lidge-jun/opencodexPublic

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

AI summary: Universal proxy translating proprietary requests from locked-down AI apps to any local or cloud LLM.

Stars
18.7K
+91 today
Forks
1.5K
Watchers
28
Open issues
43
Open PRs
36
Contributors
~325
Commits
13.9K
Branches
17
Views (30d)
14

TypeScriptMITCreated Jun 18, 2026Last push 1d agoLatest release v2.100.5+256 stars this week+993 this month

Quick answers

What is opencodex?
Universal proxy translating proprietary requests from locked-down AI apps to any local or cloud LLM.
What does opencodex do?
OpenCodex acts as a highly capable translation layer and proxy that intercepts requests from heavily locked-down AI applications like Claude Code or Grok Build. It seamlessly routes these intercepted calls to arbitrary local or cloud LLMs of the user's choosing, translating protocols on the fly. The tool exposes a standardized API endpoint that dynamically adapts proprietary provider formats—including streaming, tool calls, and images—into formats compatible with open models. This powerful capability allows developers to effectively bypass hardcoded vendor locks and use their preferred models in otherwise severely restricted tools, while safely pooling accounts.
Who is opencodex for?
Power users, AI developers, and security researchers who demand absolute control over which models back their AI coding applications. It is perfect for those looking to heavily optimize their API costs or utilize local, privacy-preserving models.
How do I get started with opencodex?
npm install -g @bitkyc08/opencodex && ocx start
How popular is opencodex on GitHub?
lidge-jun/opencodex has 18,657 stars and 1,532 forks on GitHub, and gained 256 stars in the last 7 days.
What license does opencodex use?
lidge-jun/opencodex is released under the MIT license.

Star history

since Jul 29, 2026
05K10K15KJul 2026Sep 2026Oct 2026Nov 2026
18.7K stars as of Nov 19, 2026. Measured daily since Jul 29, 2026; GitHub no longer exposes earlier star timestamps.

