Code Repository Intelligence Embedding Tools

Tools for indexing, analyzing, and semantically searching code repositories using embeddings and AST parsing. Includes code understanding, commit message generation, and code-aware Q&A systems. Does NOT include general code review platforms, CI/CD tools, or non-semantic code search.

There are 75 code repository intelligence tools tracked. 9 score above 50 (established tier). The highest-rated is dtsola/xiaoyaosearch at 67/100 with 1,207 stars. 3 of the top 10 are actively maintained.

Get all 75 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=embeddings&subcategory=code-repository-intelligence&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	dtsola/xiaoyaosearch 小遥搜索，听懂你的话、看懂你的图，用AI找到本地任何文件。让搜索像聊天一样简单。XiaoyaoSearch: Understands your...	67	Established	1,207	Python
2	cocoindex-io/cocoindex Data transformation framework for AI. Ultra performant, with incremental...	62	Established	6,438	Rust
3	justincasher/lean-explore A search engine for Lean 4 declarations	60	Established	55	Python
4	Ryandonofrio3/osgrep Open Source Semantic Search for your AI Agent	58	Established	1,080	TypeScript
5	yoanbernabeu/grepai Semantic Search & Call Graphs for AI Agents (100% Local)	58	Established	1,443	C
6	infinilabs/coco-server 🥥 Coco AI Server - Search, Connect, Collaborate, AI-powered Enterprise...	56	Established	134	TypeScript
7	probelabs/probe AI-friendly semantic code search engine for large codebases. Combines...	53	Established	494	Rust
8	starthackHQ/Contextinator Turning messy repos into weapons of mass structured context.	53	Established	22	Python
9	scarletkc/vexor A semantic search engine for files and code.	52	Established	208	Python
10	revokslab/codecrawl 🌊 Turn entire codebases into LLM-ready data. Extract data, search, and...	47	Emerging	79	TypeScript
11	cyberytti/ToolHunt This is a local search engine to search for cybersecurity tools. It has...	43	Emerging	201	HTML
12	SylphxAI/coderag Lightning-fast semantic code search with AST chunking (15+ languages) -...	42	Emerging	7	TypeScript
13	auyelbekov/rawq Context retrieval engine for AI agents — semantic + lexical search over codebases	41	Emerging	31	Rust
14	XiaoConstantine/sgrep CLI for semantic grep	40	Emerging	11	Go
15	tomohiro-owada/devrag Markdown vector search MCP server for Claude Code. Natural language search...	39	Emerging	36	Go
16	SecrinLabs/secrin The living wiki that writes itself.	38	Emerging	4	Python
17	billlzzz10/bl1nk-mcp-server Modular, audit-ready memory system combining knowledge graph, semantic...	38	Emerging	1	TypeScript
18	rekal-dev/rekal-cli Git-anchored decentralised intent(conversation) ledger for teams who build with AI	36	Emerging	4	Go
19	definitive-io/code-indexer-loop Code Indexer Loop is a Python library for indexing and retrieving source...	36	Emerging	176	Python
20	M9nx/CodexA Codexa is a local semantic code intelligence CLI designed to help AI...	36	Emerging	18	Python
21	sagarmk/beacon-plugin Semantic code search plugin for Claude Code using hybrid vector search +...	36	Emerging	16	JavaScript
22	wjddusrb03/diffmind AI Code Review Memory - learns from your team's bug history and warns when...	35	Emerging	1	Python
23	mvp-scale/aOa Semantic compression Claude and Gemini. 5 angles of O(1) indexed search —...	34	Emerging	1	Go
24	pwrdrvr/ghcrawl Terminal UI and local CLI for crawling GitHub issues and pull requests,...	34	Emerging	6	TypeScript
25	iagocavalcante/claude-turbo-search Optimized file search and semantic indexing for large codebases in Claude Code	34	Emerging	9	Shell
26	chiraag-kakar/context-nexus Context Nexus is an AI-native backend platform and SDK for managing,...	32	Emerging	2	Python
27	jsbattig/code-indexer Python application to index code locally and support running server with...	31	Emerging	2	Python
28	zircote/rlm-rs-plugin Claude Code plugin for processing documents 100x larger than context limits...	28	Experimental	3	MDX
29	dvcdsys/code-index Semantic code search powered by embeddings. Search your codebase by meaning,...	25	Experimental	4	Go
30	sltnsrh/knowledge-base Semantic search knowledge base with vector embeddings and Claude MCP integration	25	Experimental	2	Python
31	Pomilon/Kestr High-performance daemon for real-time codebase indexing. Generates semantic...	24	Experimental	1	C++
32	AssahBismarkabah/42context A Local Context Engine	23	Experimental	6	TypeScript
33	Tomcat132025/odino 🔍 Discover and access your code quickly with Odino, a fast local semantic...	23	Experimental	—	Python
34	Shun0212/Owl-CLI Semantic code search using vector embeddings. Search your codebase with...	22	Experimental	1	Python
35	ShadReyes/cortex-recall Semantic code & git history search CLI — tree-sitter parsing, pluggable...	22	Experimental	1	TypeScript
36	usr-wwelsh/botdocs Turn md into a pretty site with chatbot	22	Experimental	1	CSS
37	Sharper-Flow/lgrep Dual-engine code intelligence for OpenCode: semantic code search plus symbol...	22	Experimental	1	Python
