✓ Memory ✓ –
Pi Coexist – – – ✓ ✓ AGENTS.md, SYSTEM.md, prompt templates ✓ ✓
MiniMax Code Coexist – – – ✓ ✓ AGENTS.md ✓ ✓
Kimi Code Coexist – – – ✓ ✓ AGENTS.md ✓ ✓
Oh My Pi Coexist – – – ✓ ✓ AGENTS.md ✓ –
  • Switch: only one provider is active at a time; Coexist: multiple providers are written into the tool's own config at the same time, and you pick one inside the tool.
  • Local Routing: CC Switch forwards requests on your machine and converts API formats; see Local Routing & Failover below. Claude Desktop providers can use "Direct" or "Model Mapping"; with "Model Mapping", requests go through local routing.
  • Aggregation: Puts models from several providers into one model list and sends each request to the provider of the model you pick; see Aggregation Mode below.
  • Sessions: Browse and search conversation history, open the reading view, and copy a resume command to continue a conversation (resuming OpenClaw and Hermes sessions isn't supported yet). Hermes shows only the 500 most recent sessions.
  • Usage Stats: Without local routing, usage is collected from each tool's local session logs; requests that go through local routing are counted as well.
  • The MCP, Skills, Prompts, and Sessions panels opened from the Claude Desktop page apply to Claude Code.

Provider Management

  • 90+ provider presets — Pick a preset and enter your key to add a provider, or create a custom configuration. The add panel lets you search by name (including Chinese names) and domain, and a vendor's different plans and regions are merged into one row
  • Key fields only — Switching replaces only the connection details such as the endpoint, key, and model; plugins, hooks, MCP, settings you added yourself, and comments stay as they are. The editor shows what the config file will look like after switching, and CC Switch automatically backs up each config file before rewriting it for the first time
  • Projects — Save Claude Code's or Codex's current provider, MCP, Skills, and prompt files as a project (for Claude Desktop, only the provider is saved), then switch the whole setup in one click from the project switcher at the top of the page or from the tray; when you switch to another project, the current state is automatically saved back to the previous project. The project switcher is hidden by default; turn on "Show project switcher" in "Settings → General"
  • Accounts (Beta) — Sign in to multiple GitHub Copilot, ChatGPT, and xAI (Grok) accounts under "Accounts" in the sidebar and use those subscriptions as providers in Claude Code, Claude Desktop, and Codex (everything except Codex's OpenAI Official has to be used in Routing mode). Using a subscription outside the official client may violate the vendor's terms of service; assess the risk yourself
  • Third-party providers for Claude Desktop — Connect directly to Anthropic-compatible endpoints; for non-Claude models, choose "Model Mapping" to map tiers like Sonnet, Opus, and Haiku to the provider's actual models through local routing
  • Universal providers — One config syncs to Claude Code, Codex, and Gemini CLI
  • One-click switching, system tray quick switching (Claude Code, Claude Desktop, Codex, Gemini CLI, Grok Build), drag-and-drop sorting, import/export

Local Routing & Failover

  • API format conversion — Local routing converts requests between Anthropic Messages, OpenAI Chat Completions, OpenAI Responses, and Gemini Native: Claude Code and Claude Desktop can use OpenAI- or Gemini-format providers, and Codex and Grok Build can use Chat Completions or Anthropic Messages providers
  • Per-tool toggle — Claude Code, Codex, Gemini CLI, and Grok Build can each enter Routing mode separately: click "Start routing" on the "Routing" tab at the top of the page. In Routing mode, switching providers takes effect immediately for subsequent requests (Codex, Gemini CLI, and Grok Build may still need a restart if the switch changes the model). When you quit CC Switch, it writes the direct configuration back first and reconnects the next time it starts
  • Auto-failover — Configure a failover queue for each tool; when a request fails, CC Switch automatically moves on to the next provider in the queue, backed by a circuit breaker and provider health monitoring
  • Rectifier — Automatically fixes certain requests that some upstreams can't handle (e.g. Thinking signatures, or falling back when images aren't supported)
  • Official providers (e.g. Claude Official) can't go through local routing (except Codex's OpenAI Official)
  • The routing service's status, listen address, and failover settings are all in "Settings → Local routing"
  • Guides: Using GPT in Claude Code · Using Claude in Codex

Aggregation Mode

  • One model list, many providers — On the Claude Code or Codex page, switch to "Aggregation" and add a few providers; their models all appear in the client's model picker. Each request goes to the provider of the model you pick, with no need to switch in CC Switch
  • Add and remove anytime — Click "Add" or "Remove" on a provider card, then pick one provider as the default; requests that don't name an aggregated model go to it. Codex's OpenAI Official can only be the default provider; Claude official subscriptions are currently unsupported in Aggregation
  • Notes — Aggregation doesn't provide failover; Claude Code requires version 2.1.243 or later; Codex needs a restart after the aggregated list changes, while Claude Code doesn't. When you switch models within a session, the new model has to rebuild its prompt cache, so the first turn costs a bit more
  • Much of Aggregation mode's design draws on opencodex — thanks to its author and contributors
  • Documentation: Aggregation mode manual · Illustrated guide (Chinese)

MCP, Prompts & Skills

  • Unified MCP panel — Manage all MCP servers in one place, choose which tools to sync each one to (Claude Code, Codex, Gemini CLI, Grok Build, OpenCode, Hermes, Pi, MiniMax Code, Kimi Code, Oh My Pi), import existing configs from each tool, and import via Deep Link
  • Prompts — A per-tool prompt library with a Markdown editor; enabling a prompt writes it to that tool's prompt file (CLAUDE.md / AGENTS.md / GEMINI.md), and the file's existing content is saved back to the library first, so nothing is lost. Pi can also edit SYSTEM.md, APPEND_SYSTEM.md, and prompt templates
  • Skills — Search skills.sh, or install in one click from GitHub repos or ZIP files; check for updates and update all in one click; sync to each tool automatically, via symlinks only, or via copies only; you can optionally store them in ~/.agents/skills
  • All three panels support search, and MCP and Skills can also be enabled or disabled all at once per tool; providers, MCP servers, and prompts are edited full-page in the content area, and you're warned before leaving with unsaved changes