Update history

5 recorded
  • Nov 19, 2026New release v2.100.5 (previously v2.99.0).
  • Nov 8, 2026New release v2.99.0 (previously v2.93.0).
  • Oct 28, 2026New release v2.93.0 (previously v2.88.0).
  • Oct 17, 2026New release v2.88.0 (previously v2.77.0).
  • Oct 5, 2026New release v2.77.0 (previously v2.64.0).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-23: 0 commits2025-11-24: 0 commits2025-11-25: 0 commits2025-11-26: 0 commits2025-11-27: 0 commits2025-11-28: 0 commits2025-11-29: 0 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 0 commits2025-12-03: 0 commits2025-12-04: 0 commits2025-12-05: 0 commits2025-12-06: 0 commits2025-12-07: 0 commits2025-12-08: 0 commits2025-12-09: 0 commits2025-12-10: 0 commits2025-12-11: 0 commits2025-12-12: 0 commits2025-12-13: 0 commits2025-12-14: 0 commits2025-12-15: 0 commits2025-12-16: 0 commits2025-12-17: 0 commits2025-12-18: 0 commits2025-12-19: 0 commits2025-12-20: 0 commits2025-12-21: 0 commits2025-12-22: 0 commits2025-12-23: 0 commits2025-12-24: 0 commits2025-12-25: 0 commits2025-12-26: 0 commits2025-12-27: 0 commits2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 0 commits2025-12-31: 0 commits2026-01-01: 0 commits2026-01-02: 0 commits2026-01-03: 0 commits2026-01-04: 0 commits2026-01-05: 0 commits2026-01-06: 0 commits2026-01-07: 0 commits2026-01-08: 0 commits2026-01-09: 0 commits2026-01-10: 0 commits2026-01-11: 0 commits2026-01-12: 0 commits2026-01-13: 0 commits2026-01-14: 0 commits2026-01-15: 0 commits2026-01-16: 0 commits2026-01-17: 0 commits2026-01-18: 0 commits2026-01-19: 0 commits2026-01-20: 0 commits2026-01-21: 0 commits2026-01-22: 0 commits2026-01-23: 0 commits2026-01-24: 0 commits2026-01-25: 0 commits2026-01-26: 0 commits2026-01-27: 0 commits2026-01-28: 0 commits2026-01-29: 0 commits2026-01-30: 0 commits2026-01-31: 0 commits2026-02-01: 0 commits2026-02-02: 0 commits2026-02-03: 0 commits2026-02-04: 0 commits2026-02-05: 0 commits2026-02-06: 0 commits2026-02-07: 0 commits2026-02-08: 0 commits2026-02-09: 0 commits2026-02-10: 0 commits2026-02-11: 0 commits2026-02-12: 0 commits2026-02-13: 0 commits2026-02-14: 0 commits2026-02-15: 0 commits2026-02-16: 0 commits2026-02-17: 0 commits2026-02-18: 0 commits2026-02-19: 0 commits2026-02-20: 0 commits2026-02-21: 0 commits2026-02-22: 0 commits2026-02-23: 0 commits2026-02-24: 0 commits2026-02-25: 0 commits2026-02-26: 0 commits2026-02-27: 0 commits2026-02-28: 0 commits2026-03-01: 0 commits2026-03-02: 0 commits2026-03-03: 0 commits2026-03-04: 0 commits2026-03-05: 0 commits2026-03-06: 0 commits2026-03-07: 0 commits2026-03-08: 0 commits2026-03-09: 0 commits2026-03-10: 0 commits2026-03-11: 0 commits2026-03-12: 0 commits2026-03-13: 0 commits2026-03-14: 0 commits2026-03-15: 0 commits2026-03-16: 0 commits2026-03-17: 0 commits2026-03-18: 0 commits2026-03-19: 0 commits2026-03-20: 0 commits2026-03-21: 0 commits2026-03-22: 0 commits2026-03-23: 0 commits2026-03-24: 0 commits2026-03-25: 0 commits2026-03-26: 0 commits2026-03-27: 0 commits2026-03-28: 0 commits2026-03-29: 0 commits2026-03-30: 0 commits2026-03-31: 0 commits2026-04-01: 0 commits2026-04-02: 0 commits2026-04-03: 0 commits2026-04-04: 0 commits2026-04-05: 0 commits2026-04-06: 0 commits2026-04-07: 0 commits2026-04-08: 0 commits2026-04-09: 0 commits2026-04-10: 0 commits2026-04-11: 0 commits2026-04-12: 0 commits2026-04-13: 0 commits2026-04-14: 0 commits2026-04-15: 0 commits2026-04-16: 0 commits2026-04-17: 0 commits2026-04-18: 0 commits2026-04-19: 0 commits2026-04-20: 0 commits2026-04-21: 0 commits2026-04-22: 0 commits2026-04-23: 0 commits2026-04-24: 0 commits2026-04-25: 0 commits2026-04-26: 0 commits2026-04-27: 0 commits2026-04-28: 0 commits2026-04-29: 0 commits2026-04-30: 0 commits2026-05-01: 0 commits2026-05-02: 0 commits2026-05-03: 0 commits2026-05-04: 0 commits2026-05-05: 0 commits2026-05-06: 0 commits2026-05-07: 0 commits2026-05-08: 0 commits2026-05-09: 0 commits2026-05-10: 0 commits2026-05-11: 0 commits2026-05-12: 0 commits2026-05-13: 0 commits2026-05-14: 0 commits2026-05-15: 0 commits2026-05-16: 0 commits2026-05-17: 0 commits2026-05-18: 0 commits2026-05-19: 0 commits2026-05-20: 0 commits2026-05-21: 0 commits2026-05-22: 0 commits2026-05-23: 0 commits2026-05-24: 0 commits2026-05-25: 0 commits2026-05-26: 0 commits2026-05-27: 0 commits2026-05-28: 0 commits2026-05-29: 0 commits2026-05-30: 0 commits2026-05-31: 0 commits2026-06-01: 0 commits2026-06-02: 0 commits2026-06-03: 0 commits2026-06-04: 0 commits2026-06-05: 0 commits2026-06-06: 0 commits2026-06-07: 0 commits2026-06-08: 0 commits2026-06-09: 0 commits2026-06-10: 0 commits2026-06-11: 0 commits2026-06-12: 0 commits2026-06-13: 0 commits2026-06-14: 0 commits2026-06-15: 0 commits2026-06-16: 0 commits2026-06-17: 0 commits2026-06-18: 52 commits2026-06-19: 147 commits2026-06-20: 136 commits2026-06-21: 87 commits2026-06-22: 28 commits2026-06-23: 9 commits2026-06-24: 70 commits2026-06-25: 104 commits2026-06-26: 26 commits2026-06-27: 68 commits2026-06-28: 95 commits2026-06-29: 141 commits2026-06-30: 69 commits2026-07-01: 56 commits2026-07-02: 30 commits2026-07-03: 49 commits2026-07-04: 7 commits2026-07-05: 31 commits2026-07-06: 12 commits2026-07-07: 41 commits2026-07-08: 9 commits2026-07-09: 53 commits2026-07-10: 69 commits2026-07-11: 40 commits2026-07-12: 68 commits2026-07-13: 26 commits2026-07-14: 38 commits2026-07-15: 38 commits2026-07-16: 43 commits2026-07-17: 43 commits2026-07-18: 102 commits2026-07-19: 33 commits2026-07-20: 73 commits2026-07-21: 49 commits2026-07-22: 148 commits2026-07-23: 221 commits2026-07-24: 143 commits2026-07-25: 160 commits2026-07-26: 285 commits2026-07-27: 193 commits2026-07-28: 57 commits2026-07-29: 53 commits2026-07-30: 104 commits2026-07-31: 258 commits2026-08-01: 212 commits2026-08-02: 223 commits2026-08-03: 264 commits2026-08-04: 207 commits2026-08-05: 279 commits2026-08-06: 264 commits2026-08-07: 283 commits2026-08-08: 202 commits2026-08-09: 267 commits2026-08-10: 189 commits2026-08-11: 120 commits2026-08-12: 117 commits2026-08-13: 141 commits2026-08-14: 188 commits2026-08-15: 158 commits2026-08-16: 137 commits2026-08-17: 228 commits2026-08-18: 280 commits2026-08-19: 83 commits2026-08-20: 191 commits2026-08-21: 148 commits2026-08-22: 130 commits2026-08-23: 39 commits2026-08-24: 28 commits2026-08-25: 65 commits2026-08-26: 139 commits2026-08-27: 94 commits2026-08-28: 105 commits2026-08-29: 79 commits2026-08-30: 73 commits2026-08-31: 44 commits2026-09-01: 69 commits2026-09-02: 108 commits2026-09-03: 48 commits2026-09-04: 86 commits2026-09-05: 381 commits2026-09-06: 357 commits2026-09-07: 436 commits2026-09-08: 163 commits2026-09-09: 130 commits2026-09-10: 102 commits2026-09-11: 262 commits2026-09-12: 399 commits2026-09-13: 281 commits2026-09-14: 89 commits2026-09-15: 109 commits2026-09-16: 119 commits2026-09-17: 67 commits2026-09-18: 166 commits2026-09-19: 53 commits2026-09-20: 106 commits2026-09-21: 74 commits2026-09-22: 17 commits2026-09-23: 135 commits2026-09-24: 52 commits2026-09-25: 117 commits2026-09-26: 132 commits2026-09-27: 148 commits2026-09-28: 201 commits2026-09-29: 37 commits2026-09-30: 59 commits2026-10-01: 52 commits2026-10-02: 64 commits2026-10-03: 220 commits2026-10-04: 173 commits2026-10-05: 138 commits2026-10-06: 38 commits2026-10-07: 19 commits2026-10-08: 26 commits2026-10-09: 76 commits2026-10-10: 83 commits2026-10-11: 22 commits2026-10-12: 21 commits2026-10-13: 108 commits2026-10-14: 10 commits2026-10-15: 107 commits2026-10-16: 40 commits2026-10-17: 16 commits2026-10-18: 20 commits2026-10-19: 48 commits2026-10-20: 0 commits2026-10-21: 16 commits2026-10-22: 26 commits2026-10-23: 50 commits2026-10-24: 43 commits2026-10-25: 42 commits2026-10-26: 53 commits2026-10-27: 48 commits2026-10-28: 104 commits2026-10-29: 66 commits2026-10-30: 52 commits2026-10-31: 14 commits2026-11-01: 6 commits2026-11-02: 9 commits2026-11-03: 59 commits2026-11-04: 7 commits2026-11-05: 0 commits2026-11-06: 37 commits2026-11-07: 41 commits2026-11-08: 30 commits2026-11-09: 96 commits2026-11-10: 35 commits2026-11-11: 106 commits2026-11-12: 31 commits2026-11-13: 103 commits2026-11-14: 29 commits2026-11-15: 10 commits2026-11-16: 29 commits2026-11-17: 47 commits2026-11-18: 40 commits2026-11-19: 111 commits2026-11-20: 0 commits2026-11-21: 0 commits
15,665 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Widely adopted

    18,657 stars

  • Very active

    15,665 commits in 52 weeks

  • Community-driven

    ~325 contributors

  • Well documented

    High community health score

  • Permissive license

    MIT

  • Continuous integration

    Automated checks passing

What opencodex does

OpenCodex acts as a highly capable translation layer and proxy that intercepts requests from heavily locked-down AI applications like Claude Code or Grok Build. It seamlessly routes these intercepted calls to arbitrary local or cloud LLMs of the user's choosing, translating protocols on the fly. The tool exposes a standardized API endpoint that dynamically adapts proprietary provider formats—including streaming, tool calls, and images—into formats compatible with open models. This powerful capability allows developers to effectively bypass hardcoded vendor locks and use their preferred models in otherwise severely restricted tools, while safely pooling accounts.