38	solomonneas/code-search-api Local semantic code search with Ollama embeddings, SQLite, and hybrid...	22	Experimental	—	Python
39	Aliipou/codebase_intelligence AI-powered codebase intelligence: semantic search, dependency analysis, and...	22	Experimental	—	Python
40	evoleinik/claude-grep Search Claude Code session history. Regex + semantic (vector) search. Single...	22	Experimental	1	Go
41	sert-xx/unified-blueprint Documentation-as-Code middleware — structure Markdown docs into a Document...	22	Experimental	1	TypeScript
42	damiandelmas/flex Local search and retrieval for AI Agents	22	Experimental	1	Python
43	andycandy/CausewayAI Next-gen semantic retrieval system. Combines the power of Qdrant vector...	21	Experimental	—	Python
44	souldriver007/karp-bible-code AI-assisted ELS (Equidistant Letter Spacing) Bible code research engine for...	21	Experimental	—	JavaScript
45	souldriver007/karp-word-graph AI-powered KJV Bible study companion for Claude Desktop. Semantic scripture...	21	Experimental	—	JavaScript
46	Stahldavid/sensegrep Semantic + structural code search for AI-native development	21	Experimental	—	TypeScript
47	jsuppe/loom 🧵 Requirements traceability for AI-assisted development. Extract...	21	Experimental	—	Python
48	mvp-scale/aOa-legacy 5 angles. 1 attack. O(1) indexed search. Up to 95% fewer tokens per...	21	Experimental	—	Shell
49	PEACEBINFLOW/mindscript-search Semantic & structural search engine for the MindScript ecosystem. Index...	20	Experimental	1	Python
50	PPierzc/hive 🐝🔍 Hive: A CLI Tool for Semantic Searching of Your Knowledge Base	20	Experimental	7	Python
51	parbhatkapila4/RepoDocs An AI-Powered Code Documentation Platform Automated documentation engine...	20	Experimental	3	TypeScript
52	josehu07/codetective Takes code, gives AI authorship detection in five clicks :mag_right:	20	Experimental	5	Rust
53	tanuj077/codeatlas CodeAtlas: AI-powered code search and chat system using AST parsing,...	19	Experimental	2	Python
54	MohammedNasserAhmed/CodeXpert CodeXpert: A cutting-edge AI-powered code analysis tool leveraging...	19	Experimental	3	Python
55	louisfghbvc/CppSeek AI-Powered Semantic Search for C/C++	19	Experimental	2	TypeScript
56	davidteren/code_grasp A CLI tool that uses the Qodo-Embed-1-1.5B embedding model to analyze code,...	19	Experimental	1	Python
57	moabualruz/rice-search A fully local, production-ready code search platform with hybrid BM25 +...	18	Experimental	1	Python
58	ThinkerYzu/kb-indexer LLM-powered knowledge base indexer that builds a growing semantic layer of...	17	Experimental	—	Python
59	nshkrdotcom/portfolio_manager AI-native personal project intelligence system - manage, track, and search...	17	Experimental	—	Elixir
60	Lioness100/decimeta A website to help you find the correct Dewey Decimal number for any subject using AI.	17	Experimental	3	HTML
61	nshkrdotcom/portfolio_coder Code Intelligence Platform: Repository analysis, semantic code search,...	17	Experimental	—	Elixir
62	copyleftdev/tala Intent-native narrative execution layer. Reimagines Linux shell history as a...	16	Experimental	2	Rust
63	souldriver007/karp-graph-lite "Personal knowledge graph for Claude Desktop — remember, recall, connect"	15	Experimental	—	JavaScript
64	gantumurbattumur/Github-aware-RAG Semantic search across your starred and own GitHub repos, right inside VS...	14	Experimental	1	Python
65	bhavesh-kalluru/genai-project-2026-03-27 AI-powered CLI that analyzes git diffs and generates conventional commit...	14	Experimental	—	Python
66	bhavesh-kalluru/genai-project-2026-03-26 AI-powered Python code review tool that detects anti-patterns using...	14	Experimental	—	Python
67	moijafcor/glean Ask plain-English questions about your projects — source code,...	14	Experimental	—	Python
68	NeaByteLab/AI-Indexing Code indexing examples for converting source code into structured repository...	13	Experimental	—	TypeScript
69	The-Focus-AI/embeddings-search-skill Claude Code plugin for hybrid document search (grep + semantic embeddings)	13	Experimental	—	TypeScript
70	NeaByteLab/Dev-Knowledge Build searchable knowledge bases by scraping developer documentation and...	13	Experimental	—	TypeScript
71	oroinc/documentation-markdown Markdown variant for AI	13	Experimental	—	—
72	luanvenancio/design-extractor A self-hosted backend that captures websites, extracts design signals, and...	13	Experimental	—	TypeScript
73	Agents365-ai/semanticscholar-skill Claude Code skill for academic paper search using the Semantic Scholar API	13	Experimental	—	Python
74	SyntaxSidekick/historisnap HistoriSnap is an interactive explorer of historical events — from ancient...	12	Experimental	1	JavaScript
75	SoulDev07/CodeCompass CodeCompass transforms any GitHub repo into an interactive, searchable...	11	Experimental	—	JavaScript

Comparisons in this category

osgrep and grepai (58 vs 58) grepai and sgrep (58 vs 40) osgrep and sgrep (58 vs 40) probe and rawq (53 vs 41) probe and coderag (53 vs 42)