Usage & Cost Tracking

  • Usage dashboard — Works without local routing: by default it automatically scans each tool's local session logs and tracks requests, tokens, cache hit rate, output speed, and spending by provider and model, with trend charts, a full-year heatmap, and per-request logs
  • Quotas & balances — Provider cards and the tray show what's left and the reset countdown, e.g. "5h 94% left": official subscription quotas (Claude, ChatGPT, Gemini, SuperGrok), Coding Plan 5-hour / weekly / monthly quotas (Kimi, Zhipu GLM, MiniMax, Volcengine Ark, etc.), and account balances (DeepSeek, OpenRouter, SiliconFlow, etc.); some need to be turned on first via "Configure usage query" on the provider card, and for other providers you can write a custom usage script. ChatGPT subscriptions also show remaining limit resets and the Codex Credits balance
  • Custom pricing — Set per-model prices, or import them from models.dev

Session Manager & Workspace

  • Session reading view — Parses each tool's session logs into structured content: text, thinking, tool calls, tool results, and images are shown separately; each turn of work collapses into a one-line summary (how many steps, how many files changed, how many failures), with failed steps marked in red; a conversation outline sits on the right, with in-session search, Markdown export, and copying a single turn or the whole conversation
  • List & resume — Group by project or time, search titles, directories, messages, or session IDs, and delete in bulk; copy a resume command to continue a conversation, and on macOS resume in a terminal with one click
  • Workspace editor (OpenClaw) — Edit agent files (AGENTS.md, SOUL.md, etc.) and daily memory
  • Memory (Hermes) — Edit Hermes's MEMORY.md and USER.md

System & Platform

  • Cloud sync — Sync across devices via WebDAV (Jianguoyun, Nextcloud, Synology NAS, etc.) or S3-compatible storage (AWS S3, Cloudflare R2, Alibaba Cloud OSS, Tencent Cloud COS, etc.); you can also put the CC Switch configuration directory in a cloud drive folder such as Dropbox, OneDrive, or iCloud
  • CLI tool management — On the "Apps" page in the sidebar, see the current and latest versions of command-line tools like Claude Code and Codex, install, upgrade, or upgrade all in one click, and diagnose duplicate installations; on Windows it can also manage tools inside WSL (see FAQ)
  • Deep Link (ccswitch://) — Import providers, MCP servers, and prompts, or add skill repositories, in one click via a link; create links with the online generator; site owners who want an import button can follow the integration guide
  • Built-in utilities — Skip Claude Code's first-run confirmation, hide AI attribution, have the VS Code Claude Code extension follow CC Switch's provider switches, and more
  • Dark / Light / System theme, auto-launch, auto-updater, atomic writes, auto-backups (see where every backup lives and how much space it takes in "Settings → Data"), i18n (Simplified Chinese, Traditional Chinese, English, Japanese, Korean, Turkish, Russian, German)

FAQ

Which AI tools does CC Switch support?

CC Switch supports twelve tools: Claude Code, Claude Desktop, Codex, Gemini CLI, Grok Build, OpenCode, OpenClaw, Hermes, Pi, MiniMax Code, Kimi Code, Oh My Pi. Each tool has dedicated provider presets and configuration management; see Supported Features by Tool for what each one supports.

Do I need to restart the terminal after switching providers?

It depends on the tool:

  • Claude Code: supports hot-switching of provider data — no restart needed.
  • Codex, Gemini CLI, Grok Build: restart your terminal or the CLI tool for changes to take effect (CC Switch reminds you after switching). In Routing mode, requests go to the new provider immediately, but all three tools may still need a restart if the switch changes the model.
  • Aggregation mode: changes to Claude Code's aggregated models take effect immediately; for Codex, entering or leaving Aggregation and changing the aggregated model list all require a full restart — see the next entry.
  • Claude Desktop: fully quit and reopen Claude Desktop; when using "Model Mapping", also keep CC Switch running.
  • OpenCode, OpenClaw, Hermes, Pi, MiniMax Code, Kimi Code, Oh My Pi: these are coexist-mode tools — clicking "Add" ("Enable" for Pi and Oh My Pi) writes the provider into the tool's own config alongside the others; you then pick the model you want inside the tool. Kimi Code also provides a "Switch" button to select a provider's model; models still referenced as primary or secondary models cannot be removed. See the Kimi Code integration guide (Chinese) for configuration and account details.
In Aggregation mode, why don't the aggregated models show up in Codex's /model?

Codex reads its model list only at startup. After entering or leaving Aggregation mode, adding or removing an aggregated provider, or changing a provider's aggregated models, fully restart Codex to see the new list:

  • Codex CLI: Closing the terminal and running codex again isn't enough. Every codex in every terminal shares one background daemon, and it has to be restarted to pick up the new list. When CC Switch detects that Codex is still using the old list, it shows a notice at the top of the Codex page; click "Restart Codex daemon" in the notice. Restarting interrupts any tasks running in the daemon.
  • Codex desktop app: Quit it completely and reopen it (press ⌘Q on macOS; closing the window isn't enough).
  • Editor extensions: Reopen the editor window.

Claude Code isn't affected: changes to aggregated models take effect immediately.

Will switching providers change my plugins, hooks, or other settings?

No. When you switch providers for Claude Code, Codex, Gemini CLI, or Grok Build, CC Switch replaces only the key fields in the config file: the endpoint, key, model name, and API protocol (plus the reasoning effort for Codex and the auth method for Gemini CLI), along with a few compatibility options that belong to the provider (such as Claude Code's "Disable Artifact Tool" and the context window). Plugins, hooks, permissions, MCP, environment variables you added yourself, comments, and formatting all stay as they are and apply to every provider.

