GitHub Codebase RAG Vector Databases

Tools for indexing and querying GitHub repositories using RAG to enable semantic code search, repository understanding, and conversational code analysis. Does NOT include general code review tools, issue similarity detection, or RAG applications for non-code documents.

There are 32 github codebase rag tools tracked. 1 score above 50 (established tier). The highest-rated is SynapseKit/SynapseKit at 58/100 with 3 stars and 2,488 monthly downloads.

Get all 32 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=vector-db&subcategory=github-codebase-rag&limit=20"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.

#	Tool	Score	Tier	Stars	Language
1	SynapseKit/SynapseKit Ship LLM apps faster. Production-grade LLM framework for Python....	58	Established	3	Python
2	hoangsonww/FRED-Data-Analysis 💸 A comprehensive AI-powered data explorer that combines FRED economic data...	44	Emerging	15	TypeScript
3	vericle/intellyweave AI-powered platform for OSINT intelligence analysis. Features archive...	44	Emerging	52	Python
4	codextde/vectorbase-ai-knowledgebase Open-source AI knowledge base SaaS. Build RAG-powered chatbots from...	33	Emerging	2	TypeScript
5	Priyadarshan-Garg/Synapse Sybapse : Low-Latency Hybrid Edge Computing	29	Experimental	1	C++
6	alexpovel/issuedigger For your repository, issuedigger will notify authors of new issues about...	26	Experimental	16	TypeScript
7	Open-Technology-Foundation/customkb CustomKB transforms your documents into AI-powered, searchable...	25	Experimental	4	Python
8	tankyhsu/nanobot-viking OpenViking knowledge base integration for nanobot — RAG augmentation,...	24	Experimental	1	Python
9	dsk-dev-ai/repochat-ai Chat with any GitHub repository using local AI (Ollama). Understand...	22	Experimental	—	Python
10	AlanDev-fr/repoinsight Understand any GitHub repository in seconds with AI — semantic search, repo...	22	Experimental	—	TypeScript
11	gperdrizet/nixx Synthetic research assistant	22	Experimental	—	Python
12	younismahmoud1234/gitsage Index GitHub repositories to enable AI-driven code queries with precise...	22	Experimental	—	Java
13	hackastak/repog RepoG is a CLI-first, local AI-powered tool that helps you explore, search,...	22	Experimental	—	Go
14	Sayan-Mondal2022/enterprise-knowledge-copilot An AI-powered Enterprise Knowledge Base Copilot using Vector Search and RAG...	20	Experimental	1	Jupyter Notebook
15	rameshreddy-adutla/gitsage 🧙 A sage that knows your codebase — RAG-powered GitHub org knowledge bot...	20	Experimental	1	Java
16	Deepakkasyapa11/GitQuery-AI AI-powered GitHub repository analyzer. Uses Gemini 1.5 Flash for RAG-based...	20	Experimental	1	TypeScript
17	eswar-7116/CalGist AI powered Google Calendar events summarizer built using Next.js, Supabase...	20	Experimental	12	TypeScript
18	dannyl1u/doppelganger Similarity detection for Github Issues + AI code reviews	19	Experimental	58	Python
19	aymen-000/PaperLens An intelligent research discovery platform that automatically crawls ArXiv...	17	Experimental	2	TypeScript
20	Daryl131/rag-nodejs 📄 Create a lightweight Node.js backend for Retrieval-Augmented Generation,...	16	Experimental	—	JavaScript
21	Ujjwal-Bajpayee/OpenScout OpenScout is a Perplexity-inspired answer engine that turns a single...	16	Experimental	1	Python
22	Garvit-Nag/Qodex AI-powered code repository analysis and chat system	15	Experimental	1	TypeScript
23	kabir276/GreptileCodeMirrorer Code Mirrorer: It clones and implements features from any public repository,...	15	Experimental	6	TypeScript
24	Rohit16031/kb-service-superfone Standalone KB service that ingests documents, chunks & embeds them, stores...	14	Experimental	—	Python
25	zoepranataksm/Mind_Vault_AI 📚 Automate knowledge transfer with Mind Vault, an AI-driven system that...	14	Experimental	—	JavaScript
26	YoussefAbbes/Synapse-Entreprise-RAG-Document-Engine Synapse is a production-ready RAG engine for chatting with your PDFs. Built...	14	Experimental	—	Python
27	kimberlykuya/ai_analytics_copilot A local natural-language analytics assistant built on the Olist Brazilian...	14	Experimental	—	Python
28	mugnihidayah/synapse-instant-document-insight A production-ready Retrieval-Augmented Generation (RAG) API featuring...	14	Experimental	—	Python
29	garg-khushi/repo-intelligence-engine LLM-powered repository intelligence engine for contextual code...	12	Experimental	1	Python
30	24kr/rag-search-app RAG search app with Next.js & Google Gemini AI. Upload docs, search...	11	Experimental	—	TypeScript
31	christivn/mebox 🗃️✨ Mebox is an open-source RAG multi model tool, designed to efficiently...	11	Experimental	2	HTML
32	PhongCT1105/SyntheSearch 📚 SyntheSearch: A smart research tool that uses AI to find and synthesize...	11	Experimental	2	Jupyter Notebook