bytedance/deer-flow
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.
About the project
Open-source harness for long-horizon AI agent tasks: orchestrates sub-agents, memory, sandboxes and skills for research, coding and content creation.
Useful for
- Run deep research on a topic with automated source gathering and analysis
- Build a multi-step agent pipeline with sub-agents and a code sandbox
- Connect DeerFlow to Claude Code or Cursor for automatic environment setup
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 23 stars so far today, about 54 expected by the end of the day.
- GitHub Trending Python today: #10, +79 stars.
- About 30 forks a day — people are taking the code.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 83,203
- Today
- 23 · ≈ 54 by evening
- Forks
- 11,543
- Issues and pull requests
- 5,843
- Watchers
- 344
- Language
- Python
- License
- MIT
- Latest release
- v2.1.0 · September 24, 2026
- Created
- May 7, 2025
- Last push
- September 29, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 29, 2026GitHub Trending Python today: #10, +79 stars
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/bytedance/deer-flow)Similar by description
-
0.0
agentscope-ai-java/agentscope-java
Java framework for building distributed, long-running enterprise-grade agents with events, tool-call permissions, middleware, sandboxes and multi-agent orchestration.
-
1.6
ApodexAI/FrontierAgent
Open-source agent runtime with a terminal TUI: ReAct and Agent Team modes for long-horizon research and file work in a sandbox, plus an evaluation suite.