You can change these shared settings in the tool itself or by editing the config file by hand. You can also edit any provider in CC Switch: the editor shows "what the config file will look like after switching to this provider". When you save, the key fields are stored in that provider, and every other change is written to the config file and applies to every provider.

So the old "Common Config Snippet" is no longer needed, and its buttons have been removed. Settings that were in your snippet before the upgrade were already written into the config file when you switched, so they stay. Before CC Switch rewrites each config file for the first time, it also backs up the original to ~/.cc-switch/backups/live-first-write/.

I changed the model inside the tool — why does it go back after I switch away and back?

The model is a key field and belongs to the provider. A model you pick inside the tool (such as with /model in Claude Code) stays in effect until the next switch; when you switch, the model in the config file is replaced with the one saved in the target provider, and CC Switch doesn't save the model you picked back to the previous provider. To keep using a model long-term, edit that provider in CC Switch.

Older versions saved the whole config file back to the provider when you switched away. That no longer happens: it froze plugins and other shared settings into one provider, so they were lost when you switched to another one.

Why can't I delete the provider currently in use?

CC Switch follows a "minimal intrusion" design principle — even if you uninstall the app, your tools will continue to work normally.

So for tools that use one active provider at a time (Claude Code, Claude Desktop, Codex, Gemini CLI, Grok Build), the system always keeps one configuration in use, because deleting all configurations would make the corresponding tool unusable; to delete it, switch to another provider first. Likewise, the default provider in Aggregation mode can't be removed; make another provider the default first. Coexist-mode tools (OpenCode, OpenClaw, Hermes, Pi, and MiniMax Code) aren't subject to this restriction — you can delete any provider directly. If you rarely use a tool, you can hide it from the sidebar on the "Apps" page. To switch back to official login, see the next question.

How do I switch back to official login?

In CC Switch, the provider lists for Claude Code, Claude Desktop, Codex, Gemini CLI, and Grok Build each include a built-in official provider (Claude Official, Claude Desktop Official, OpenAI Official, Google Official, Grok Official); if you deleted it, add it back from the presets. After switching to the official provider, follow the tool's own login flow (e.g. /login in Claude Code, codex login for Codex), and then you can freely switch between the official provider and third-party providers.

For Codex, you can also sign in to multiple ChatGPT accounts inside CC Switch via "Sign in with ChatGPT" and choose an "Account to use" for each OpenAI Official card, so switching between multiple Plus, Pro, or Team accounts takes one click; cards set to "Follow Codex login" keep using the Codex CLI's own login.

Note: official subscriptions use the tool's own login and don't go through local routing. Official providers can't be selected in Routing mode (Codex's OpenAI Official cards are the exception); switch back to Direct first.

After I start routing, why does my config file point to 127.0.0.1?

In Routing mode, the tool's requests first go to CC Switch's local routing (http://127.0.0.1:15721 by default), and CC Switch then forwards them to the provider you selected. That's why the tool's config file only contains the local address and the placeholder key PROXY_MANAGED; for Claude Code, the model name is also written as a fixed alias such as claude-sonnet-5 (the /model menu still shows the real model name). The real provider address, key, and model are all stored in CC Switch. Aggregation mode works the same way.

In the request logs under "Usage" in the sidebar, you can see "requested model → actual model" for each request.

In Routing mode, switching changes the provider that routing uses; the provider you were using before you entered Routing stays the same and is labeled "Direct" on its card. When you click "Back to direct", the config file is written back to this direct provider's configuration. Quitting CC Switch also writes back the direct provider first, and it reconnects the next time CC Switch starts.

Can I use OpenAI-compatible APIs, Gemini, or local models in Claude Code?

Yes, but you need to use Routing. When editing the provider, set "Upstream Format" under "Advanced Options" to match the provider's API: choose "OpenAI Chat Completions" for services that only offer a Chat Completions endpoint (as many local model servers do), "OpenAI Responses API" for services that offer a Responses endpoint, and "Gemini Native generateContent" for Gemini. Then click "Start routing" on the "Routing" tab of the Claude Code page. Choosing the wrong format or not starting routing usually results in a 404 or 405 error.

Conversely, choosing "Anthropic Messages" as the "Upstream Format" in Codex or Grok Build lets you use Claude-format providers; this also requires Routing. See Using GPT in Claude Code and Using Claude in Codex for details.

"Connectivity check" passed, so why do requests still fail?

The "Connectivity check" on a provider card only checks whether the provider address is reachable; it doesn't send a real model request, so it can't verify whether the API key and model name are correct. When requests fail, check the key, model name, and upstream format; for requests that go through Routing, you can also see the exact error in the request logs under "Usage" in the sidebar.

Where is my data stored?

By default, everything is stored in the .cc-switch folder in your home directory (C:\Users\<user>\.cc-switch on Windows):

  • Database: cc-switch.db (SQLite — providers, MCP, prompts, Skills, projects, usage records, etc.)
  • Local settings: settings.json (device-level settings such as each tool's config directory, backup policy, and cloud sync connection details)
  • Backups: backups/ (backed up automatically every 24 hours by default, keeping the 10 most recent; adjustable in "Settings → Data → Backup & Restore"; "Other Backups" below it lists the location and size of every other backup, which you can clean up by category)
  • Skills: skills/ (can be changed to ~/.agents/skills in Settings), synced to each tool via symlinks by default, falling back to copying if that fails
  • Skill Backups: skill-backups/ (created automatically before uninstalling or updating a skill, keeping the 20 most recent)
  • OAuth login credentials: copilot_auth.json, codex_oauth_auth.json, xai_oauth_auth.json
  • Logs: logs/cc-switch.log and crash.log — please attach them when reporting an issue
  • Device state: live-state.json (whether each tool is currently in Direct, Routing, or Aggregation mode, and what was last written), codex-login-stash.json (the official Codex login moved aside when you switch to a third-party provider, restored when you switch back to an official one)
  • Original config files: backups/live-first-write/ (each tool's config file as it was before CC Switch first rewrote it)

After you change "CC Switch Configuration Directory" in "Settings → Data → Location", all of the files above except settings.json, the device state, and the original config files are stored in the new directory. CC Switch doesn't move existing files automatically, so copy them over manually first. settings.json, the device state, and the original config files belong to this computer only: they always stay in the default directory and are not included in cloud sync.

