Structural codebase indexer with MCP server for AI-assisted development

Stacklit: AI Codebase Indexing 2026 – Zero-Setup Local Repo Mapping for Agents

Create a codebase snapshot an LLM can read: budgeted Markdown parts for Claude, ChatGPT and Cursor, a manifest of every included and skipped file, secret redaction, and validate, which fails when the snapshot drifts. Local CLI and MCP server.

A precise local codebase map for AI coding agents: find, trace, and predict with file-line evidence.

MCP server for AI-powered codebase indexing with semantic memory, smart bootstrap, and intelligent context compilation

Standalone MCP server for codebase-chat — codebase intelligence tools for Cursor, Claude, Windsurf and any MCP client. Works without DeepSeek Harness.

Standalone MCP server for dsh-codebase-chat — codebase intelligence tools for Cursor, Claude, Windsurf and any MCP client. Works without DeepSeek Harness.

Claude Code context engine — pack, compress, and optimize any codebase for AI. Save 60-90% tokens.

Verification for agent-written code: evidence-backed findings, honest coverage.

Codebase knowledge graph for your project in DDEV — MCP server for AI coding agents, plus a browsable graph UI.

17 MCP query tools for codebase navigation — functions, classes, imports, dependency graphs, change impact. Zero dependencies. 87% token reduction.

Auto-generate AI-ready context from your codebase. One command → CONTEXT.md ready to paste into Claude, Cursor, ChatGPT or any MCP agent. Full MCP server mode included.

Auto-generate AI-ready context from your codebase. One command → CONTEXT.md ready to paste into Claude, Cursor, ChatGPT or any MCP agent. Full MCP server mode included.

Codebase Guardian: MCP server that watches a Git repository, pushes events, and ships Skills

Unofficial Termux (Android/bionic) builds of codebase-memory-mcp, auto-built with GitHub Actions for arm64, arm, x86_64 and x86.

Ask questions about any GitHub repo in natural language. Local embedding + ChromaDB + LLM with cited code paths (Anthropic + OpenAI-compatible)

代码库考古 MCP server：8 个只读工具（pickaxe / blame / 决策日志 / 改动热点），让 coding agent 能查代码的历史与决策

Local-first RAG engine with hybrid search, BGE reranker, self-learning loop, and MCP server

AI context engine for Claude Code, Cursor, Windsurf — pack, compress, and optimize any codebase. Save 60-90% tokens. Web dashboard on port 7456.

Automate the extraction of your codebase context for Large Language Models. This tool scans your project directory, respects .gitignore rules, and formats the output for seamless integration with MCP-compatible clients. Save time and enhance your LLM's context with structured codebase information.

Local repository maps, code search and symbol references for coding agents. MCP server with model-free keyword search and optional embeddings.

AI Architect Codebase: cross-platform code intelligence MCP for Claude Code, Codex, Gemini, Cursor, VS Code, and Zed. Tree-sitter AST to LadybugDB graph, hybrid search, and impact analysis.

Local CLI and MCP server that packs a repository into budgeted Markdown parts, writes a manifest of every included and skipped file with the reason, masks secrets in place, and exits non-zero when the snapshot drifts. For Claude, ChatGPT, Cursor and CI.

Persistent code intelligence for MCP with native graph, vector, full-text, and cross-repository search.

Local code intelligence and project memory for Codex and Claude Code. Explore TypeScript, JavaScript and Prisma through call graphs, model usage and source context. Project-scoped MCP server with a shared CLI.

Codebase Context gives AI agents understanding of your codebase through semantic code search, team conventions, patterns, and memory, so they use fewer tokens, spend less time, and produce better, more familiar output.

A Retrieval-Augmented Generation (RAG) Model-Controller-Provider (MCP) server designed to assist AI agents and developers in understanding and navigating codebases.. It supports incremental indexing and multi-language parsing, enabling LLMs to understand and interact with code.

Code knowledge graph and MCP search server with tree-sitter parsing, vector + reranker retrieval, and bitemporal knowledge.

