bytedance/deer-flowPublic

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

AI summary: An open-source super-agent framework that orchestrates sub-agents, memory, and sandboxes to perform deep exploration ...

Stars
85.5K
+140 today
Forks
12.1K
Watchers
335
Open issues
597
Open PRs
526
Contributors
~678
Commits
4.9K
Branches
45
Views (30d)
5

PythonMITCreated May 7, 2025Last push 2d agoLatest release v2.2.0+249 stars this week+1.3K this month

Quick answers

What is deer-flow?
An open-source super-agent framework that orchestrates sub-agents, memory, and sandboxes to perform deep exploration ...
What does deer-flow do?
DeerFlow acts as a highly extensible super-agent harness designed to tackle complex, long-horizon tasks that may take minutes to hours to execute. It systematically coordinates multiple specialized sub-agents alongside managed memory and secure execution sandboxes to automate intricate coding, research, and data gathering workflows. Version 2.0 represents a complete, ground-up rewrite focused on robust task orchestration and integrating intelligent external toolsets, such as deep search and crawling. The framework natively supports seamless integration with various LLM providers and enables developers to trace complex multi-step reasoning natively via LangSmith.
Who is deer-flow for?
AI researchers and senior software engineers looking to build, orchestrate, and debug extremely complex, long-running multi-agent workflows. It is designed for developers seeking efficiency. It helps streamline their workflows and save time.
How do I get started with deer-flow?
npm install -g @bytedance/deer-flow
How popular is deer-flow on GitHub?
bytedance/deer-flow has 85,484 stars and 12,056 forks on GitHub, and gained 249 stars in the last 7 days.
What license does deer-flow use?
bytedance/deer-flow is released under the MIT license.

Star history

since Jul 28, 2026
025K50K75KJul 2026Sep 2026Oct 2026Nov 2026
85.5K stars as of Nov 18, 2026. Measured daily since Jul 28, 2026; GitHub no longer exposes earlier star timestamps.

Update history

1 recorded
  • Nov 11, 2026New release v2.2.0 (previously v2.1.0).

