Source: https://seerepo.com/compare/dataelement/bisheng/vs/langchain-ai/local-deep-researcher
Markdown source: https://seerepo.com/compare/dataelement/bisheng/vs/langchain-ai/local-deep-researcher.md
Description: bisheng and local-deep-researcher share 6 technologies: OpenAI, LangChain, LangGraph, langchain-openai, langchain-ollama, and markdownify. Both are written in Python.

# bisheng vs local-deep-researcher

bisheng and local-deep-researcher share 6 technologies: OpenAI, LangChain, LangGraph, langchain-openai, langchain-ollama, and markdownify. Both are written in Python.

- [dataelement/bisheng](https://seerepo.com/r/dataelement/bisheng): BISHENG is an open-source enterprise Agent platform for building, deploying, and managing AI applications. It combines AI agents, workflows, RAG and knowledge management, desktop agent integration, and vibecoding app hosting with unified model management, evaluation, observability, access control, and enterprise administration.
- [langchain-ai/local-deep-researcher](https://seerepo.com/r/langchain-ai/local-deep-researcher): Fully local web research and report writing assistant

## What they share and what sets them apart

- In common: OpenAI, LangChain, LangGraph, langchain-openai, langchain-ollama, markdownify
- Only in bisheng: React, FastAPI, uvicorn, aiomysql, asyncpg, ibm-db, ibm-db-sa, oracledb, psycopg2-binary, pymongo, pymilvus, Celery, MongoDB, MySQL, Postgres, pymysql, MinIO, Vite, react-router-dom, matplotlib, cryptography, pyjwt, captcha, langchain-google-genai, MCP, opencv-python, dashscope, langchain-anthropic, langchain-deepseek, llama-index, e2b-code-interpreter, pymupdf, pillow, bs4, markdown, openpyxl, jinja2, Pydantic, loguru, docker, PostCSS, Tailwind CSS, class-variance-authority, React Hook Form, Radix UI, tanstack, Ariakit, react-activation, Framer, Headless UI, react-textarea-autosize, CodeSandbox, input-otp, react-dnd, react-resizable-panels, react-transition-group, rc-input-number, react-dnd-html5-backend, @dicebear/core, @hello-pangea/dnd, react-avatar-editor, react-flip-toolkit, react-lazy-load-image-component, react-speech-recognition, Lucide, @radix-ui/react-icons, DiceBear, react-markdown, rehype-highlight, rehype-katex, remark-gfm, remark-math, remark-supersub, unified, unist-util-visit, export-from-json, js-yaml, pdfjs-dist, qrcode.react, html-to-image, rehype-slug, remark-directive, Zod, dompurify, mammoth, xlsx, tailwind-merge, xyflow, react-syntax-highlighter, react-ace, react-dropzone, react-color, recharts, ace-builds, cmdk, react-day-picker, react-grid-layout, react-resizable, react-window, ansi-to-html, rehype-mathjax
- Only in local-deep-researcher: tavily-python

## Side by side

| | bisheng | local-deep-researcher |
|---|---|---|
| Size | 1,115,223 lines written, 4,262 code files | 946 lines written, 7 code files |
| Who writes it | 16.3% of its commits signed by AI. With Claude Code and Cursor | 0% of its commits signed by AI |
| Activity | Last push November 11, 2026, 9,587 commits, 12,249 stars | Last push October 15, 2026, 84 commits, 9,410 stars |
| Tests | 2,201 test files. 43.1% of its code files have a test that imports them | 0 test files |

- 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, bisheng or local-deep-researcher?

bisheng, with 1,115,223 lines written; local-deep-researcher has 946.

The proof: [dataelement/bisheng's code at commit af1894a](https://github.com/dataelement/bisheng/tree/af1894a53859708efb1db471c05b0915d53056d9)

### Which has more GitHub stars, bisheng or local-deep-researcher?

bisheng, with 12,249 stars; local-deep-researcher has 9,410.

The proof: [dataelement/bisheng on GitHub](https://github.com/dataelement/bisheng)

### Which has more tests, bisheng or local-deep-researcher?

bisheng, with 2,201 test files.

The proof: [dataelement/bisheng's code at commit af1894a](https://github.com/dataelement/bisheng/tree/af1894a53859708efb1db471c05b0915d53056d9)

### Which was updated more recently, bisheng or local-deep-researcher?

bisheng: its last push was on November 11, 2026, and local-deep-researcher's on October 15, 2026.

The proof: [dataelement/bisheng's commits on GitHub](https://github.com/dataelement/bisheng/commits)

### Which has more commits signed by AI, bisheng or local-deep-researcher?

bisheng: an AI signed 16.3% of its commits, with Claude Code and Cursor.

The proof: [the commits each tool signed in dataelement/bisheng](https://seerepo.com/r/dataelement/bisheng/ai)

## Sources

- dataelement/bisheng: Read on November 11, 2026, at commit af1894a (https://github.com/dataelement/bisheng/tree/af1894a53859708efb1db471c05b0915d53056d9)
- langchain-ai/local-deep-researcher: Read on November 15, 2026, at commit 9655564 (https://github.com/langchain-ai/local-deep-researcher/tree/96555649619b9c482442f2cba043312bd7692507)

## 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.