How do I manage tools inside WSL on Windows?

CC Switch doesn't detect WSL automatically. In "Settings → App config", change the config directory for the corresponding tool to a path inside WSL, e.g. \\wsl.localhost\Ubuntu\home\<user>\.claude; after you save, CC Switch reads and writes the config inside WSL (supported for Claude Code, Codex, Gemini CLI, Grok Build, OpenCode, OpenClaw, Hermes, and Pi). Once this is set, the "Apps" page in the sidebar also detects and upgrades that tool in the corresponding WSL distribution.

Note: Routing and Aggregation write 127.0.0.1 as the address into the config. In WSL2's default NAT networking mode, 127.0.0.1 inside WSL can't reach local routing on Windows; switch WSL to mirrored networking mode instead.

Is there a command-line or headless version?

CC Switch itself only ships as a desktop app that requires a graphical interface (see Download & Installation for system requirements). For servers, SSH sessions, or machines without a desktop environment, we recommend the community-maintained CC Switch CLI: it offers both an interactive terminal UI (TUI) and a command-line mode, supports Claude Code, Codex, Gemini CLI, OpenCode, OpenClaw, Hermes, and Pi, and can be installed via Homebrew (brew install cc-switch-cli) or an install script.

By default, CC Switch CLI shares the ~/.cc-switch data directory with the desktop app and is compatible with the desktop app's WebDAV sync. The two projects are released separately, and the database version the CLI supports sometimes lags behind the desktop app; if you see a "database version is too new" message, upgrade the CLI or wait for it to catch up.

Linux (Wayland + NVIDIA): clicks don't register and the window black-screens on resize

The AppImage forces GDK_BACKEND=x11 (XWayland) to avoid a historical native-Wayland crash. On newer Wayland + NVIDIA setups this can leave the web content area unclickable (the title-bar buttons still work) and black-screen on resize. Launch with the opt-in escape hatch to switch back to native Wayland:

CC_SWITCH_GDK_BACKEND=wayland ./CC-Switch-*.AppImage

If you launch from a desktop icon, add it to the .desktop Exec= line (e.g. env CC_SWITCH_GDK_BACKEND=wayland /path/to/AppImage) or set it in your session environment. The variable is generic: on tiling Wayland compositors (sway/Hyprland) where clicks don't register, try CC_SWITCH_GDK_BACKEND=x11 instead. Leaving it unset keeps the default behavior.

For more questions, see the FAQ in the User Manual.

Contributing

Issues and suggestions are welcome! Before developing a new feature, please open an issue to discuss the approach first; feature PRs that aren't a good fit for the project may be closed.

For development setup, pre-submit checks, and architecture notes, see

Recent activity

commits and pull requests

Releases and announcements

91 total
  1. CC Switch v4.0.35v4.0.35Nov 18, 202692.6K downloads

    # CC Switch v4.0.35 本版本让 Claude Code / Claude Desktop 里用 ChatGPT 账号的 Codex 卡片能用上 **GPT-6.2**,会话管理里可以看到 Codex `/goal` 的**完整目标**,请求详情里的请求 ID 可以**一键复制**。 另外修复了 Claude Code 的 auto 模式在关不掉思考的模型上被整体拦下;Codex 聚合模式和「打开终端」报 Responses-Lite 需要 `reasoning.context`;Codex 压缩上下文后第一条请求被拒;用量页自定义日期选到很早的年份时卡死;Skill 的托管副本不在了就卸载不掉等问题。 **[English →](https://github.com/farion1231/cc-switch/blob/main/docs/release-notes/v4.0.35-en.md) | [日本語版 →](https://github.com/farion1231/cc-switch/blob/main/docs/release-notes/v4.0.35-ja.md)** --- ## 新增 ### 会话管理里显示 Codex `/goal` 的完整目标 目标超过 700 字节时,Codex 注入的上下文里不写目标内容,会话管理里也就看不到目标(见 [#9647](https://github.com/farion1231/cc-switch/issues/9647))。现在从会话记录里读出完整目标,显示成一步「目标 · 状态」,展开即是完整内容;目标和状态都没变的重复记录不再显示。 ### 请求详情里可以复制完整的请求 ID 请求详情里过长的值会被省略号截断,像 Codex 的 `resp_...` 这类长请求 ID 没法完整复制去对日志(见 [#9681](https://github.com/farion1231/cc-switch/issues/9681))。现在请求 ID 后面多了一个复制按钮。 ### 新增 GPT-6.2 Sol / Astra 的价格 按官方标准档(272K 以内)的价格计费;长上下文档、Batch / Fast 等档位和 GPT-6 一样暂不区分。 --- ## 修复 - **Claude Code / Claude Desktop 里用 ChatGPT 账号的 Codex 卡片获取不到 GPT-6.2,手动填了也报「not supported when using Codex with a ChatGPT account」**([#9678](https://github.com/farion1231/cc-switch/pull/9678),见 [#9670](h