Contribution activity

commits per day, last 52 weeks
NovDecJanFebMarAprMayJunJulAugSepOctNovMonWedFri2025-11-23: 0 commits2025-11-24: 2 commits2025-11-25: 1 commit2025-11-26: 0 commits2025-11-27: 3 commits2025-11-28: 4 commits2025-11-29: 3 commits2025-11-30: 0 commits2025-12-01: 0 commits2025-12-02: 3 commits2025-12-03: 0 commits2025-12-04: 1 commit2025-12-05: 1 commit2025-12-06: 2 commits2025-12-07: 0 commits2025-12-08: 1 commit2025-12-09: 1 commit2025-12-10: 1 commit2025-12-11: 1 commit2025-12-12: 1 commit2025-12-13: 1 commit2025-12-14: 0 commits2025-12-15: 2 commits2025-12-16: 1 commit2025-12-17: 2 commits2025-12-18: 0 commits2025-12-19: 1 commit2025-12-20: 0 commits2025-12-21: 2 commits2025-12-22: 0 commits2025-12-23: 2 commits2025-12-24: 0 commits2025-12-25: 3 commits2025-12-26: 2 commits2025-12-27: 1 commit2025-12-28: 0 commits2025-12-29: 0 commits2025-12-30: 2 commits2025-12-31: 0 commits2026-01-01: 1 commit2026-01-02: 0 commits2026-01-03: 0 commits2026-01-04: 0 commits2026-01-05: 1 commit2026-01-06: 2 commits2026-01-07: 2 commits2026-01-08: 0 commits2026-01-09: 3 commits2026-01-10: 1 commit2026-01-11: 0 commits2026-01-12: 0 commits2026-01-13: 0 commits2026-01-14: 25 commits2026-01-15: 14 commits2026-01-16: 56 commits2026-01-17: 71 commits2026-01-18: 26 commits2026-01-19: 26 commits2026-01-20: 25 commits2026-01-21: 25 commits2026-01-22: 39 commits2026-01-23: 15 commits2026-01-24: 52 commits2026-01-25: 25 commits2026-01-26: 11 commits2026-01-27: 10 commits2026-01-28: 22 commits2026-01-29: 52 commits2026-01-30: 16 commits2026-01-31: 30 commits2026-02-01: 24 commits2026-02-02: 59 commits2026-02-03: 24 commits2026-02-04: 9 commits2026-02-05: 9 commits2026-02-06: 69 commits2026-02-07: 33 commits2026-02-08: 28 commits2026-02-09: 61 commits2026-02-10: 8 commits2026-02-11: 3 commits2026-02-12: 2 commits2026-02-13: 5 commits2026-02-14: 7 commits2026-02-15: 1 commit2026-02-16: 0 commits2026-02-17: 0 commits2026-02-18: 3 commits2026-02-19: 1 commit2026-02-20: 0 commits2026-02-21: 3 commits2026-02-22: 0 commits2026-02-23: 0 commits2026-02-24: 4 commits2026-02-25: 8 commits2026-02-26: 3 commits2026-02-27: 2 commits2026-02-28: 4 commits2026-03-01: 6 commits2026-03-02: 4 commits2026-03-03: 2 commits2026-03-04: 5 commits2026-03-05: 5 commits2026-03-06: 7 commits2026-03-07: 1 commit2026-03-08: 8 commits2026-03-09: 4 commits2026-03-10: 8 commits2026-03-11: 8 commits2026-03-12: 2 commits2026-03-13: 10 commits2026-03-14: 7 commits2026-03-15: 0 commits2026-03-16: 4 commits2026-03-17: 7 commits2026-03-18: 7 commits2026-03-19: 1 commit2026-03-20: 5 commits2026-03-21: 2 commits2026-03-22: 9 commits2026-03-23: 8 commits2026-03-24: 13 commits2026-03-25: 15 commits2026-03-26: 15 commits2026-03-27: 15 commits2026-03-28: 8 commits2026-03-29: 20 commits2026-03-30: 12 commits2026-03-31: 8 commits2026-04-01: 13 commits2026-04-02: 11 commits2026-04-03: 17 commits2026-04-04: 10 commits2026-04-05: 11 commits2026-04-06: 15 commits2026-04-07: 12 commits2026-04-08: 8 commits2026-04-09: 14 commits2026-04-10: 14 commits2026-04-11: 12 commits2026-04-12: 9 commits2026-04-13: 2 commits2026-04-14: 10 commits2026-04-15: 6 commits2026-04-16: 6 commits2026-04-17: 1 commit2026-04-18: 10 commits2026-04-19: 6 commits2026-04-20: 5 commits2026-04-21: 2 commits2026-04-22: 2 commits2026-04-23: 7 commits2026-04-24: 10 commits2026-04-25: 5 commits2026-04-26: 22 commits2026-04-27: 0 commits2026-04-28: 12 commits2026-04-29: 0 commits2026-04-30: 10 commits2026-05-01: 8 commits2026-05-02: 7 commits2026-05-03: 1 commit2026-05-04: 6 commits2026-05-05: 5 commits2026-05-06: 2 commits2026-05-07: 5 commits2026-05-08: 9 commits2026-05-09: 12 commits2026-05-10: 5 commits2026-05-11: 7 commits2026-05-12: 8 commits2026-05-13: 4 commits2026-05-14: 1 commit2026-05-15: 7 commits2026-05-16: 3 commits2026-05-17: 5 commits2026-05-18: 3 commits2026-05-19: 2 commits2026-05-20: 10 commits2026-05-21: 13 commits2026-05-22: 5 commits2026-05-23: 8 commits2026-05-24: 0 commits2026-05-25: 1 commit2026-05-26: 7 commits2026-05-27: 1 commit2026-05-28: 11 commits2026-05-29: 8 commits2026-05-30: 1 commit2026-05-31: 2 commits2026-06-01: 3 commits2026-06-02: 3 commits2026-06-03: 9 commits2026-06-04: 1 commit2026-06-05: 2 commits2026-06-06: 2 commits2026-06-07: 7 commits2026-06-08: 15 commits2026-06-09: 11 commits2026-06-10: 7 commits2026-06-11: 6 commits2026-06-12: 11 commits2026-06-13: 13 commits2026-06-14: 8 commits2026-06-15: 1 commit2026-06-16: 4 commits2026-06-17: 14 commits2026-06-18: 7 commits2026-06-19: 18 commits2026-06-20: 5 commits2026-06-21: 18 commits2026-06-22: 8 commits2026-06-23: 13 commits2026-06-24: 11 commits2026-06-25: 9 commits2026-06-26: 2 commits2026-06-27: 5 commits2026-06-28: 5 commits2026-06-29: 0 commits2026-06-30: 2 commits2026-07-01: 8 commits2026-07-02: 10 commits2026-07-03: 14 commits2026-07-04: 23 commits2026-07-05: 9 commits2026-07-06: 15 commits2026-07-07: 10 commits2026-07-08: 4 commits2026-07-09: 12 commits2026-07-10: 14 commits2026-07-11: 23 commits2026-07-12: 26 commits2026-07-13: 14 commits2026-07-14: 27 commits2026-07-15: 14 commits2026-07-16: 13 commits2026-07-17: 10 commits2026-07-18: 9 commits2026-07-19: 16 commits2026-07-20: 14 commits2026-07-21: 24 commits2026-07-22: 17 commits2026-07-23: 15 commits2026-07-24: 13 commits2026-07-25: 11 commits2026-07-26: 25 commits2026-07-27: 18 commits2026-07-28: 24 commits2026-07-29: 21 commits2026-07-30: 9 commits2026-07-31: 11 commits2026-08-01: 12 commits2026-08-02: 8 commits2026-08-03: 2 commits2026-08-04: 6 commits2026-08-05: 7 commits2026-08-06: 0 commits2026-08-07: 2 commits2026-08-08: 7 commits2026-08-09: 0 commits2026-08-10: 3 commits2026-08-11: 16 commits2026-08-12: 3 commits2026-08-13: 4 commits2026-08-14: 9 commits2026-08-15: 6 commits2026-08-16: 6 commits2026-08-17: 7 commits2026-08-18: 1 commit2026-08-19: 2 commits2026-08-20: 1 commit2026-08-21: 0 commits2026-08-22: 7 commits2026-08-23: 9 commits2026-08-24: 17 commits2026-08-25: 9 commits2026-08-26: 0 commits2026-08-27: 11 commits2026-08-28: 6 commits2026-08-29: 8 commits2026-08-30: 17 commits2026-08-31: 7 commits2026-09-01: 19 commits2026-09-02: 16 commits2026-09-03: 9 commits2026-09-04: 10 commits2026-09-05: 2 commits2026-09-06: 18 commits2026-09-07: 3 commits2026-09-08: 17 commits2026-09-09: 7 commits2026-09-10: 8 commits2026-09-11: 10 commits2026-09-12: 28 commits2026-09-13: 10 commits2026-09-14: 27 commits2026-09-15: 12 commits2026-09-16: 26 commits2026-09-17: 23 commits2026-09-18: 24 commits2026-09-19: 12 commits2026-09-20: 29 commits2026-09-21: 5 commits2026-09-22: 39 commits2026-09-23: 27 commits2026-09-24: 43 commits2026-09-25: 30 commits2026-09-26: 14 commits2026-09-27: 29 commits2026-09-28: 30 commits2026-09-29: 11 commits2026-09-30: 38 commits2026-10-01: 32 commits2026-10-02: 20 commits2026-10-03: 30 commits2026-10-04: 30 commits2026-10-05: 35 commits2026-10-06: 38 commits2026-10-07: 36 commits2026-10-08: 46 commits2026-10-09: 31 commits2026-10-10: 43 commits2026-10-11: 34 commits2026-10-12: 24 commits2026-10-13: 19 commits2026-10-14: 49 commits2026-10-15: 24 commits2026-10-16: 16 commits2026-10-17: 10 commits2026-10-18: 38 commits2026-10-19: 36 commits2026-10-20: 25 commits2026-10-21: 29 commits2026-10-22: 34 commits2026-10-23: 41 commits2026-10-24: 47 commits2026-10-25: 57 commits2026-10-26: 34 commits2026-10-27: 26 commits2026-10-28: 12 commits2026-10-29: 13 commits2026-10-30: 17 commits2026-10-31: 17 commits2026-11-01: 14 commits2026-11-02: 13 commits2026-11-03: 1 commit2026-11-04: 13 commits2026-11-05: 18 commits2026-11-06: 15 commits2026-11-07: 14 commits2026-11-08: 21 commits2026-11-09: 25 commits2026-11-10: 22 commits2026-11-11: 12 commits2026-11-12: 27 commits2026-11-13: 16 commits2026-11-14: 10 commits2026-11-15: 7 commits2026-11-16: 6 commits2026-11-17: 18 commits2026-11-18: 15 commits2026-11-19: 0 commits2026-11-20: 0 commits2026-11-21: 0 commits
4,291 commits in the last yearLessMore

