#2828th of 51 in RAG, knowledge and search
opendeepwiki
Generates wiki-style docs and chat for Git repos, with per-repo MCP endpoints
- Stars
- 3.7k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- C#
3,057 on 21 Apr 20263,661 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
OpenDeepWiki ingests Git URLs, ZIP archives or local directories and uses configured LLMs to generate READMEs, wiki catalogs, document pages, translations and mind maps. The ASP.NET Core (.NET 10) backend and Next.js 16 frontend publish the result as a public site and reuse it for a chat assistant, embedded chat and repository-scoped MCP endpoints. An admin console manages users, roles, API keys and AI providers.
Who it is for: Teams wanting auto-generated, searchable docs and MCP access for their repos
Strengths
- Accepts Git URLs, ZIP uploads and approved local directories as sources
- Per-repo MCP endpoints at /api/mcp/{owner}/{repo}
- Separate model bindings for catalog, content and translation; translation falls back to content model
- SQLite by default, PostgreSQL supported via compose.pgsql.yaml
Weaknesses
- Needs an external LLM API key; local model setup is not documented beyond optional Graphify Ollama
- Seeded default admin credentials must be changed manually before real use
- Several moving parts: .NET backend, Next.js web app, background workers
- Enterprise support and pricing exist; the split with the MIT edition is unclear
What it needs
- no GPU
- Compose
- Needs LLM API (OpenAI-compatible endpoint), SQLite or PostgreSQL, Docker Compose
- Models: OpenAI-compatible APIs, Ollama (Graphify only)
- port 3000
Quick answers
Is opendeepwiki open source?
Yes. Its code is on GitHub under the MIT license.
Can you run opendeepwiki with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does opendeepwiki need a GPU?
No, it runs without one.
Also in RAG, knowledge and search
See all 51| Rank | Project | Score |
|---|---|---|
| 1 | RAGFlowRAG engine with deep document parsing, template chunking and agentic retrieval | 90 out of 100 |
| 2 | LightRAGGraph-based RAG framework with a REST API server and web UI | 90 out of 100 |
| 3 | deeptutorSelf-hosted AI tutor with knowledge bases, guided learning, books and quizzes | 89 out of 100 |
| #4 | Open NotebookSelf-hosted NotebookLM alternative for research notebooks, chat, and podcasts | 89 out of 100 |
| #5 | MaxKBEnterprise knowledge-base agent platform with RAG, workflows and MCP tools | 87 out of 100 |