Power users, AI developers, and security researchers who demand absolute control over which models back their AI coding applications. It is perfect for those looking to heavily optimize their API costs or utilize local, privacy-preserving models.

  • Universal Protocol Translation: Intercepts and translates API calls seamlessly between proprietary apps and 40+ LLM providers.
  • ChatGPT Account Pooling: Manages multiple ChatGPT subscriptions for Codex auth, intelligently routing sessions to avoid rate limits.
  • Virtual Model Combos: Creates virtual model IDs that enable failover or weighted round-robin distribution across multiple backends.
  • Web Dashboard Interface: Provides a comprehensive UI to manage providers, configure routing, and view live request logs and tokens.
  • Web Search Sidecars: Equips non-OpenAI models with internet search and vision capabilities by proxying through a ChatGPT login.
  • Strict Memory Bounding: Employs aggressive garbage collection and bounded memory tracking to ensure the proxy runs lightly.

Where teams use it

Bypassing Vendor Lock-in

Forcing Claude Code or Grok Build to utilize a locally hosted Llama 3 or DeepSeek model instead of their default engines.

API Rate Limit Mitigation

Pooling multiple ChatGPT accounts and automatically routing incoming Codex requests to the account with the most available quota.

Multi-Agent Orchestration

Configuring sub-agents within an IDE that silently failover to backup providers if the primary LLM API goes down.

Traffic Inspection

Using the web dashboard to intercept, monitor, and debug the exact prompts and token counts being sent by closed AI tools.

Getting started: npm install -g @bitkyc08/opencodex && ocx start

README

dev branch

opencodex — one local gateway for Codex, Claude Code, Claude Desktop, Grok Build and more

One local gateway for your AI coding tools and models.

Use the models you choose with Codex, Claude Code, Claude Desktop and Grok Build,
and connect OpenCode, Pi, Qoder, WorkBuddy, Kilo, Cline, T3 Code and more through managed configs.

See every supported tool →

Part of GOAT: run your coding agents on any model, on any machine → trygoat.ai

Follow @claudeebum on X npm version license node version

npm install -g --allow-scripts=bun @bitkyc08/opencodex
ocx start

Download for macOS (.dmg) Download for Windows (.msi) Download for Linux (.AppImage) Download for Linux (.deb)

Claude Code, running any model

The picker is stock Claude Code. The brain behind it isn't.

Claude Code running a routed model through opencodex — the status bar shows gpt-5.6-luna-medium as the active model

Codex, running any model

Pick a provider and go — same workflow, different brain.

opencodex demo — running a task in the Codex app on a routed non-OpenAI model

Claude Desktop, running any model

Opus answers, then hands the task to a GPT-5.6 Sol subagent.

Claude Desktop answering as Claude Opus 4.8, then dispatching a GPT-5.6 Sol subagent through opencodex

Grok Build, running any model

Sol drives the session and calls a Kimi K3 subagent.

Grok Build running GPT-5.6 Sol through opencodex and calling a Kimi K3 subagent

English · Français · 한국어 · 简体中文 · 繁體中文 · Русский · 日本語 · Türkçe · 📖 Full documentation →

opencodex is a lightweight local gateway between your coding tools and your model providers. It accepts the Responses, Chat Completions and Anthropic Messages APIs and translates each request into whatever your provider speaks, carrying streaming, tool calls, reasoning and images where the client, model and provider support them. Use Claude, Gemini, Grok, GLM, DeepSeek, Kimi, Qwen, Ollama and other providers with Codex, Claude Code, Claude Desktop, Grok Build and the tools listed on the client support page.

Quick start

Personal install (CLI)

npm install -g --allow-scripts=bun @bitkyc08/opencodex   # Node 18+; the Bun runtime is bundled automatically
ocx start                         # proxy + dashboard on localhost:10100

Use ocx service to run it in the background.

Open http://localhost:10100 and configure everything in the web dashboard — add providers (40+ built-ins, or any OpenAI-compatible endpoint), pick models, manage accounts. ocx gui re-opens the dashboard at any time.

Connect your tool

Connect the tool you already use:

Tool How to connect
Codex Turn on the Codex switch on the dashboard's Connect page, then run codex as usual. On a local listener this points Codex's built-in provider at the proxy. From the terminal, run ocx init before adding providers in the dashboard and accept its Codex prompt.
Claude Code With the claude CLI installed, run ocx claude. It starts the proxy if needed and launches Claude Code through it.
Claude Desktop Run ocx claude desktop. On a new install it sets up the gateway profile for the whole app; an existing first-party setup is kept, and ocx claude desktop apply --gateway switches explicitly. See the Claude Code guide. Fully quit and reopen Claude Desktop after a switch.
Grok Build On a local listener with Grok integration enabled, ocx start registers the models when ~/.grok exists; pick an ocx-* model in Grok Build. Remote setups: see the Grok Build guide. After adding providers, restart the proxy (or run ocx ensure when Codex autostart is enabled) to refresh the list.
Tools with a managed integration Use the dashboard Connect page, or ocx integration client enable --client <id>.
Any other tool Set a custom OpenAI-compatible base URL of http://localhost:10100/v1, or an Anthropic base URL of http://localhost:10100.

The client support page lists which path each tool has and which protocol it speaks.

Desktop app (beta)

The desktop app is the same proxy and dashboard in a native window, with a tray and bundled ocx. It attaches to a proxy that is already running, or starts its bundled one, and the dashboard stays on the proxy port (http://localhost:10100 unless you configured another). Pick the file for your platform from the latest release:

Platform File Notes
macOS 13+ (Apple Silicon and Intel) OpenCodex-<version>-macos.dmg Universal build, signed with a Developer ID and notarized
Windows (x64) OpenCodex-<version>-windows-x64.msi Code signing via SignPath Foundation is rolling out (code signing policy); until a release is signed, SmartScreen asks once: choose More info → Run anyway
Linux (x86_64) OpenCodex-<version>-linux-x86_64.AppImage or -linux-amd64.deb The tray needs an AppIndicator-capable desktop

Every file has a .sha256 next to it on the release page. On macOS 14+ the app also ships a WidgetKit extension that shows proxy status, today's usage and provider quotas; the snapshot model it renders lives in app/ (MenuBarCore). To build the app yourself, run bun install && bun run build:gui at the repository root, then in desktop/ run bun install && bun run prepare-sidecar && bun run prepare-widget && bun run build:local on macOS, or bun install && bun run prepare-sidecar && bun run build:local on Windows and Linux (the widget step needs macOS). The Desktop App guide and the macOS Menu Bar App guide cover first launch, and AGENTS_INSTALL.md lists everything written to disk.