Signals and awards

derived from tracked data
  • Landmark project

    85,484 stars

  • Very active

    4,291 commits in 52 weeks

  • Community-driven

    ~678 contributors

  • Well documented

    High community health score

  • Permissive license

    MIT

  • Repeat trending

    21 trending appearances

  • Top 10% tracked

    Rank 110 of 1243

What deer-flow does

DeerFlow acts as a highly extensible super-agent harness designed to tackle complex, long-horizon tasks that may take minutes to hours to execute. It systematically coordinates multiple specialized sub-agents alongside managed memory and secure execution sandboxes to automate intricate coding, research, and data gathering workflows. Version 2.0 represents a complete, ground-up rewrite focused on robust task orchestration and integrating intelligent external toolsets, such as deep search and crawling. The framework natively supports seamless integration with various LLM providers and enables developers to trace complex multi-step reasoning natively via LangSmith.

AI researchers and senior software engineers looking to build, orchestrate, and debug extremely complex, long-running multi-agent workflows. It is designed for developers seeking efficiency. It helps streamline their workflows and save time.

  • Sub-Agent Orchestration: Dynamically routes complex tasks to specialized, highly focused sub-agents to parallelize long-horizon workflows.
  • Sandbox Execution: Encloses task execution within highly secure environment sandboxes, allowing agents to write and test code safely.
  • Integrated Memory Management: Persists context and intermediate reasoning securely across extremely long, multi-hour agent operations.
  • Extensible Skill System: Allows developers to rapidly plug in new custom tools, APIs, and domain-specific capabilities into the agent framework.
  • InfoQuest Integration: Bundles out-of-the-box support for advanced intelligent search and deep crawling toolsets directly into the harness.
  • Desktop Inspection Tooling: Pairs natively with the LLM Space companion app to visually trace, replay, and benchmark complex agent behaviors.

Where teams use it

Deep Automated Research

Researchers deploy the framework to crawl massive documentation sites iteratively and synthesize comprehensive technical reports automatically over several hours.

