MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
GraphRAG code search over MCP. Parses code with tree-sitter, weaves a Neo4j code graph, and serves hybrid semantic search to AI agents at lower cost than grep.
PythonMITFew starsNo key
Semantic code search MCP server: Tree-sitter AST chunking + voyage-code-3 embeddings + hybrid retrieval (sqlite-vec + FTS5 + RRF) + Voyage rerank-2.5 + call graph expansion
PythonMIT★ 2Few starsNo key
An MCP server plus a CLI tool that indexes local code into a graph database to provide context to AI assistants.
PythonMIT★ 4.4kNo key
Read-only MCP server exposing MyHeritage Family Tree Builder (.ftb) and GEDCOM genealogy trees, with reverse-engineered format notes
PythonApache-2.0★ 2Few starsNo key
🗺️ Token-efficient code knowledge graph & MCP server for AI agents. 96% token reduction with zero-infra SQLite + tree-sitter.
PythonMIT★ 1Few starsNo key
Persistent code graph for AI agents. Tree-sitter → SQLite → MCP. Agents store understanding once, skip re-reads forever. 51–1500x fewer tokens.
PythonMIT★ 4Few starsNo key
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
PythonAGPL-3.0★ 41kNo key
Agent-native code intelligence: turn any repo into a queryable code graph over MCP. tree-sitter + SQLite, no embeddings, no API keys.
PythonMITFew starsNo key
search a codebase by what the code does, not the words in it. tree-sitter chunking, hybrid vector + bm25 retrieval, one sqlite file, offline.
PythonMITFew starsNo key
Local codebase intelligence CLI + MCP server for AI coding agents: SQLite code graph, 28 languages, 287 commands, 246 MCP tools, change-safety gates, audit evidence, zero API keys.
PythonApache-2.0★ 517No key
Headless Skill Hub and GitOps for Agentic Memory. Turn complex codebases and documents into version-controlled, immutable cognitive skills. Featuring AST chunking, cryptographic Delta Updates, and nat
PythonApache-2.0★ 5No key
Code graph for AI agents: impact analysis and call tracing over MCP (Python, TypeScript). Local, deterministic, SQLite.
PythonMIT★ 2Few starsNo key
A 100% local semantic code search tool featuring hybrid search (vector + BM25), AST-aware chunking, and native MCP integration for AI coding assistants.
PythonMIT★ 3Few starsNo key
Neo4j knowledge graph of Alliance codebases using TreeSitter for cross-repository analysis and pipeline tracing
PythonMIT★ 1Few starsNo key
Persistent memory for AI coding agents via MCP: a bitemporal knowledge graph of your codebase, served to Claude Code, Cursor, Gemini CLI, and any MCP client. Tree-sitter and Gemini Flash into Neo4j vi
PythonMIT★ 12No key
An MCP server plus a CLI tool that uses LSPs to index local code into a graph database to provide context to AI assistants.
PythonMIT★ 1Few starsNo key
Centralized codebase knowledge graph + coordinate index for AI coding agents. Backed by Neo4j 5.x Community, written in Python 3.11+, parses with Tree-sitter, exposes the graph to agents via the Model
PythonApache-2.0★ 1Few starsNo key
Nexus-Dev is an open-source MCP server that provides persistent memory for AI coding agents. It uses LanceDB as a local vector database and tree-sitter for multi-language intelligent code chunking.
PythonMIT★ 8No key
A structural similarity-based code security filter for MCP (Model Context Protocol). Blocks dangerous code patterns before they reach execution tools by comparing code structure against a blacklist of
PythonMITFew starsNo key
Local code indexing for AI coding assistants using Tree-sitter, SQLite, and the Model Context Protocol (MCP).
PythonApache-2.0★ 1Few starsNo key
Corpus forge syncs a local file system with a SQL database with vector embeddings for storing and serving sovereign AI models.
PythonApache-2.0★ 2Few starsNo key
Dual-view evidence for declared agent-tool effect contracts under ambiguous failures.
PythonApache-2.0Few starsNo key
Who stands behind it