Sponsors

Sponsors keep opencodex maintained across every upstream protocol change. Interested? See SPONSORS.md.

OrcaRouter Thanks to OrcaRouter for sponsoring this project! OrcaRouter is one OpenAI-compatible AI gateway for production AI: adaptive routing that grades every prompt and sends it to the model that clears your bar, automatic failover, routing rules as code, zero-markup provider pricing with prompt caching, and guardrails, an agent firewall, and request logs on every call across 200+ models. Pick OrcaRouter in the Add provider picker or run ocx provider add orcarouter; orcarouter/auto is the adaptive router.
TokenLab Thanks to TokenLab for sponsoring this project! TokenLab gives coding agents one API key for leading models, supporting OpenAI Responses and Chat Completions, Anthropic Messages, and Gemini's native API formats, with streaming and tool calling. It also provides an MCP server and agent Skills for easy integration. Choose your delivery mode and pay as you go. Pick TokenLab in the Add provider picker or run ocx provider add tokenlab.
TokenLab 为编程智能体提供统一的多模型 API,一枚 API Key 即可接入主流模型,支持 OpenAI Responses、Chat Completions、Anthropic Messages 和 Gemini 原生 API 格式,以及流式输出和工具调用。同时提供 MCP 服务器和 Agent Skills,方便接入现有工作流;交付模式可选,按量付费。

Docker Compose

The repository ships a digest-pinned, non-root Compose build. The build generates and verifies the canonical compatibility manifest from the selected Git snapshot. A local clone needs Git and Docker Compose; a remote Git context needs Docker Compose. Neither path needs host Bun or a preparation step. Initialize the data-plane token once through stdin and start the hub:

git clone https://github.com/lidge-jun/opencodex.git
cd opencodex
docker compose build
openssl rand -hex 32 | docker compose run --rm -T hub bun run docker/bootstrap-token.ts
docker compose up -d
curl --fail --silent http://127.0.0.1:10100/healthz
curl --fail --silent http://127.0.0.1:10100/readyz

The default host binding is 127.0.0.1:10100. Remote exposure requires explicit OPENCODEX_BIND_ADDRESS=<LAN-or-Tailscale-IP> docker compose up -d; 0.0.0.0 opts into all host interfaces. Restrict access with a firewall and an authenticated TLS/tailnet frontend. The generated JSON stays untracked. The build context admits only .git/index and .git/HEAD — the inventory git ls-files reads, about 1 MB rather than the full object store — and they are visible only to the build-only manifest stage through a read-only mount, so no COPY includes .git. An existing host-generated manifest is still accepted only after validation; otherwise the build generates one itself. The build rejects stale manifests, missing or mismatched files, extra source files, and symlinks. It checks every recorded SHA-256 against the build context and copied runtime files, including package.json, bun.lock, and the specifically included scripts/model-metadata.source.json.

A remote Git context needs BuildKit to retain Git metadata. This Compose build fragment selects the remote snapshot and passes the required built-in argument:

services:
  hub:
    pull_policy: build
    build:
      context: https://github.com/lidge-jun/opencodex.git#dev
      dockerfile: Dockerfile
      target: runtime
      args:
        BUILDKIT_CONTEXT_KEEP_GIT_DIR: "1"

The token and mutable state stay in the ocx-state named volume; no credential is placed in the image, Compose file, environment, or shell arguments. See the Remote Hub deployment guide for provider setup, authenticated acceptance checks, remote management, and rollback.

Install from source (latest dev)

macOS / Linux:

curl -fsSL https://bun.sh/install | bash
git clone -b dev https://github.com/lidge-jun/opencodex.git
cd opencodex && ~/.bun/bin/bun install
~/.bun/bin/bun run build:gui
~/.bun/bin/bun run src/cli/index.ts start

Windows (PowerShell):

irm bun.sh/install.ps1 | iex
git clone -b dev https://github.com/lidge-jun/opencodex.git
cd opencodex; bun install
bun run build:gui
bun run src/cli/index.ts start

Source install runs the latest dev branch. Memory ownership patches, runtime GC improvements, and unreleased fixes are available here before they reach the npm package.

For agents
npm install -g --allow-scripts=bun @bitkyc08/opencodex
ocx start     # or `ocx service`
ocx init      # interactive setup: writes ~/.opencodex/config.json and wires Codex

ocx init never starts the proxy; start it first (or after — either order works, but headless commands like ocx provider add and ocx combo set talk to the live proxy and exit nonzero when it is unreachable). ocx status / ocx doctor / ocx health report the running state.

Agents installing or running opencodex: read AGENTS_INSTALL.md. An interactive ocx start may ask once whether to star this repository — that is the user's decision, never an agent's. The CLI suppresses the prompt for agent-driven runs and the API refuses them with 403 agent_consent_required.

Supported platforms

OS Status Service manager Desktop app (beta)
macOS (arm64 / x64) Fully supported launchd Universal .dmg
Linux (x64 / arm64) Fully supported systemd (user unit) x86_64 .AppImage / .deb
Windows (x64) Fully supported Task Scheduler (hidden) / opt-in native service (--native, WinSW) x64 .msi

The CLI install requires Node 18+; the desktop app needs neither Node nor Bun. The Bun runtime is bundled on npm install — no separate Bun install needed, no WSL needed on Windows. If npm blocked the bundled runtime's install scripts, see the installation docs.