Complex Code Generation

Software teams utilize the sandboxed sub-agents to rapidly scaffold, test, and debug massive full-stack application architectures autonomously.

Agent Capability Prototyping

AI developers use the native LLM Space integration to meticulously prototype, step-debug, and benchmark experimental multi-agent workflows.

Long-Horizon Data Extraction

Data engineers instruct the agent to autonomously navigate complex corporate portals, extract specific metrics, and compile structured datasets securely.

Getting started: npm install -g @bytedance/deer-flow

README

main branch

English | 中文 | 日本語 | Français | Русский | Português | 한국어

Python Node.js License: MIT

bytedance%2Fdeer-flow | Trendshift

On February 28th, 2026, DeerFlow claimed the 🏆 #1 spot on GitHub Trending following the launch of version 2. Thanks a million to our incredible community — you made this happen! 💪🔥

DeerFlow (Deep Exploration and Efficient Research Flow) is an open-source super agent harness that orchestrates sub-agents, memory, and sandboxes to do almost anything — powered by extensible skills.

deer-flow-720p.mp4

Note

DeerFlow 2.0 is a ground-up rewrite. It shares no code with v1. If you're looking for the original Deep Research framework, it's maintained on the 1.x branch — contributions there are still welcome. Active development has moved to 2.0.

Official Website

Learn more and see real demos on our official website. The landing-page case studies open as allowlisted, read-only showcases without requiring a sign-in.

Sister Projects

image
  • LLM Space - Meet our secret weapon behind DeerFlow — one desktop tool to prototype agent ideas, inspect each harness step, replay failures, and benchmark performance.

Coding Plan from ByteDance Volcengine

InfoQuest

DeerFlow has newly integrated the intelligent search and crawling toolset independently developed by BytePlus — InfoQuest (supports free online experience)

InfoQuest_banner

One-Line Agent Setup

If you use Claude Code, Codex, Cursor, Windsurf, or another coding agent, you can hand it the setup instructions in one sentence:

Help me clone DeerFlow if needed, then bootstrap it for local development by following https://raw.githubusercontent.com/bytedance/deer-flow/main/Install.md

That prompt is intended for coding agents. It tells the agent to clone the repo if needed, choose Docker when available, and stop with the exact next command plus any missing config the user still needs to provide.

Quick Start

git clone https://github.com/bytedance/deer-flow.git
cd deer-flow
make setup          # interactive wizard: writes config.yaml and .env (about 2 minutes)

Then start DeerFlow with Docker (recommended) or run it locally:

# Docker
make docker-init    # pull the sandbox image (once, or when the image updates)
make docker-start   # start services
# Local development
make check          # verifies Node.js 22+, pnpm, uv, nginx
make install
make dev

The local commands use the pnpm version pinned in frontend/package.json. If a different global pnpm is on PATH, they use Corepack when available; otherwise they report the version mismatch before installing frontend dependencies.

Run make doctor after setting model credentials. It reports obvious placeholder API keys as incomplete configuration; replace them with real keys before testing model calls.

Open http://localhost:2026.

From Deep Research to Super Agent Harness

DeerFlow started as a Deep Research framework — and the community ran with it. Since launch, developers have pushed it far beyond research: building data pipelines, generating slide decks, spinning up dashboards, automating content workflows. Things we never anticipated.

That told us something important: DeerFlow wasn't just a research tool. It was a harness — a runtime that gives agents the infrastructure to actually get work done.

So we rebuilt it from scratch.

DeerFlow 2.0 is no longer a framework you wire together. It's a super agent harness — batteries included, fully extensible. Built on LangGraph and LangChain, it ships with everything an agent needs out of the box: a filesystem, memory, skills, sandbox-aware execution, and the ability to plan and spawn sub-agents for complex, multi-step tasks.

Use it as-is. Or tear it apart and make it yours.

Guides

Each guide is the full reference for its topic. Open the one you need.

Topic Guide
Models, providers, config.yaml, environment variables Configuration
DeepSeek web search, thinking mode and citation excerpts DeepSeek Web Search
Docker, local development, upgrades, production deployment Running the Application
Sandbox modes, file system, uploads and outputs Sandbox
boxd machines, bounded output copies and cleanup retries boxd sandbox provider
Skills, built-in tools, script workflows, Claude Code integration Skills & Tools
MCP servers MCP Server
Sub-agents, task delegation and optional SQLite checkpoint history Sub-Agents, Tool restrictions
Long-term memory Long-Term Memory
Session goals, context compaction, task notes, evidence-based decisions Context, Goals and Agent Decisions
Private knowledge retrieval (RAGFlow) Private Knowledge Retrieval
Agentic browser control Agentic Browser Control
Projects, instructions, document shelf Projects
Scheduled tasks Scheduled Tasks
Feishu, Slack, Telegram, Discord, DingTalk and other IM channels IM Channels
File attachments, downloads and Office previews File Previews
Token usage dashboard, workspace, chat archive Workspace UI
Terminal workbench Terminal Workbench (TUI)
Personal access tokens, stream actions, embedded Python client API Access and Python Client
Trace correlation, LangSmith, Langfuse, Monocle Tracing and Observability
Deployment risks, admin model, security recommendations Security Notice

