GitHub radar
DeerFlow: ByteDance Open-Source Agent Harness
ByteDance's open-source super agent harness — 82 000 GitHub stars, runs on Docker, and tackles long-horizon tasks by coordinating sub-agents with shared memory and sandboxes.
DeerFlow (Deep Exploration and Efficient Research Flow) is an open-source super agent harness from ByteDance, the company behind TikTok. Version 2.0, launched in February 2026, rebuilt the system from scratch as a multi-agent coordination platform. Sub-agents work in parallel — one searches the web, one writes and executes code in an isolated sandbox, one reviews results — all sharing long-term memory so context survives between sessions. Built-in skills include Claude Code, Codex CLI, MCP servers, web search via Tavily, Jina, or InfoQuest, and file creation. Compatible with OpenAI, Anthropic, Gemini, DeepSeek, Qwen, and any OpenAI-compatible API including OpenRouter. A web interface opens in your browser; setup uses an interactive wizard that takes about 2 minutes. 82 000+ GitHub stars; reached #1 on GitHub Trending after version 2 launched.
Why a vibe-coder should care
If you have tasks that combine research, coding, and review — without babysitting the agent every step — DeerFlow runs the full pipeline end to end. Sub-agents share a workspace and memory, so a multi-hour task doesn't hit context limits or lose earlier findings. You can hand setup to Claude Code or Codex in one sentence and be running in minutes.
How to install
Copy this and send it to your agent — Claude Code, Codex, any of them:
Help me set up DeerFlow from here: https://github.com/bytedance/deer-flow — clone the repo, follow Install.md, use Docker, ask me which LLM provider and API keys I have, and open the web interface on localhost. Ask if you need clarification.
Нужен Docker и от 8 ГБ оперативки — MacBook на M-чипе справится для тестов. Для постоянной работы рекомендуется 16 ГБ и более.
Open on GitHub▌ More finds