Highlights

  • Use any LLM with Codex, Claude Code, Claude Desktop, and Grok Build — 40+ providers out of the box, each keeping its own native UI.
  • Combos — one virtual model id with failover or weighted round-robin across providers. See the combo guide.
  • Sub-agents on any model — feature routed models in Codex's sub-agent picker, with v1/v2 surface control and fallback chains. See the sub-agent guide.
  • Log in once, skip the API key — OAuth for xAI, Anthropic, and Kimi; or forward codex login, paste a key, or use ${ENV_VAR} references.
  • Web search & vision sidecars — non-OpenAI models get real web search and image understanding through a sidecar over your ChatGPT login.
  • See what's happening — the dashboard shows providers, OAuth status, model selection, and a live request log with cache token counts.
  • Clean exit, zero residue — ocx stop restores Codex to its original configuration.
  • Bounded memory ownership — every long-lived cache, ring buffer, and protocol-translation store has a finite cap, byte budget, or active reconciliation. No unbounded Map or Set survives a config reload.
Memory ownership details

OpenCodex tracks process-retained state in the categories below. Each has a documented bound:

  • 15 retained stores (request log, debug rings, image cache, model cache, vision descriptions, cursor blobs, responses continuation, etc.) are byte-accounted and evicted by the app-owned memory budget (default 256 MiB), except the native control replay store, which is pinned and never evicted.
  • 4 observed buffers (translator accumulators, image/OAuth/Grok tails) are monitored for in-flight byte pressure without eviction.
  • 32 state-store registrations handle expiry sweeps (60 s interval) and config-generation reconciliation so stale provider/account keys are removed.
  • Path and fingerprint memos (workspace metadata, hardened identities, installation salts, mode-hint capabilities) use insertion-order LRU caps (8–128 entries).
  • Model-cache generation tombstones are deleted after reconciliation; a global generation increment prevents stale in-flight discoveries from repopulating removed providers.
  • Lab event-id deduplication runs under a ledger lock from disk, with no process-level RAM index.

Run GET /api/system/memory (with the admin token) to inspect live retained bytes, eviction counters, and watchdog samples.

Model routing

Target any configured provider and model with the provider/model syntax:

codex -m "anthropic/claude-opus-5" "Explain this stack trace"
codex -m "google/gemini-3-pro" "Write unit tests for auth.ts"
codex -m "ollama/llama3" "Refactor this function"

Omit the provider/ prefix to use the default provider or auto-match by model name pattern. Provider model ids containing / are exposed with inner slashes aliased to -; the raw full-slash form keeps working too. Details: model routing docs.

JEV Auto routing (optional)

TypeSafe JEV can choose the first model and reasoning effort for an opt-in Combo while the normal model picker and every direct route stay unchanged. Add the credential with ocx login jev, from Providers → TypeSafe JEV → Add API key, or through TYPESAFE_API_KEY/JEV_API_KEY. Then open Models → Combos → Create JEV Auto, choose the allowed target models, and check the exact efforts JEV may select for each target. Leaving a target's effort setting untouched allows all efforts that model currently advertises.

JEV is consulted only for jev-auto and only once per logical model call. Missing credentials, network failures, or invalid decisions fail open to the first currently eligible target; caller cancellation still cancels the request. Automated tests use a mocked TypeSafe endpoint and do not validate a live JEV account.

A JEV Combo can instead ask a self-hosted decision model, such as Ollama's keyless tev1: add a jev-decision provider whose baseUrl is the full /v1/systemone endpoint and set the Combo's decisionProvider to it. TypeSafe credentials are never sent there. Details: System One-compatible server.

Providers & adapters

OpenAI (ChatGPT login or API key), Anthropic, Google Gemini, xAI, Kimi, Azure OpenAI, Ollama (local + Cloud), Cursor (experimental), and every OpenAI-compatible endpoint — plus DeepSeek, Groq, OpenRouter, OpenGateway, Together, Fireworks, Cerebras, Mistral, Hugging Face, NVIDIA NIM, MiniMax, Qwen Cloud, Qoder Global and CN (official PAT + CLI), SiliconFlow, and more. Full list: ocx init or the provider docs.

CLI

ocx init                       # interactive setup (writes config, wires Codex, offers the shim)
ocx start [--port 10100] [--socks5 [host:port] | --socks5-off]  # SOCKS5 defaults to socks5://127.0.0.1:10808
ocx stop                       # stop + restore native Codex
ocx service [install|repair|restart|start|stop|status|uninstall|remove]  # background service
ocx codex-shim install         # start the proxy on demand whenever `codex` launches
ocx health [--json]            # check immediate proxy liveness
ocx ready [--json] [--wait [--timeout <seconds>]]  # check post-sync readiness
ocx status                     # is the proxy running?
ocx gui                        # open the web dashboard
ocx provider <...>             # manage providers (list/add/edit/test/remove)
ocx account <...>              # manage ChatGPT accounts & API-key pools
ocx combo <...>                # manage failover / round-robin combos
ocx v2 <...>                   # multi-agent v1/v2 surface controls
ocx update [--tag preview]     # update opencodex

A start whose preferred port is busy stops and names the holder instead of moving to another port, so it can never leave a second proxy running beside the first. Free the port, or name a different one with --port. Full reference: CLI docs.

Health and readiness

GET /healthz reports immediate proxy liveness. The unauthenticated GET /readyz endpoint reports post-sync readiness with the sanitized JSON identity {service, version, uptime, pid, port, status}. It returns 200 when status is ready; pending and terminal failed return 503 with Retry-After: 1.

ocx ready [--json] [--wait [--timeout <seconds>]] performs one probe by default. --wait polls for up to 45 seconds by default, but exits immediately when it observes terminal failed; --timeout <seconds> sets a 1–300 second limit, requires --wait, and accepts only positive integers. CLI --json output is {ready, status, pid, port}, where status is ready, pending, failed, or unreachable.

Exit Result
0 Ready
1 Not ready: pending, failed, timeout, or unreachable
64 Invalid arguments

An older proxy without /readyz fails closed as unreachable with exit 1, while ocx health remains compatible.

Autostart: service vs shim

Use the service (ocx service) for an always-on proxy that restarts on crash. Use the shim (ocx codex-shim install) for lightweight, on-demand startup without a background daemon. Remove them with ocx service uninstall / ocx codex-shim uninstall.

Uninstall

ocx uninstall                  # stop, remove service/shim, restore native Codex, clean up state
npm uninstall -g @bitkyc08/opencodex

Remote access

By default opencodex binds to 127.0.0.1 and needs no extra authentication. Binding beyond loopback ("hostname": "0.0.0.0") requires a bearer token — the proxy refuses to start without OPENCODEX_API_AUTH_TOKEN, and every client request must carry it as x-opencodex-api-key. Details: configuration reference.

Advanced usage

Self-hosted options for power users. Review each provider's terms before you enable them.

ChatGPT account pool

opencodex can also manage a ChatGPT account pool for Codex auth. Add multiple ChatGPT / Codex accounts, refresh their 5h / weekly / 30d quota in the dashboard. Under quota routing, new sessions can use the lowest-usage healthy account; round-robin and fill-first use their own policies. Existing Codex threads normally retain affinity to the account that started them, so long SSH, tmux, or mobile-connected sessions do not jump accounts mid-conversation — but quota re-evaluation, failover, account exclusion, affinity expiry, or 401/403 and 429 recovery can rebind them. Give the accounts a selection order when one of them — usually your Codex Desktop login — should only be reached for once the others are drained.