Recommended Models

DeerFlow is model-agnostic — it works with any LLM that implements the OpenAI-compatible API. That said, it performs best with models that support:

  • Long context windows (100k+ tokens) for deep research and multi-step tasks
  • Reasoning capabilities for adaptive planning and complex decomposition
  • Multimodal inputs for image understanding and video comprehension
  • Strong tool-use for reliable function calling and structured outputs

More Documentation

⚠️ Security Notice

DeerFlow can execute commands and read and write files. It is designed to run in a local trusted environment, and a Gateway admin account is equivalent to code execution on the host. Before you deploy it on a server or expose it to a network, read the full Security Notice and SECURITY.md.

Contributing

We welcome contributions! Please see CONTRIBUTING.md for development setup, workflow, and guidelines.

License

This project is open source and available under the MIT License.

Acknowledgments

DeerFlow is built upon the incredible work of the open-source community. We are deeply grateful to all the projects and contributors whose efforts have made DeerFlow possible. Truly, we stand on the shoulders of giants.

We would like to extend our sincere appreciation to the following projects for their invaluable contributions:

  • LangChain: Their exceptional framework powers our LLM interactions and chains, enabling seamless integration and functionality.
  • LangGraph: Their innovative approach to multi-agent orchestration has been instrumental in enabling DeerFlow's sophisticated workflows.

These projects exemplify the transformative power of open-source collaboration, and we are proud to build upon their foundations.

Key Contributors

A heartfelt thank you goes out to the core authors of DeerFlow, whose vision, passion, and dedication have brought this project to life:

Your unwavering commitment and expertise have been the driving force behind DeerFlow's success. We are honored to have you at the helm of this journey.

Star History

Star History Chart

View on GitHub

Recent activity

commits and pull requests

Releases and announcements

3 total
  1. DeerFlow 2.2.0v2.2.0Nov 4, 2026

    # DeerFlow 2.2.0 DeerFlow 2.2 turns the 2.1 super-agent harness into a deployment-grade platform with a focus on **operating at scale and delegating with trust**: scheduled tasks grow into goal-driven workflows with fair multi-owner execution, every subsystem from IM channels to workflows runs across multiple Gateway instances, the extension platform ships full-stack plugins, knowledge retrieval becomes provider-independent with verifiable citations, and models, memory and channels gain production-grade management — hardened by fail-closed defaults, at-rest credential encryption, and a much stricter uploads and paths layer. This release closes the [2.2.0 milestone](https://github.com/bytedance/deer-flow/milestone/3) with **1068 merged PRs** since the 2.1.0 release. > 📖 Full notes: [CHANGELOG.md](../CHANGELOG.md) · [中文版](../CHANGELOG_zh.md) --- ## ⚠️ Breaking changes - **Local dev binds loopback** — `make dev` / `make start` no longer listen on all interfaces; ports 2026/8001/3000 and `/setup` stay off LAN/VPN. Set `BIND_HOST=0.0.0.0` in `.env` to expose the stack, and note that values nginx would misread (`0`, `1.2.3`, bracketed IPv6) are now re

  2. v2.1.0 Releasev2.1.0Sep 24, 2026

    # DeerFlow 2.1.0 DeerFlow 2.1 builds on the 2.0 super-agent harness with a focus on **trust, scale, and operability**: verifiable agent execution, durable batch delegation, pluggable memory backends, four new sandbox providers, an out-of-tree extension system, and enterprise-grade authentication and authorization — wrapped in a much richer workspace with projects, conversation branching, and referenced conversations. This release closes the [2.1.0 milestone](https://github.com/bytedance/deer-flow/milestone/2) with **772 merged PRs** since the 2.0.0 release. > 📖 Full notes: [CHANGELOG.md](CHANGELOG.md) · [中文版](CHANGELOG_zh.md) --- ## ⚠️ Breaking changes - **Trace ids are unconditional** — every Gateway HTTP response carries an `X-Trace-Id` header, and `logging.enhance.enabled` now controls log output only. Client-supplied `deerflow_trace_id` values in run metadata are overwritten so header, logs, and the persisted run cannot disagree — send the `X-Trace-Id` request header to pin a correlation id. ([#5119]) - **`/mnt/skills` is reserved** for managed enabled-only skill projections. `DEER_FLOW_HOST_SKILLS_PATH` / `SKILLS_HOST_PATH` are no longe