  2. CC Switch v4.0.34v4.0.34Nov 17, 202672.4K downloads

    # CC Switch v4.0.34 本版本的技能仓库支持 **GitLab、Gitea 和 Forgejo**(包括自建实例和 Codeberg),不再只能添加 GitHub 上的仓库。会话管理里现在可以直接删除 **Antigravity CLI** 的会话;开启自动下载更新后,发现新版本会立刻开始下载。另外,WorkBuddy 手动添加的模型可以设置思考强度,S3 同步也可以像 WebDAV 一样清除本机保存的配置。 另外修复了 Gemini CLI 的供应商「获取模型列表」报 Key 无效或拿到空列表;Codex 里的 GitHub Copilot 模型被当成不支持图片;阿里云 OSS、腾讯云 COS、华为云 OBS 用不了 S3 同步;Skills 目录里有失效链接时整个云同步上传失败;路由模式下 Fable 5.2 被显示成 Fable 5;Copilot 上的 Gemini 模型缓存命中率低;Copilot 上勾了 1M 的 Fable 模型请求失败等问题。 **[English →](https://github.com/farion1231/cc-switch/blob/main/docs/release-notes/v4.0.34-en.md) | [日本語版 →](https://github.com/farion1231/cc-switch/blob/main/docs/release-notes/v4.0.34-ja.md)** --- ## 新增 ### 技能仓库支持 GitLab、Gitea 和 Forgejo 「管理技能仓库」以前只接受 github.com 的地址,现在也能添加 GitLab、Gitea、Forgejo 上的公开仓库(需求见 [#1324](https://github.com/farion1231/cc-switch/issues/1324)、[#4227](https://github.com/farion1231/cc-switch/pull/4227)),包括自建实例和 Codeberg: - 填 `owner/name` 仍按 GitHub 处理;填其他站点的完整地址时,CC Switch 会先问一次这个站点是 Gitea / Forgejo 还是 GitLab,再按对应的方式下载。自定义端口、GitLab 的多级分组、Gitea 页面上复制的地址都能用。 - 浏览技能、安装、检查更新和「打开文档」链接都会去仓库所在的站点。 - 只支持公开仓库,地址必须是 https。Gitee 暂不支持(它的下载接口需要令牌)。 - 同一个 `owner/name` 只能保留在一个站点上,在另一个站点添加同名仓库会替换原来的。 ### 在会话管理里删除 Antigravity CLI 会话

  3. CC Switch v4.0.33v4.0.33Nov 16, 202692.7K downloads

    # CC Switch v4.0.33 本版本修复了从第三方供应商切回 Claude 官方后,已经开着的 Claude Code 会话仍把请求发给上一家、要重开会话才恢复的问题。套餐额度查询新增 **Ollama Cloud**;授权中心的 **Antigravity 账号切换**现在也支持 Windows。 另外修复了 Claude Code / Claude Desktop 的供应商选 Gemini Native 格式时获取模型列表总报「API Key 无效或无权限」;部分服务商获取模型列表被 Cloudflare 拦下;Antigravity Orchestrator 仍有部分请求显示未定价;WebDAV 同步在一些 NAS 上完全用不了;WebDAV / S3 上传失败只显示「请求构造失败」;查询 xAI 额度时遇到网络抖动就被要求重新登录;更新 Skill 中途失败把原来的 Skill 删掉等问题。 **[English →](https://github.com/farion1231/cc-switch/blob/main/docs/release-notes/v4.0.33-en.md) | [日本語版 →](https://github.com/farion1231/cc-switch/blob/main/docs/release-notes/v4.0.33-ja.md)** --- ## 新增 ### Ollama Cloud 套餐额度 地址是 `ollama.com` 的供应商现在可以查询 Token Plan 额度(需求见 [#9382](https://github.com/farion1231/cc-switch/issues/9382)):现行套餐显示本期套餐内额度的剩余比例和重置时间,旧版套餐显示 5 小时和每周两个窗口的剩余比例。单独购买的额度不显示;按量付费的账号没有套餐额度,会说明原因。本机运行的 Ollama(`localhost:11434`)没有套餐,不会被识别。 - 新添加或一键导入的 Ollama Cloud 供应商默认开启额度查询;已有的供应商在卡片上点「配置用量查询」,Token Plan 模板会自动选好,打开「启用用量查询」后保存即可。 ### Windows 上切换 Antigravity 账号 授权中心的 Antigravity 账号切换以前只支持 macOS,现在 Windows 也能用:切换后 agy 读到的是新账号,Antigravity 官方卡可以绑定账号、查看所绑账号的额度,打开终端前也会提示将切换到哪个账号。Linux 暂不支持。 --- ## 修复 - **从第三方供应商切回 Claude 官方后,已经开着的 Claude Code 会话仍把请求发给上一家,要重开

  4. CC Switch v4.0.32v4.0.32Nov 14, 202681.2K downloads

    # CC Switch v4.0.32 本版本新增**后台自动下载更新**:在「设置 → 关于」打开「自动下载更新」后,新版本会在后台下载并校验好,右下角弹出提示问你是否安装,不会未经确认就重启。「设置 → 网络」新增 **IP 检测**,可以查看 CC Switch 经全局代理、临时代理或当前网络访问时的出口 IP 和所在地区。 另外修复了 Codex 经路由换供应商续接旧会话后,上游先回 200 再报「无法解密」导致整轮报废;Codex 经路由或聚合接 Mistral AI 时请求报 422;CC Switch 内部某个操作崩溃一次后,托盘变空、切不了供应商,直到重启;用 mise 装的工具在「应用」页显示两条安装记录等问题。 **[English →](https://github.com/farion1231/cc-switch/blob/main/docs/release-notes/v4.0.32-en.md) | [日本語版 →](https://github.com/farion1231/cc-switch/blob/main/docs/release-notes/v4.0.32-ja.md)** --- ## 新增 ### 后台自动下载更新 「设置 → 关于」新增「自动下载更新」开关,默认关闭,每台设备单独设置。 - 打开后,CC Switch 启动一分钟后检查一次,之后每六小时检查一次,有新版本就在后台下载并校验。 - 下载好后,主界面右下角会问你是否安装。安装会重启 CC Switch,正在经本地路由的请求会中断,所以一定要你点「安装并重启」才会进行;路由开着时提示里会写明这一点。 - 点「稍后」只是不再为这个版本弹提示,设置里的红点、「关于」页的按钮,以及托盘菜单和快捷面板里新增的「重启并更新到 vX」仍然可以安装。 - 便携版和 Linux 的 deb / rpm 安装包不能自动安装,开关会置灰并说明原因。 ### IP 检测 「设置 → 网络」在全局代理下方新增 IP 检测([#9449](https://github.com/farion1231/cc-switch/pull/9449),需求见 [#9448](https://github.com/farion1231/cc-switch/issues/9448)):选已保存的全局代理或填一个临时代理(只用于这次检测,不保存),点「检测 IP」后会显示出口 IP、两个检测服务的结果是否一致,以及国家或地区、城市、运营商等信息。没设全局代理时,按系统代理或直连检测;指定了代理时,代理连不上不会改用直连。 - 只在点击后运行,会访问 icanhazip.com、ipify.org,并把测得的 IP 发给 ipwho.is 查询位置。 - 测的是 CC Swit

