Source: https://seerepo.com/compare/bytedance/deer-flow/vs/langchain-ai/deepagents
Markdown source: https://seerepo.com/compare/bytedance/deer-flow/vs/langchain-ai/deepagents.md
Description: deer-flow and deepagents share 7 technologies: aiosqlite, langgraph-checkpoint-sqlite, SQLite, LangChain, LangGraph, langchain-openai, and langchain-anthropic. Both are written in Python.

# deer-flow vs deepagents

deer-flow and deepagents share 7 technologies: aiosqlite, langgraph-checkpoint-sqlite, SQLite, LangChain, LangGraph, langchain-openai, and langchain-anthropic. Both are written in Python.

- [bytedance/deer-flow](https://seerepo.com/r/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.
- [langchain-ai/deepagents](https://seerepo.com/r/langchain-ai/deepagents): The batteries-included agent harness.

## What they share and what sets them apart

- In common: aiosqlite, langgraph-checkpoint-sqlite, SQLite, LangChain, LangGraph, langchain-openai, langchain-anthropic
- Only in deer-flow: FastAPI, starlette, uvicorn, React, Next.js, SQLAlchemy, alembic, pyjwt, cryptography, bcrypt, langchain-mcp-adapters, e2b-code-interpreter, exa-py, langchain-deepseek, langfuse, html5lib, beautifulsoup4, email-validator, jsonschema, kubernetes, Tailwind CSS, class-variance-authority, next-themes, @uiw/codemirror-theme-monokai, tailwind-merge, sonner, Radix UI, motion, @tanstack/react-virtual, @uiw/react-codemirror, react-resizable-panels, use-stick-to-bottom, @streamdown/code, canvas-confetti, cmdk, CodeMirror, embla-carousel-react, GSAP, Headless UI, Lucide, @radix-ui/react-icons, ai, streamdown, katex, shiki, papaparse, qrcode.react, rehype-katex, rehype-raw, rehype-sanitize, remark-gfm, remark-math, unist-util-visit, Zod
- Only in deepagents: fastmcp, anyio, AIOHTTP, agent-client-protocol, deepagents-code, deepagents, langsmith, langgraph-checkpoint, langgraph-prebuilt, MCP, langgraph-sdk, langchain-google-genai, voyageai, daytona, vercel, qrcode-terminal

## Side by side

| | deer-flow | deepagents |
|---|---|---|
| Size | 1,085,017 lines written, 1,515 code files | 731,023 lines written, 452 code files |
| Who writes it | 12.7% of its commits signed by AI. With Claude Code, GitHub Copilot, Cursor, Codex, and Factory | 1.2% of its commits signed by AI. With Claude Code, GitHub Copilot, Cursor, and Amp |
| Activity | Last push November 4, 2026, 4,588 commits, 84,984 stars | Last push November 7, 2026, 4,640 commits, 31,068 stars |
| Tests | 1,922 test files. 72.5% of its code files have a test that imports them | 672 test files. 18.6% of its code files have a test that imports them |

- Size: Lines written by people and agents, without generated ones; code files, without tests.
- Who writes it: A commit counts as AI's when it carries its signature: a Co-Authored-By line, its author name or the merge of its branch.
- Activity: From GitHub and its history, on the day SeeRepo read it.
- Tests: The files that test the code, and the share of code files a test imports.

## Frequently asked questions

### Which is bigger, deer-flow or deepagents?

deer-flow, with 1,085,017 lines written; deepagents has 731,023.

The proof: [bytedance/deer-flow's code at commit a46d922](https://github.com/bytedance/deer-flow/tree/a46d9221f8ab029ef0b7b8caae25c10ab4153395)

### Which has more GitHub stars, deer-flow or deepagents?

deer-flow, with 84,984 stars; deepagents has 31,068.

The proof: [bytedance/deer-flow on GitHub](https://github.com/bytedance/deer-flow)

### Which has more tests, deer-flow or deepagents?

deer-flow, with 1,922 test files; deepagents has 672.

The proof: [bytedance/deer-flow's code at commit a46d922](https://github.com/bytedance/deer-flow/tree/a46d9221f8ab029ef0b7b8caae25c10ab4153395)

### Which was updated more recently, deer-flow or deepagents?

deepagents: its last push was on November 7, 2026, and deer-flow's on November 4, 2026.

The proof: [langchain-ai/deepagents's commits on GitHub](https://github.com/langchain-ai/deepagents/commits)

### Which has more commits signed by AI, deer-flow or deepagents?

deer-flow: an AI signed 12.7% of its commits, with Claude Code, GitHub Copilot, Cursor, Codex, and Factory; in deepagents, 1.2%.

The proof: [the commits each tool signed in bytedance/deer-flow](https://seerepo.com/r/bytedance/deer-flow/ai)

## Sources

- bytedance/deer-flow: Read on November 4, 2026, at commit a46d922 (https://github.com/bytedance/deer-flow/tree/a46d9221f8ab029ef0b7b8caae25c10ab4153395)
- langchain-ai/deepagents: Read on November 7, 2026, at commit 9c5d330 (https://github.com/langchain-ai/deepagents/tree/9c5d330893e0580ece0422511248d1048373cd7f)

## What is your repo built with?

Any public repo, with no account: https://seerepo.com/r/owner/repo/built, with the owner and name it has on GitHub.