  3. DeerFlow 2.0.0 releasedv2.0.0Jun 25, 2026

    # DeerFlow 2.0.0 DeerFlow 2.0 is a **ground-up rewrite** around a "super agent" harness that orchestrates **sub-agents**, **persistent memory**, **sandboxed execution**, and an extensible **skills/tools** system. It shares no code with the 1.x line, which lives on the [`main-1.x` branch](https://github.com/bytedance/deer-flow/tree/main-1.x). This release closes the [2.0.0 milestone](https://github.com/bytedance/deer-flow/milestone/1) with **182 merged PRs** since the first 2.0 milestone tag. > 📖 Full notes: [CHANGELOG.md](CHANGELOG.md) · [中文版](CHANGELOG_zh.md) --- ## ⚠️ Breaking change - **Run hydration** — runs now hydrate from `RunStore` and persist `interrupted` status. Cancellation now requires the worker who owns the run; cross-worker cancels return `409` instead of silently appearing successful. ([#2932]) ## ✨ Highlights - **Custom agents that update themselves** — agents can persist edits to their own `SOUL.md` / `config.yaml` from a normal chat, with full per-user isolation. ([#2713]) - **User-owned IM channel connections** — users can bind their own Slack, Telegram, Discord, Feishu/Lark, DingTalk, WeChat, and WeCom accounts on t

Code frequency

additions and deletions
+154.6K-154.6KWeek of 2025-11-23: +2,642 linesWeek of 2025-11-23: -491 linesWeek of 2025-11-30: +2,510 linesWeek of 2025-11-30: -338 linesWeek of 2025-12-07: +451 linesWeek of 2025-12-07: -106 linesWeek of 2025-12-14: +1,831 linesWeek of 2025-12-14: -121 linesWeek of 2025-12-21: +3,064 linesWeek of 2025-12-21: -66 linesWeek of 2025-12-28: +44 linesWeek of 2025-12-28: -11 linesWeek of 2026-01-04: +1,046 linesWeek of 2026-01-04: -144 linesWeek of 2026-01-11: +49,970 linesWeek of 2026-01-11: -6,862 linesWeek of 2026-01-18: +78,212 linesWeek of 2026-01-18: -18,786 linesWeek of 2026-01-25: +48,357 linesWeek of 2026-01-25: -10,453 linesWeek of 2026-02-01: +42,129 linesWeek of 2026-02-01: -20,898 linesWeek of 2026-02-08: +19,581 linesWeek of 2026-02-08: -154,609 linesWeek of 2026-02-15: +246 linesWeek of 2026-02-15: -114 linesWeek of 2026-02-22: +5,064 linesWeek of 2026-02-22: -811 linesWeek of 2026-03-01: +9,025 linesWeek of 2026-03-01: -1,219 linesWeek of 2026-03-08: +34,770 linesWeek of 2026-03-08: -19,522 linesWeek of 2026-03-15: +4,263 linesWeek of 2026-03-15: -535 linesWeek of 2026-03-22: +14,256 linesWeek of 2026-03-22: -1,905 linesWeek of 2026-03-29: +30,174 linesWeek of 2026-03-29: -8,825 linesWeek of 2026-04-05: +46,382 linesWeek of 2026-04-05: -2,840 linesWeek of 2026-04-12: +10,377 linesWeek of 2026-04-12: -3,605 linesWeek of 2026-04-19: +5,354 linesWeek of 2026-04-19: -2,097 linesWeek of 2026-04-26: +13,047 linesWeek of 2026-04-26: -4,251 linesWeek of 2026-05-03: +8,378 linesWeek of 2026-05-03: -921 linesWeek of 2026-05-10: +8,854 linesWeek of 2026-05-10: -1,165 linesWeek of 2026-05-17: +15,769 linesWeek of 2026-05-17: -1,151 linesWeek of 2026-05-24: +7,382 linesWeek of 2026-05-24: -969 linesWeek of 2026-05-31: +5,337 linesWeek of 2026-05-31: -1,614 linesWeek of 2026-06-07: +35,386 linesWeek of 2026-06-07: -2,096 linesWeek of 2026-06-14: +12,234 linesWeek of 2026-06-14: -1,490 linesWeek of 2026-06-21: +21,998 linesWeek of 2026-06-21: -2,469 linesWeek of 2026-06-28: +56,472 linesWeek of 2026-06-28: -4,032 linesWeek of 2026-07-05: +47,553 linesWeek of 2026-07-05: -2,658 linesWeek of 2026-07-12: +36,277 linesWeek of 2026-07-12: -8,430 linesWeek of 2026-07-19: +63,330 linesWeek of 2026-07-19: -5,281 linesWeek of 2026-07-26: +72,482 linesWeek of 2026-07-26: -7,745 linesWeek of 2026-08-02: +18,508 linesWeek of 2026-08-02: -1,842 linesWeek of 2026-08-09: +26,871 linesWeek of 2026-08-09: -3,388 linesWeek of 2026-08-16: +13,442 linesWeek of 2026-08-16: -565 linesWeek of 2026-08-23: +41,808 linesWeek of 2026-08-23: -2,283 linesWeek of 2026-08-30: +61,294 linesWeek of 2026-08-30: -3,849 linesWeek of 2026-09-06: +57,616 linesWeek of 2026-09-06: -3,520 linesWeek of 2026-09-13: +79,940 linesWeek of 2026-09-13: -7,056 linesWeek of 2026-09-20: +87,173 linesWeek of 2026-09-20: -5,529 linesWeek of 2026-09-27: +65,285 linesWeek of 2026-09-27: -4,600 linesWeek of 2026-10-04: +129,554 linesWeek of 2026-10-04: -10,193 linesWeek of 2026-10-11: +106,957 linesWeek of 2026-10-11: -18,483 linesWeek of 2026-10-18: +86,842 linesWeek of 2026-10-18: -8,204 linesWeek of 2026-10-25: +43,501 linesWeek of 2026-10-25: -4,950 linesWeek of 2026-11-01: +30,903 linesWeek of 2026-11-01: -1,747 linesWeek of 2026-11-08: +75,966 linesWeek of 2026-11-08: -20,382 linesWeek of 2026-11-15: +60,616 linesWeek of 2026-11-15: -35,714 linesNov 23, 2025Nov 15, 2026
+1.8M lines added, -430.9K removed over the last year.

