codebase-context

Rails MCP server: stop AI coding agents from guessing your app. A Ruby gem with 35 read-only tools that give Claude Code, Cursor, GitHub Copilot, OpenCode and Codex CLI your real schema, models, routes, controllers and views. MCP or CLI, Gemfile or standalone, and it still answers when the app can't boot.

One command gives AI agents instant codebase context. ~250 tokens replaces 50,000+ tokens of exploration. Auto-configures Claude Code, Cursor, Aider.

MCP server for AI coding agents. Instead of reading files one by one, your agent gets dependency graphs, git intent, blast radius, and change health in a single call. Works with any language deep analysis for TypeScript,Java, Go, and C#.

Retrieval + inference offload for AI coding agents.

Portable Agent Skill for codebase understanding and developer onboarding, producing source-cited Markdown artifacts with architecture, flows, error paths, and unknowns.

Local-first repo maps for coding agents—ranked files, test routes, risks, CLI/MCP/GitHub Action, and public GitHub URLs.

Persistent codebase knowledge layer for AI agents. Pre-builds architecture, dependency, coupling, and risk knowledge served via MCP. 27 languages, 13 tools.

AI codebase context tool that analyzes, ranks, and compresses repositories into optimized context files for LLMs, AI coding assistants, and MCP workflows.

Project memory and a code map for AI agents: where to look, why the code is the way it is, and what a change will touch. Committed .context/ files, served over MCP. Local-first, no embeddings.

Local, explainable context compiler for AI coding agents. Analyze → plan → emit optimal context — with why/doctor diagnostics. No embeddings, no server.

Generate AI context files from your codebase's actual conventions. Not what agents already know — what they keep missing.

An MCP server that reverse-engineers repository culture and workflows into actionable agent skills.

Turn a local codebase into clean, token-counted context for an LLM. One Rust binary with gitignore-aware selection, clipboard/pipe workflows, and a built-in UI.

Remote-first, project-aware AI prompt optimizer: select real codebase files, add Web Search or Deep Research, and run inference on an always-on home workstation. Originally developed in Cowork mode.

Deterministic repository context for AI coding agents.

Codex-native codebase intelligence: deterministic repo context, change-plan drift review, and verification gating for AI coding agents. Local-first, zero API keys.

A Claude Code plugin that understands your codebase and generates only the docs that actually matter. Run `/project-mds`, it scans everything and creates clean, connected markdown for APIs, models, auth, infra, and more so your agents don’t have to dig through code again and again.

Generate AI-friendly repository maps using ast-grep for providing codebase context to AI assistants and LLMs

Repository knowledge graph for Cursor and Claude Code. Trace callers, callees, symbol definitions, and dependencies to understand unfamiliar code and make better-informed changes.

One codebase, one context layer — every AI understands it. Analyze a repo once, then retrieve task-specific context for any coding agent.