  • Pool ChatGPT accounts — thread affinity, quota-aware auto-switching, cooldown and fail-closed auth handling.

    Provider-policy note: Account pooling is for routing and operational resilience only; it does not guarantee protection from provider rate limits, enforcement, suspension, or other account actions. OpenCodex does not endorse using additional accounts to circumvent provider limits or sharing account credentials between people. You are responsible for complying with each provider's current terms. See the Codex Auth account-pool guidance and OpenAI's current Terms of Use.

Documentation

The public docs — install, providers, routing, combos, sub-agents, sidecars, integrations, and the CLI/config/management-API references — are built from docs-site/ and published to opencodex.me.

Maintainer source-of-truth notes live under structure/, contributor setup in CONTRIBUTING.md, and security reporting in SECURITY.md. Report undisclosed vulnerabilities privately through GitHub private vulnerability reporting, not a public issue. That form is the only technical channel — there is no security email. Follow-ups stay in the private report itself; a public issue may carry coordination only, never vulnerability details. Acknowledging a report is not the same as triaging it, and no first-response target is promised.

Development

Source development requires the bun CLI on your PATH. The published npm package bundles its own Bun runtime for installed ocx commands; package scripts may also resolve Bun through that bundled dependency.

git clone https://github.com/lidge-jun/opencodex.git
cd opencodex
bun install
bun run typecheck
bun run test

See Contributing.

Contributor work that landed through a maintainer carry or reimplementation, where the commit does not name its original author, is recorded in CREDITS.md.

Code signing policy

Windows binaries are moving to Authenticode signing (#7207). The Windows Code Signing guide covers the rollout, how to verify a signature, and the full policy.

Free code signing provided by SignPath.io, certificate by SignPath Foundation.

  • Committers and reviewers: lidge-jun
  • Approvers: lidge-jun
  • Privacy: opencodex sends one anonymous daily usage summary (a per-day install hash that changes daily, version, release channel, platform, install channel, provider kind, coarse model family, active minutes and request, token and error counts; never prompts, model outputs, keys, accounts, hostnames or paths) to telemetry.opencodex.me, and only after the person installing or operating it has seen the notice in the dashboard or an interactive CLI prompt and has not declined. It can be turned off in that notice, in the Windows installer ("Send anonymous usage statistics", checked by default), in Proxy details, or with ocx telemetry disable, OCX_TELEMETRY=0 or DO_NOT_TRACK=1. Only project-wide aggregates of this anonymous data are public. A separate public leaderboard profile is off unless you connect one yourself (dashboard Home or ocx telemetry profile connect); it shares only a chosen handle, display name and colour and your daily request, token and model-family totals, never your anonymous telemetry ID, and disconnecting deletes it. Everything else goes only to the providers and services you configure. See the telemetry guide.

Disclaimer

opencodex is an independent, community-maintained project and is not affiliated with or endorsed by OpenAI, Anthropic, or any other provider.

Some providers — notably Anthropic (Claude) — may suspend or restrict accounts that route API traffic through third-party proxies. Use at your own risk (UAYOR). Before connecting a provider, review its Terms of Service to confirm that proxy-based access is permitted. The opencodex maintainers are not responsible for any account actions taken by upstream providers.

License

MIT

View on GitHub

Recent activity

commits and pull requests

Releases and announcements

314 total
  1. v2.100.5v2.100.5Nov 18, 20268.3K downloads

    Published to npm as `@bitkyc08/[email protected]` with dist-tag `latest`. ## New Features - Add Kimi (Responses) as its own row under the Kimi login (#8798) - Add GPT-6.2 Sol and Astra and upgrade subagent defaults (#8893) ## Bug Fixes - Stream the Linux listener table so a busy host is not refused (#8855) - Refuse Anthropic redirects, keep chat caller restrictions, gate explicit SSH routes (#8868) - Fence retained native login by account identity (#8808) - Bind model discovery to Google destinations (#8802) - Yield within indexed row decoding and aggregation (#8800) - Bound WebSocket event retention (#8801) - Keep unbounded tool catalog admission linear (#8804) - Bound eager tool warning diagnostics (#8810) - Keep a child's reasoning replay out of the parent's record (#8634) - Fail closed when stream replay classification fails (#8805) - Preserve literal spans in citation escaping (#8811) - Bound duplicate citation title updates (#8813) - R5 platform and test-hygiene lane (zh-CN/ko-KR checked stop, Windows git config, test network guard) (#8870) - Keep localized schtasks denials and harden the test egress guard (#8870 follow-up) (#8872) - Avoid Gemini rejection of tool catalog

  2. v2.100.5-preview.20261118.1v2.100.5-preview.20261118.1Nov 18, 2026pre-release88 downloads

    Published to npm as `@bitkyc08/[email protected]` with dist-tag `preview`. ## New Features - Add Kimi (Responses) as its own row under the Kimi login (#8798) - Add GPT-6.2 Sol and Astra and upgrade subagent defaults (#8893) ## Bug Fixes - Stream the Linux listener table so a busy host is not refused (#8855) - Refuse Anthropic redirects, keep chat caller restrictions, gate explicit SSH routes (#8868) - Fence retained native login by account identity (#8808) - Bind model discovery to Google destinations (#8802) - Yield within indexed row decoding and aggregation (#8800) - Bound WebSocket event retention (#8801) - Keep unbounded tool catalog admission linear (#8804) - Bound eager tool warning diagnostics (#8810) - Keep a child's reasoning replay out of the parent's record (#8634) - Fail closed when stream replay classification fails (#8805) - Preserve literal spans in citation escaping (#8811) - Bound duplicate citation title updates (#8813) - R5 platform and test-hygiene lane (zh-CN/ko-KR checked stop, Windows git config, test network guard) (#8870) - Keep localized schtasks denials and harden the test egress guard (#8870 follow-up) (#8872) - Avoid Gemini rejec