Commits per week

last 52 weeks
2590Week of 2025-11-23: 13 commitsWeek of 2025-11-30: 7 commitsWeek of 2025-12-07: 6 commitsWeek of 2025-12-14: 6 commitsWeek of 2025-12-21: 10 commitsWeek of 2025-12-28: 3 commitsWeek of 2026-01-04: 9 commitsWeek of 2026-01-11: 166 commitsWeek of 2026-01-18: 208 commitsWeek of 2026-01-25: 166 commitsWeek of 2026-02-01: 227 commitsWeek of 2026-02-08: 114 commitsWeek of 2026-02-15: 8 commitsWeek of 2026-02-22: 21 commitsWeek of 2026-03-01: 30 commitsWeek of 2026-03-08: 47 commitsWeek of 2026-03-15: 26 commitsWeek of 2026-03-22: 83 commitsWeek of 2026-03-29: 91 commitsWeek of 2026-04-05: 86 commitsWeek of 2026-04-12: 44 commitsWeek of 2026-04-19: 37 commitsWeek of 2026-04-26: 59 commitsWeek of 2026-05-03: 40 commitsWeek of 2026-05-10: 35 commitsWeek of 2026-05-17: 46 commitsWeek of 2026-05-24: 29 commitsWeek of 2026-05-31: 22 commitsWeek of 2026-06-07: 70 commitsWeek of 2026-06-14: 57 commitsWeek of 2026-06-21: 66 commitsWeek of 2026-06-28: 62 commitsWeek of 2026-07-05: 87 commitsWeek of 2026-07-12: 113 commitsWeek of 2026-07-19: 110 commitsWeek of 2026-07-26: 120 commitsWeek of 2026-08-02: 32 commitsWeek of 2026-08-09: 41 commitsWeek of 2026-08-16: 24 commitsWeek of 2026-08-23: 60 commitsWeek of 2026-08-30: 80 commitsWeek of 2026-09-06: 91 commitsWeek of 2026-09-13: 134 commitsWeek of 2026-09-20: 187 commitsWeek of 2026-09-27: 190 commitsWeek of 2026-10-04: 259 commitsWeek of 2026-10-11: 176 commitsWeek of 2026-10-18: 250 commitsWeek of 2026-10-25: 176 commitsWeek of 2026-11-01: 88 commitsWeek of 2026-11-08: 133 commitsWeek of 2026-11-15: 46 commitsNov 23, 2025Nov 15, 2026
4.3K commits in the last 52 weeks.