  5. CC Switch v4.0.31v4.0.31Nov 12, 2026129.2K downloads

    # CC Switch v4.0.31 本版本新增受管应用**腾讯 WorkBuddy**:自定义模型写进 WorkBuddy 自己的模型配置,在 WorkBuddy 里直接就能选;还能在多个 WorkBuddy 账号之间切换,切换前先看到每个号的套餐、剩余积分和到期时间。界面新增**德语**,README 也有了全部八种界面语言的版本。 另外修复了 Claude Code 经路由连 OpenAI Responses 格式的中转时,会话被同一个中转分到不同 Azure 资源后每一轮都报 400、再也继续不了;经路由连 Gemini Native 格式上游时,并行工具调用报 400、缓存命中率很低;macOS 托盘悬停提示一直挂在屏幕上;Codex 续接的旧对话用量从不导入等问题。 **[English →](https://github.com/farion1231/cc-switch/blob/main/docs/release-notes/v4.0.31-en.md) | [日本語版 →](https://github.com/farion1231/cc-switch/blob/main/docs/release-notes/v4.0.31-ja.md)** --- ## 新增 ### WorkBuddy 腾讯 WorkBuddy 成为新的受管应用([#8757](https://github.com/farion1231/cc-switch/pull/8757),需求见 [#4802](https://github.com/farion1231/cc-switch/issues/4802)、[#5802](https://github.com/farion1231/cc-switch/issues/5802)、[#7419](https://github.com/farion1231/cc-switch/issues/7419)、[#7076](https://github.com/farion1231/cc-switch/issues/7076))。和 OpenCode 一样是多个供应商同时生效: - **自定义模型**:点「添加」后,供应商的模型写进 WorkBuddy 自己的 `models.json`,在 WorkBuddy 的模型选择里显示为「名称:模型 ID」,名称留空时用「厂商标签」。WorkBuddy 里自己添加的模型原样保留。WorkBuddy 的自定义模型只支持 OpenAI Chat Completions 格式。 - 预设里的模型在 WorkBuddy 的模型选择里可以选思考强度(例如 Kimi K3.1 Pro 的 low / high / max)。 - WorkBuddy 暂时不支持同一个模型 ID

Code frequency

additions and deletions
+146.1K-146.1KWeek of 2025-11-23: +17,696 linesWeek of 2025-11-23: -10,286 linesWeek of 2025-11-30: +14,025 linesWeek of 2025-11-30: -176 linesWeek of 2025-12-07: +9,811 linesWeek of 2025-12-07: -4,179 linesWeek of 2025-12-14: +5,779 linesWeek of 2025-12-14: -2,008 linesWeek of 2025-12-21: +7,818 linesWeek of 2025-12-21: -2,485 linesWeek of 2025-12-28: +6,606 linesWeek of 2025-12-28: -2,128 linesWeek of 2026-01-04: +2,631 linesWeek of 2026-01-04: -745 linesWeek of 2026-01-11: +8,467 linesWeek of 2026-01-11: -2,393 linesWeek of 2026-01-18: +4,935 linesWeek of 2026-01-18: -879 linesWeek of 2026-01-25: +4,982 linesWeek of 2026-01-25: -1,435 linesWeek of 2026-02-01: +9,184 linesWeek of 2026-02-01: -1,327 linesWeek of 2026-02-08: +16,186 linesWeek of 2026-02-08: -1,513 linesWeek of 2026-02-15: +7,178 linesWeek of 2026-02-15: -2,925 linesWeek of 2026-02-22: +9,674 linesWeek of 2026-02-22: -7,140 linesWeek of 2026-03-01: +28,009 linesWeek of 2026-03-01: -18,609 linesWeek of 2026-03-08: +11,150 linesWeek of 2026-03-08: -2,531 linesWeek of 2026-03-15: +7,276 linesWeek of 2026-03-15: -1,376 linesWeek of 2026-03-22: +2,956 linesWeek of 2026-03-22: -630 linesWeek of 2026-03-29: +11,918 linesWeek of 2026-03-29: -1,708 linesWeek of 2026-04-05: +20,495 linesWeek of 2026-04-05: -2,227 linesWeek of 2026-04-12: +16,890 linesWeek of 2026-04-12: -3,374 linesWeek of 2026-04-19: +10,421 linesWeek of 2026-04-19: -3,335 linesWeek of 2026-04-26: +5,611 linesWeek of 2026-04-26: -1,529 linesWeek of 2026-05-03: +5,234 linesWeek of 2026-05-03: -651 linesWeek of 2026-05-10: +12,242 linesWeek of 2026-05-10: -3,705 linesWeek of 2026-05-17: +14,822 linesWeek of 2026-05-17: -1,576 linesWeek of 2026-05-24: +16,106 linesWeek of 2026-05-24: -4,347 linesWeek of 2026-05-31: +15,005 linesWeek of 2026-05-31: -1,920 linesWeek of 2026-06-07: +11,362 linesWeek of 2026-06-07: -2,309 linesWeek of 2026-06-14: +6,266 linesWeek of 2026-06-14: -3,195 linesWeek of 2026-06-21: +6,673 linesWeek of 2026-06-21: -836 linesWeek of 2026-06-28: +9,854 linesWeek of 2026-06-28: -3,336 linesWeek of 2026-07-05: +13,936 linesWeek of 2026-07-05: -2,095 linesWeek of 2026-07-12: +13,318 linesWeek of 2026-07-12: -1,821 linesWeek of 2026-07-19: +22,089 linesWeek of 2026-07-19: -6,662 linesWeek of 2026-07-26: +13,956 linesWeek of 2026-07-26: -5,710 linesWeek of 2026-08-02: +13,183 linesWeek of 2026-08-02: -1,644 linesWeek of 2026-08-09: +40,016 linesWeek of 2026-08-09: -3,917 linesWeek of 2026-08-16: +15,225 linesWeek of 2026-08-16: -3,634 linesWeek of 2026-08-23: +10,072 linesWeek of 2026-08-23: -1,633 linesWeek of 2026-08-30: +5,745 linesWeek of 2026-08-30: -281 linesWeek of 2026-09-06: +9,146 linesWeek of 2026-09-06: -1,045 linesWeek of 2026-09-13: +5,268 linesWeek of 2026-09-13: -470 linesWeek of 2026-09-20: +20,393 linesWeek of 2026-09-20: -6,045 linesWeek of 2026-09-27: +146,125 linesWeek of 2026-09-27: -75,129 linesWeek of 2026-10-04: +37,292 linesWeek of 2026-10-04: -8,833 linesWeek of 2026-10-11: +58,778 linesWeek of 2026-10-11: -9,896 linesWeek of 2026-10-18: +71,720 linesWeek of 2026-10-18: -25,785 linesWeek of 2026-10-25: +32,826 linesWeek of 2026-10-25: -4,592 linesWeek of 2026-11-01: +27,809 linesWeek of 2026-11-01: -4,299 linesWeek of 2026-11-08: +65,915 linesWeek of 2026-11-08: -10,191 linesWeek of 2026-11-15: +63,128 linesWeek of 2026-11-15: -51,156 linesNov 23, 2025Nov 15, 2026
+1M lines added, -321.7K removed over the last year.