  3. v2.100.4v2.100.4Nov 16, 202613.4K downloads

    Published to npm as `@bitkyc08/[email protected]` with dist-tag `latest`. ## New Features - Skip repeated scans of fragmented frames (#8695) - Route video_gen to images.videoProvider (#8783) - Headless Windows Desktop updater (ocx update --desktop) (#8795) - Add machine-readable cause fields to combo_unavailable (#7965) (#8789) - Opt-in estimated usage when a native provider omits it (#7427) (#8793) - Opt-in offline wait and one resend after a pre-connect failure (#7958) (#8790) - Experimental per-message effort keeps the prompt cache across effort changes (#8787) - Config-first routed catalog row defaults (#8797) - Require an explicit acknowledgement before any Google Antigravity sign-in (#8820) - Give Luna Reserve its own setting, seeded once from authless (#8788) ## Bug Fixes - Keep session identity when the per-turn tk is oversized (#8568) - Scale the integrity check bound with index size (#8709) - Hop past Anthropic's extra-usage refusal (#8588) - Refuse route edits during an unfinished removal; scope identity-file texts; close #8694 remedy gaps (#8754) - Handle denied Codex boilerplate and optional history rewrites (#8590) - Keep exact decimals for quota rounding (#8566)

  4. v2.100.3v2.100.3Nov 14, 202619.4K downloads

    Published to npm as `@bitkyc08/[email protected]` with dist-tag `latest`. ## New Features - Carry Claude Code's Advisor server tool on the translated Messages path (#8516) - Record the Anthropic pool account tag on each attempt (#8520) - Say why an API-key balance is unknown and when it was last read (#8519) - Opt-in admit policy for curated selections and honest arrival status (#8511) - Update, sync and restart Codex on linked Children from the Home (#8513) - Remember devices behind an operator-named reverse proxy (#8518) - Opt-in per-provider alias templates (#8512) - Ocx sync --child and --restart-children for linked Children (#8526) - Opt-in pool-only policy keeps automatic Pool routing off native main (#8536) - Record Child tunnel transitions in the diagnostics file (#8539) - Scope custom tools by model (#7507) - Codex CLI update tab over the existing plan/apply/jobs API (#8540) - Add opt-in question-only consultations (#7526) - Opt-in SSH log capture for Remote Link tunnels (#8551) - Read-only Remote Link diagnostics viewer (CLI, route, dashboard) (#8555) - Hand the stop deadline to ocx stop and read the Windows stop reasons (#7771 slice 3) (#8560) - Checked Windows stop pr

  5. v2.100.2v2.100.2Nov 11, 202621.1K downloads

    Published to npm as `@bitkyc08/[email protected]` with dist-tag `latest`. ## New Features - Complete manual pause and resume for API key pools (#7636) - Add bounded waits for stored Codex replies (#8090) - Persist target cooldowns across restarts (#8117) - Strip named hosted tools only beside client tools (#8499) - Keep the Chat tool catalog stable across ToolSearch loads (opt-in dispatcher) (#8502) - Opt in to skipping invalid /models rows (#8503) - Gated remote ocx, Child update contract and observation cache (#8505) - Show Child version, install kind and catalog freshness; ocx link check (#8508) - Explicit health-gated resume, and login that clears an automatic pause (#8515) ## Bug Fixes - Seed Command Code's auth store so the desktop app can open (#8340) - Keep the census reader quiet and bound to the first record (#8431) - Expire a carried weekly reading once its window is over (#8185) - Wait for npm to serve a new version before verifying it (#8477) - Match the Getting started startup step to OpenCodex Desktop (#8476) - Fail over zero-output max_output_tokens terminal (#8222) - Show Mistral API and Vibe budget usage (#8295) - Show inactive model-scoped quota rows without

Code frequency

additions and deletions
+578.6K-578.6KWeek of 2026-06-14: +36,080 linesWeek of 2026-06-14: -6,197 linesWeek of 2026-06-21: +54,173 linesWeek of 2026-06-21: -4,288 linesWeek of 2026-06-28: +72,790 linesWeek of 2026-06-28: -43,673 linesWeek of 2026-07-05: +61,029 linesWeek of 2026-07-05: -23,146 linesWeek of 2026-07-12: +73,560 linesWeek of 2026-07-12: -18,265 linesWeek of 2026-07-19: +280,936 linesWeek of 2026-07-19: -105,382 linesWeek of 2026-07-26: +441,650 linesWeek of 2026-07-26: -212,692 linesWeek of 2026-08-02: +578,564 linesWeek of 2026-08-02: -439,039 linesWeek of 2026-08-09: +212,761 linesWeek of 2026-08-09: -30,054 linesWeek of 2026-08-16: +182,067 linesWeek of 2026-08-16: -79,071 linesWeek of 2026-08-23: +124,475 linesWeek of 2026-08-23: -12,087 linesWeek of 2026-08-30: +17,656 linesWeek of 2026-08-30: -3,216 linesJun 14, 2026Aug 30, 2026
+2.1M lines added, -977.1K removed over the last year.