When work happens

weekday and hour
SunMonTueWedThuFriSat036912151821Sun 0:00 — 14 commitsSun 1:00 — 0 commitsSun 2:00 — 2 commitsSun 3:00 — 1 commitsSun 4:00 — 8 commitsSun 5:00 — 4 commitsSun 6:00 — 5 commitsSun 7:00 — 26 commitsSun 8:00 — 36 commitsSun 9:00 — 43 commitsSun 10:00 — 58 commitsSun 11:00 — 66 commitsSun 12:00 — 17 commitsSun 13:00 — 21 commitsSun 14:00 — 28 commitsSun 15:00 — 43 commitsSun 16:00 — 33 commitsSun 17:00 — 33 commitsSun 18:00 — 13 commitsSun 19:00 — 34 commitsSun 20:00 — 40 commitsSun 21:00 — 61 commitsSun 22:00 — 77 commitsSun 23:00 — 44 commitsMon 0:00 — 14 commitsMon 1:00 — 4 commitsMon 2:00 — 7 commitsMon 3:00 — 9 commitsMon 4:00 — 2 commitsMon 5:00 — 2 commitsMon 6:00 — 12 commitsMon 7:00 — 32 commitsMon 8:00 — 34 commitsMon 9:00 — 45 commitsMon 10:00 — 34 commitsMon 11:00 — 34 commitsMon 12:00 — 22 commitsMon 13:00 — 23 commitsMon 14:00 — 38 commitsMon 15:00 — 60 commitsMon 16:00 — 49 commitsMon 17:00 — 24 commitsMon 18:00 — 24 commitsMon 19:00 — 31 commitsMon 20:00 — 33 commitsMon 21:00 — 42 commitsMon 22:00 — 41 commitsMon 23:00 — 40 commitsTue 0:00 — 14 commitsTue 1:00 — 3 commitsTue 2:00 — 2 commitsTue 3:00 — 3 commitsTue 4:00 — 3 commitsTue 5:00 — 3 commitsTue 6:00 — 3 commitsTue 7:00 — 29 commitsTue 8:00 — 34 commitsTue 9:00 — 50 commitsTue 10:00 — 52 commitsTue 11:00 — 53 commitsTue 12:00 — 11 commitsTue 13:00 — 31 commitsTue 14:00 — 30 commitsTue 15:00 — 37 commitsTue 16:00 — 29 commitsTue 17:00 — 35 commitsTue 18:00 — 26 commitsTue 19:00 — 29 commitsTue 20:00 — 19 commitsTue 21:00 — 42 commitsTue 22:00 — 58 commitsTue 23:00 — 49 commitsWed 0:00 — 3 commitsWed 1:00 — 4 commitsWed 2:00 — 5 commitsWed 3:00 — 7 commitsWed 4:00 — 5 commitsWed 5:00 — 6 commitsWed 6:00 — 17 commitsWed 7:00 — 34 commitsWed 8:00 — 50 commitsWed 9:00 — 52 commitsWed 10:00 — 74 commitsWed 11:00 — 27 commitsWed 12:00 — 16 commitsWed 13:00 — 16 commitsWed 14:00 — 41 commitsWed 15:00 — 30 commitsWed 16:00 — 33 commitsWed 17:00 — 28 commitsWed 18:00 — 27 commitsWed 19:00 — 34 commitsWed 20:00 — 29 commitsWed 21:00 — 44 commitsWed 22:00 — 43 commitsWed 23:00 — 40 commitsThu 0:00 — 8 commitsThu 1:00 — 11 commitsThu 2:00 — 5 commitsThu 3:00 — 4 commitsThu 4:00 — 7 commitsThu 5:00 — 4 commitsThu 6:00 — 6 commitsThu 7:00 — 26 commitsThu 8:00 — 44 commitsThu 9:00 — 60 commitsThu 10:00 — 41 commitsThu 11:00 — 52 commitsThu 12:00 — 27 commitsThu 13:00 — 23 commitsThu 14:00 — 50 commitsThu 15:00 — 62 commitsThu 16:00 — 52 commitsThu 17:00 — 41 commitsThu 18:00 — 22 commitsThu 19:00 — 23 commitsThu 20:00 — 34 commitsThu 21:00 — 33 commitsThu 22:00 — 45 commitsThu 23:00 — 34 commitsFri 0:00 — 10 commitsFri 1:00 — 1 commitsFri 2:00 — 1 commitsFri 3:00 — 2 commitsFri 4:00 — 5 commitsFri 5:00 — 2 commitsFri 6:00 — 5 commitsFri 7:00 — 28 commitsFri 8:00 — 35 commitsFri 9:00 — 44 commitsFri 10:00 — 32 commitsFri 11:00 — 36 commitsFri 12:00 — 7 commitsFri 13:00 — 15 commitsFri 14:00 — 61 commitsFri 15:00 — 61 commitsFri 16:00 — 50 commitsFri 17:00 — 47 commitsFri 18:00 — 27 commitsFri 19:00 — 28 commitsFri 20:00 — 33 commitsFri 21:00 — 67 commitsFri 22:00 — 66 commitsFri 23:00 — 48 commitsSat 0:00 — 17 commitsSat 1:00 — 4 commitsSat 2:00 — 4 commitsSat 3:00 — 2 commitsSat 4:00 — 0 commitsSat 5:00 — 4 commitsSat 6:00 — 5 commitsSat 7:00 — 14 commitsSat 8:00 — 41 commitsSat 9:00 — 37 commitsSat 10:00 — 49 commitsSat 11:00 — 49 commitsSat 12:00 — 12 commitsSat 13:00 — 9 commitsSat 14:00 — 26 commitsSat 15:00 — 41 commitsSat 16:00 — 60 commitsSat 17:00 — 44 commitsSat 18:00 — 52 commitsSat 19:00 — 36 commitsSat 20:00 — 39 commitsSat 21:00 — 59 commitsSat 22:00 — 73 commitsSat 23:00 — 41 commits
Commit volume by weekday and hour (UTC). Larger dots mean more commits.
DateListRankStars gained
Sep 8, 2026daily#7+188
Sep 7, 2026daily#7+188
Aug 3, 2026daily#14+209
Aug 2, 2026daily#14+209
Jun 23, 2026daily#17+7
Jun 22, 2026daily#20+13
Mar 30, 2026daily#8+199
Mar 29, 2026daily#12+224
Mar 28, 2026daily#11+190
Mar 27, 2026daily#5+236
Mar 26, 2026daily#5+238
Mar 25, 2026daily#1+407
Mar 24, 2026daily#1+532
Mar 23, 2026daily#3+423
Mar 22, 2026daily#4+594
  • 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

  • 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

  • donnemartin/system-design-primer

    Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.

    378.7K stars · Python

  • obra/superpowers

    An agentic skills framework & software development methodology that works.

    322.9K stars · Shell