Commits per week

last 52 weeks
2340Week of 2025-11-23: 62 commitsWeek of 2025-11-30: 16 commitsWeek of 2025-12-07: 23 commitsWeek of 2025-12-14: 44 commitsWeek of 2025-12-21: 26 commitsWeek of 2025-12-28: 32 commitsWeek of 2026-01-04: 38 commitsWeek of 2026-01-11: 52 commitsWeek of 2026-01-18: 43 commitsWeek of 2026-01-25: 36 commitsWeek of 2026-02-01: 54 commitsWeek of 2026-02-08: 24 commitsWeek of 2026-02-15: 35 commitsWeek of 2026-02-22: 44 commitsWeek of 2026-03-01: 36 commitsWeek of 2026-03-08: 56 commitsWeek of 2026-03-15: 22 commitsWeek of 2026-03-22: 15 commitsWeek of 2026-03-29: 49 commitsWeek of 2026-04-05: 88 commitsWeek of 2026-04-12: 57 commitsWeek of 2026-04-19: 71 commitsWeek of 2026-04-26: 42 commitsWeek of 2026-05-03: 16 commitsWeek of 2026-05-10: 69 commitsWeek of 2026-05-17: 53 commitsWeek of 2026-05-24: 53 commitsWeek of 2026-05-31: 47 commitsWeek of 2026-06-07: 58 commitsWeek of 2026-06-14: 35 commitsWeek of 2026-06-21: 37 commitsWeek of 2026-06-28: 50 commitsWeek of 2026-07-05: 41 commitsWeek of 2026-07-12: 37 commitsWeek of 2026-07-19: 44 commitsWeek of 2026-07-26: 48 commitsWeek of 2026-08-02: 24 commitsWeek of 2026-08-09: 50 commitsWeek of 2026-08-16: 23 commitsWeek of 2026-08-23: 33 commitsWeek of 2026-08-30: 22 commitsWeek of 2026-09-06: 50 commitsWeek of 2026-09-13: 14 commitsWeek of 2026-09-20: 58 commitsWeek of 2026-09-27: 157 commitsWeek of 2026-10-04: 172 commitsWeek of 2026-10-11: 234 commitsWeek of 2026-10-18: 186 commitsWeek of 2026-10-25: 144 commitsWeek of 2026-11-01: 123 commitsWeek of 2026-11-08: 132 commitsWeek of 2026-11-15: 121 commitsNov 23, 2025Nov 15, 2026
3.1K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 18 commitsSun 1:00 — 2 commitsSun 2:00 — 6 commitsSun 3:00 — 0 commitsSun 4:00 — 1 commitsSun 5:00 — 2 commitsSun 6:00 — 0 commitsSun 7:00 — 2 commitsSun 8:00 — 7 commitsSun 9:00 — 10 commitsSun 10:00 — 29 commitsSun 11:00 — 22 commitsSun 12:00 — 21 commitsSun 13:00 — 10 commitsSun 14:00 — 3 commitsSun 15:00 — 20 commitsSun 16:00 — 41 commitsSun 17:00 — 41 commitsSun 18:00 — 15 commitsSun 19:00 — 25 commitsSun 20:00 — 53 commitsSun 21:00 — 36 commitsSun 22:00 — 64 commitsSun 23:00 — 69 commitsMon 0:00 — 11 commitsMon 1:00 — 5 commitsMon 2:00 — 2 commitsMon 3:00 — 4 commitsMon 4:00 — 3 commitsMon 5:00 — 2 commitsMon 6:00 — 0 commitsMon 7:00 — 0 commitsMon 8:00 — 15 commitsMon 9:00 — 34 commitsMon 10:00 — 44 commitsMon 11:00 — 55 commitsMon 12:00 — 41 commitsMon 13:00 — 5 commitsMon 14:00 — 3 commitsMon 15:00 — 44 commitsMon 16:00 — 44 commitsMon 17:00 — 31 commitsMon 18:00 — 16 commitsMon 19:00 — 9 commitsMon 20:00 — 14 commitsMon 21:00 — 37 commitsMon 22:00 — 77 commitsMon 23:00 — 57 commitsTue 0:00 — 10 commitsTue 1:00 — 0 commitsTue 2:00 — 5 commitsTue 3:00 — 1 commitsTue 4:00 — 2 commitsTue 5:00 — 2 commitsTue 6:00 — 1 commitsTue 7:00 — 1 commitsTue 8:00 — 15 commitsTue 9:00 — 43 commitsTue 10:00 — 53 commitsTue 11:00 — 37 commitsTue 12:00 — 28 commitsTue 13:00 — 6 commitsTue 14:00 — 6 commitsTue 15:00 — 36 commitsTue 16:00 — 62 commitsTue 17:00 — 31 commitsTue 18:00 — 12 commitsTue 19:00 — 17 commitsTue 20:00 — 18 commitsTue 21:00 — 28 commitsTue 22:00 — 46 commitsTue 23:00 — 59 commitsWed 0:00 — 19 commitsWed 1:00 — 1 commitsWed 2:00 — 0 commitsWed 3:00 — 0 commitsWed 4:00 — 1 commitsWed 5:00 — 4 commitsWed 6:00 — 1 commitsWed 7:00 — 18 commitsWed 8:00 — 17 commitsWed 9:00 — 37 commitsWed 10:00 — 45 commitsWed 11:00 — 50 commitsWed 12:00 — 24 commitsWed 13:00 — 22 commitsWed 14:00 — 9 commitsWed 15:00 — 35 commitsWed 16:00 — 43 commitsWed 17:00 — 26 commitsWed 18:00 — 9 commitsWed 19:00 — 8 commitsWed 20:00 — 11 commitsWed 21:00 — 25 commitsWed 22:00 — 46 commitsWed 23:00 — 63 commitsThu 0:00 — 10 commitsThu 1:00 — 4 commitsThu 2:00 — 1 commitsThu 3:00 — 1 commitsThu 4:00 — 2 commitsThu 5:00 — 2 commitsThu 6:00 — 6 commitsThu 7:00 — 4 commitsThu 8:00 — 16 commitsThu 9:00 — 40 commitsThu 10:00 — 32 commitsThu 11:00 — 38 commitsThu 12:00 — 30 commitsThu 13:00 — 5 commitsThu 14:00 — 5 commitsThu 15:00 — 47 commitsThu 16:00 — 59 commitsThu 17:00 — 54 commitsThu 18:00 — 8 commitsThu 19:00 — 12 commitsThu 20:00 — 21 commitsThu 21:00 — 40 commitsThu 22:00 — 65 commitsThu 23:00 — 61 commitsFri 0:00 — 17 commitsFri 1:00 — 2 commitsFri 2:00 — 1 commitsFri 3:00 — 0 commitsFri 4:00 — 0 commitsFri 5:00 — 2 commitsFri 6:00 — 0 commitsFri 7:00 — 1 commitsFri 8:00 — 23 commitsFri 9:00 — 40 commitsFri 10:00 — 28 commitsFri 11:00 — 50 commitsFri 12:00 — 26 commitsFri 13:00 — 12 commitsFri 14:00 — 12 commitsFri 15:00 — 53 commitsFri 16:00 — 56 commitsFri 17:00 — 31 commitsFri 18:00 — 20 commitsFri 19:00 — 11 commitsFri 20:00 — 43 commitsFri 21:00 — 41 commitsFri 22:00 — 54 commitsFri 23:00 — 66 commitsSat 0:00 — 8 commitsSat 1:00 — 7 commitsSat 2:00 — 0 commitsSat 3:00 — 1 commitsSat 4:00 — 0 commitsSat 5:00 — 2 commitsSat 6:00 — 1 commitsSat 7:00 — 2 commitsSat 8:00 — 24 commitsSat 9:00 — 22 commitsSat 10:00 — 29 commitsSat 11:00 — 38 commitsSat 12:00 — 23 commitsSat 13:00 — 13 commitsSat 14:00 — 5 commitsSat 15:00 — 23 commitsSat 16:00 — 37 commitsSat 17:00 — 31 commitsSat 18:00 — 19 commitsSat 19:00 — 20 commitsSat 20:00 — 39 commitsSat 21:00 — 63 commitsSat 22:00 — 64 commitsSat 23:00 — 58 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.

Who is committing

last 52 weeks
Maintainer commits2,200 (71%)
Community commits907 (29%)

3,107 commits in total over the last year.

DateListRankStars gained
Jul 26, 2026daily#15+3
Jul 21, 2026daily#21+3
Jul 13, 2026daily#17+3
Jul 12, 2026daily#23+2
Jul 7, 2026daily#18+6
Jul 2, 2026daily#14+26
Jun 29, 2026daily#20+11
Jun 27, 2026daily#25+27
Jun 25, 2026daily#19+18
Jun 18, 2026daily#11+20
Jun 17, 2026daily#25+11
Jun 16, 2026daily#4+27
Jun 15, 2026daily#12+24
Jun 14, 2026daily#11+47
Jun 13, 2026daily#18+36
  • public-apis/public-apis

    A collective list of free APIs

    500.5K stars · Python

  • morluto/rea

    Reverse engineer anything with agents, from app behavior down to native binaries.

    471.6K stars · TypeScript

  • obra/superpowers

    An agentic skills framework & software development methodology that works.

    322.9K stars · Shell

  • affaan-m/ECC

    The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

    307.9K stars · JavaScript

  • NousResearch/hermes-agent

    The agent that grows with you

    265K stars · Python

  • n8n-io/n8n

    Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

    211.6K stars · TypeScript