Commits per week

last 52 weeks
18490Week of 2025-11-23: 0 commitsWeek of 2025-11-30: 0 commitsWeek of 2025-12-07: 0 commitsWeek of 2025-12-14: 0 commitsWeek of 2025-12-21: 0 commitsWeek of 2025-12-28: 0 commitsWeek of 2026-01-04: 0 commitsWeek of 2026-01-11: 0 commitsWeek of 2026-01-18: 0 commitsWeek of 2026-01-25: 0 commitsWeek of 2026-02-01: 0 commitsWeek of 2026-02-08: 0 commitsWeek of 2026-02-15: 0 commitsWeek of 2026-02-22: 0 commitsWeek of 2026-03-01: 0 commitsWeek of 2026-03-08: 0 commitsWeek of 2026-03-15: 0 commitsWeek of 2026-03-22: 0 commitsWeek of 2026-03-29: 0 commitsWeek of 2026-04-05: 0 commitsWeek of 2026-04-12: 0 commitsWeek of 2026-04-19: 0 commitsWeek of 2026-04-26: 0 commitsWeek of 2026-05-03: 0 commitsWeek of 2026-05-10: 0 commitsWeek of 2026-05-17: 0 commitsWeek of 2026-05-24: 0 commitsWeek of 2026-05-31: 0 commitsWeek of 2026-06-07: 0 commitsWeek of 2026-06-14: 335 commitsWeek of 2026-06-21: 392 commitsWeek of 2026-06-28: 447 commitsWeek of 2026-07-05: 255 commitsWeek of 2026-07-12: 358 commitsWeek of 2026-07-19: 827 commitsWeek of 2026-07-26: 1162 commitsWeek of 2026-08-02: 1722 commitsWeek of 2026-08-09: 1180 commitsWeek of 2026-08-16: 1197 commitsWeek of 2026-08-23: 549 commitsWeek of 2026-08-30: 809 commitsWeek of 2026-09-06: 1849 commitsWeek of 2026-09-13: 884 commitsWeek of 2026-09-20: 633 commitsWeek of 2026-09-27: 781 commitsWeek of 2026-10-04: 553 commitsWeek of 2026-10-11: 324 commitsWeek of 2026-10-18: 203 commitsWeek of 2026-10-25: 379 commitsWeek of 2026-11-01: 159 commitsWeek of 2026-11-08: 430 commitsWeek of 2026-11-15: 237 commitsNov 23, 2025Nov 15, 2026
15.7K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 121 commitsSun 1:00 — 88 commitsSun 2:00 — 97 commitsSun 3:00 — 97 commitsSun 4:00 — 67 commitsSun 5:00 — 92 commitsSun 6:00 — 49 commitsSun 7:00 — 58 commitsSun 8:00 — 59 commitsSun 9:00 — 52 commitsSun 10:00 — 97 commitsSun 11:00 — 80 commitsSun 12:00 — 70 commitsSun 13:00 — 64 commitsSun 14:00 — 90 commitsSun 15:00 — 73 commitsSun 16:00 — 89 commitsSun 17:00 — 77 commitsSun 18:00 — 74 commitsSun 19:00 — 95 commitsSun 20:00 — 102 commitsSun 21:00 — 88 commitsSun 22:00 — 71 commitsSun 23:00 — 66 commitsMon 0:00 — 122 commitsMon 1:00 — 124 commitsMon 2:00 — 84 commitsMon 3:00 — 76 commitsMon 4:00 — 51 commitsMon 5:00 — 35 commitsMon 6:00 — 30 commitsMon 7:00 — 85 commitsMon 8:00 — 45 commitsMon 9:00 — 56 commitsMon 10:00 — 78 commitsMon 11:00 — 57 commitsMon 12:00 — 86 commitsMon 13:00 — 75 commitsMon 14:00 — 80 commitsMon 15:00 — 62 commitsMon 16:00 — 62 commitsMon 17:00 — 73 commitsMon 18:00 — 90 commitsMon 19:00 — 63 commitsMon 20:00 — 77 commitsMon 21:00 — 74 commitsMon 22:00 — 56 commitsMon 23:00 — 64 commitsTue 0:00 — 60 commitsTue 1:00 — 101 commitsTue 2:00 — 51 commitsTue 3:00 — 27 commitsTue 4:00 — 45 commitsTue 5:00 — 44 commitsTue 6:00 — 33 commitsTue 7:00 — 36 commitsTue 8:00 — 35 commitsTue 9:00 — 69 commitsTue 10:00 — 66 commitsTue 11:00 — 77 commitsTue 12:00 — 78 commitsTue 13:00 — 67 commitsTue 14:00 — 36 commitsTue 15:00 — 38 commitsTue 16:00 — 43 commitsTue 17:00 — 42 commitsTue 18:00 — 48 commitsTue 19:00 — 66 commitsTue 20:00 — 63 commitsTue 21:00 — 61 commitsTue 22:00 — 25 commitsTue 23:00 — 32 commitsWed 0:00 — 44 commitsWed 1:00 — 62 commitsWed 2:00 — 82 commitsWed 3:00 — 68 commitsWed 4:00 — 57 commitsWed 5:00 — 56 commitsWed 6:00 — 38 commitsWed 7:00 — 39 commitsWed 8:00 — 47 commitsWed 9:00 — 69 commitsWed 10:00 — 71 commitsWed 11:00 — 108 commitsWed 12:00 — 75 commitsWed 13:00 — 42 commitsWed 14:00 — 47 commitsWed 15:00 — 45 commitsWed 16:00 — 59 commitsWed 17:00 — 42 commitsWed 18:00 — 65 commitsWed 19:00 — 88 commitsWed 20:00 — 56 commitsWed 21:00 — 66 commitsWed 22:00 — 59 commitsWed 23:00 — 59 commitsThu 0:00 — 81 commitsThu 1:00 — 58 commitsThu 2:00 — 51 commitsThu 3:00 — 32 commitsThu 4:00 — 34 commitsThu 5:00 — 32 commitsThu 6:00 — 46 commitsThu 7:00 — 39 commitsThu 8:00 — 62 commitsThu 9:00 — 105 commitsThu 10:00 — 52 commitsThu 11:00 — 80 commitsThu 12:00 — 48 commitsThu 13:00 — 104 commitsThu 14:00 — 78 commitsThu 15:00 — 68 commitsThu 16:00 — 70 commitsThu 17:00 — 63 commitsThu 18:00 — 62 commitsThu 19:00 — 72 commitsThu 20:00 — 55 commitsThu 21:00 — 68 commitsThu 22:00 — 69 commitsThu 23:00 — 71 commitsFri 0:00 — 93 commitsFri 1:00 — 94 commitsFri 2:00 — 108 commitsFri 3:00 — 81 commitsFri 4:00 — 90 commitsFri 5:00 — 48 commitsFri 6:00 — 38 commitsFri 7:00 — 50 commitsFri 8:00 — 89 commitsFri 9:00 — 67 commitsFri 10:00 — 87 commitsFri 11:00 — 106 commitsFri 12:00 — 120 commitsFri 13:00 — 86 commitsFri 14:00 — 57 commitsFri 15:00 — 61 commitsFri 16:00 — 53 commitsFri 17:00 — 42 commitsFri 18:00 — 58 commitsFri 19:00 — 42 commitsFri 20:00 — 75 commitsFri 21:00 — 130 commitsFri 22:00 — 124 commitsFri 23:00 — 135 commitsSat 0:00 — 89 commitsSat 1:00 — 84 commitsSat 2:00 — 66 commitsSat 3:00 — 53 commitsSat 4:00 — 57 commitsSat 5:00 — 54 commitsSat 6:00 — 57 commitsSat 7:00 — 48 commitsSat 8:00 — 48 commitsSat 9:00 — 46 commitsSat 10:00 — 57 commitsSat 11:00 — 77 commitsSat 12:00 — 125 commitsSat 13:00 — 219 commitsSat 14:00 — 160 commitsSat 15:00 — 91 commitsSat 16:00 — 73 commitsSat 17:00 — 57 commitsSat 18:00 — 58 commitsSat 19:00 — 76 commitsSat 20:00 — 65 commitsSat 21:00 — 91 commitsSat 22:00 — 91 commitsSat 23:00 — 104 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.

Who is committing

last 52 weeks
Maintainer commits8,333 (60%)
Community commits5,524 (40%)

13,857 commits in total over the last year.

DateListRankStars gained
Jul 23, 2026daily#14+5
Jul 22, 2026daily#21+4
  • morluto/rea

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

    471.6K stars · TypeScript

  • freeCodeCamp/freeCodeCamp

    freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

    459.4K stars · TypeScript

  • openclaw/openclaw

    The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

    394.9K stars · TypeScript

  • 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

  • anomalyco/opencode

    The open source coding agent.

    228.3K stars · TypeScript