Local code intelligence engine — three-tier FAISS + SQLite index with 10 MCP tools for semantic code search, blast radius analysis, and architectural investigation

MCP server for semantic code search with AST-aware chunking, incremental indexing, and real-time monitoring. --- idk if it works or, moreover, is actually helpful. But it is cool.

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

MCP server that analyzes TypeScript codebases, detects code health issues, fetches system incidents, and generates actionable remediation plans. Supports dual transport (STDIO for local dev, SSE for cloud deployment). Built with ts-morph, Express, and Zod validation.

A set of tools to use while coding using the Claude code cli. "smartgrep" is a grep-like tool that uses a semantic index of the codebase to provide Claudes with information tailored for how they think. Claudes love it! A "codebase-curator" Claude to assist the "developer" Claude in his coding tasks, together they implement fully integrated code.

A multi-agent AI system that audits any codebase and generates a styled health report (PDF). Built with LangGraph, MCP, and Gemini — three specialized agents scan structure, review code, and write the report.

Trace SQL Server tables to C# callers, controller actions, and Razor pages locally. MCP server and CLI with confidence labels. MIT.

Your AI agent writes code — but does it know WHY your code exists? Decision provenance, quality contracts, and AI anti-pattern detection for coding agents.

A sub-harness (both an MCP server and an MCP client). Delegates documentation and source code analysis, as well as interactions with related context-providing MCP servers, to a local or inexpensive OpenAI-compatible LLM. Drastically reduces token usage and context size for coding agents on the top-tier LLM.

Local code intelligence for developers and AI agents. Connect code, docs and infrastructure in a persistent graph, with CBM Lens, MCP tools, agent integrations and change-aware test selection.

Your AI agent writes code — but does it know WHY your code exists? Decision provenance, quality contracts, and AI anti-pattern detection for coding agents. 19 languages. MCP compatible.

CIS is a Rust daemon that builds a versioned code graph over your repository and exposes it to AI agents through the Model Context Protocol. Agents can navigate symbols, search semantically, apply speculative edits with confirm/revert, and merge branches — with crash-safe persistence and background maintenance.

Index codebases for AI agents with one command. Build a local map of your repository without server requirements or setup.

GraphQL-style codebase intelligence CLI — index, query, and analyze any codebase

MCP server for codebase analysis

Start querying your codebase's intent

Stop making your AI re-read your codebase. Stacklit maps your repo once and keeps the map fresh. In a 450-session test, agents ran 82% fewer grep and glob searches. Free, MIT, one Go binary. Sets up Claude Code, Cursor, Codex and 22 more.

AI-powered codebase intelligence platform — MCP Server, AST analysis, Knowledge Graph, and semantic memory with SQLite + sqlite-vec. Analyze any codebase in minutes.

Learn any codebase through conversation.

Understand any codebase in seconds - MCP server for AI coding agents

AI-powered MCP server for codebase navigation and LLM prompt optimization

Persistent codebase knowledge layer for AI agents — architecture, dependencies, coupling, and risk served via MCP

Local-first MCP server for CodeAtlas — AST analysis, codebase intelligence, semantic memory, and A2A orchestration.

Self-learning AST context engine & knowledge graph optimized for Laravel codebases and AI coding agents

High-performance CLI tool to convert codebases to Markdown for LLM context - MCP Server

MCP server that gives coding agents a structural map of a codebase

Semantic codebase graph engine — MCP server for Claude Code

MCP server (stdio) exposing ask_codebase — read-only Q&A over GitHub repositories via opencode

Instant codebase comprehension for AI coding agents

Scythe (ctx) is a live, auto-updating codebase context engine. It maintains a local SQLite relational graph of your repository, synced dynamically on edit by AI models, guaranteeing structured, zero-drift context under 10k tokens — even for million-line codebases.

Zero-config grammar-free structural codebase indexer and MCP server. ~0.16s builds, sub-ms queries, 4.7MB binary.

Pi coding agent native codebase awareness toolkit — 7 structural analysis tools. Also supports MCP (Cursor, Claude Desktop, Windsurf, etc.)