48 packages found
MCP Server for Tree-sitter
Token-saving code search for AI coding agents — TypeScript, JavaScript & Python (zero setup), C#, C++, Go & 30+ more, vi
Save 30% token costs when using Claude Code, Codex, OpenCode for free - with open source, local semantic search. Works f
@DeusDataHigh-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in mil
A Model Context Protocol (MCP) server that helps large language models index, search, and analyze code repositories with
XRAY MCP provides progressive code intelligence and navigation capabilities for AI assistants through structural code
Ask for the symbol, not the file. Token-efficient MCP server giving AI coding agents symbol-level reads of TS/JS, Rust
AI Distiller is ultra‑fast, open‑source tool for intelligently extracting only the essential public APIs, types, and str
The leading, most token-efficient MCP server for GitHub source code exploration via tree-sitter AST parsing
CodeScope does not understand code. It verifies it. A high-performance code graph engine with MCP protocol for AI agents
A sophisticated Model Context Protocol (MCP) server for analyzing Architectural Decision Records (ADRs) and providing de
MCP server for token-efficient large document analysis via the use of REPL state
Alcove is an MCP server that gives AI coding agents on-demand access to your private project docs — BM25 + vector hybrid
Semantic code searcher and codebase utility
The most comprehensive code intelligence MCP server for AI coding agents. 40+ tools, 30+ languages, 9 agent integrations
⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and
Deterministic persistent memory for AI agents.
Persistent Intelligence Infrastructure for AI Agents
MCP for semantic code search & navigation that reduces token waste
@swapnanilSemantic codebase search + persistent working memory for AI code editors. Local, zero-config, MCP. No API key.
Pre-indexed code knowledge graph for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent —
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and
Persistent code-knowledge memory for AI chats. An MCP server that caches a codebase's structure and summaries in a local
Vector MCP Server for AI Agents - Supports ChromaDB, Couchbase, MongoDB, Qdrant, and PGVector
Metatron is a self-hosted system that captures a codebase's real implementation decisions — preferred patterns, rejected
Structural graph memory for AI coding assistants — MCP server for codebase navigation
Spends CPU cycles so you don't spend tokens. The LLM gets a briefing packet instead of a flashlight in a dark room.
Local first codebase intelligence
A structural code search engine for Al agents.
Graph-native code intelligence that replaces embedding-based RAG with deterministic program understanding.
Tentra MCP — memory for AI coding agents. Persistent code graph + AI architecture diagrams. 32 MCP tools. Works in Curso
Extract domain knowledge from codebases to reduce LLM token consumption by 20x and time in agentic search by 10x — gathe
BGI tries to group code based on what the code actually does (its behavior), not just which file imports what.
Codebase Context gives AI agents understanding of your codebase through semantic code search, team conventions, patterns
Symbol Delta Ledger (SDL-MCP) is a policy-centered context budget layer for coding agents: Symbol-graph intelligence com
LeanKG: Stop Burning Tokens. Start Coding Lean.
Structural memory for coding agents — index your repo once, query symbols, callers, and call-edges over MCP.
IGraph 把代码仓库解析为「符号节点 + 调用关系边」的知识图谱，叠加 LLM 语义摘要与向量索引，通过双通道（Dense + FTS5）RRF 融合检索对外服务。支持挂载 PRD / DB Schema 等多模态资源建立跨模态关联，内
Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust bi
Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero clou
Homebrew MCP : Comprehensive brew support for installing, upgrading, searching, and maintaining macOS packages.
A map of what AI tokens actually cost, and where they're wasted vs. well spent. Tools, research, practices, and copy-pas
Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read
The ultimate Claude Code optimization toolkit. 15 AI agents, 12 MCP servers, 17 hooks, autonomous token pipeline (60-99%
Local cognitive infrastructure for AI coding agents — semantic memory, repository intelligence, and MCP tools to reduce
MCP server for Claude Code and Codex. One tool call replaces ~42 minutes of agent exploration