MCP server that indexes your codebase into a persistent knowledge graph. 35 languages, sub-ms queries, 99% fewer tokens than grep. Single Go binary, no Docker, no API keys.
# Add to your Claude Code skills
git clone https://github.com/DeusData/codebase-memory-mcp
README.md
codebase-memory-mcp
Stop paying 100x more tokens for code exploration. This MCP server indexes your codebase into a persistent knowledge graph that survives session restarts and context compaction. One graph query returns what would take dozens of grep/Glob calls — precise structural results in ~500 tokens vs ~80K tokens for file-by-file exploration.
Single Go binary. No Docker, no external databases, no API keys. One command to install, say "Index this project" — done.
Parses source code with tree-sitter, extracts functions, classes, modules, call relationships, and cross-service HTTP links. Exposes the graph through 12 MCP tools for use with Claude Code, Codex CLI, Cursor, Windsurf, or any MCP-compatible client. Also includes a CLI mode for direct tool invocation from the shell — no MCP client needed.
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
177,612
developer-tools
golang
knowledge-graph
mcp
mcp-server
model-context-protocol
sqlite
tree-sitter
windsurf
detect_changes
Risk-classified tracing: trace_call_path with risk_labels=true adds impact classification to every node in the call chain
Case-insensitive search: search_graph and search_code are case-insensitive by default — set case_sensitive=true for exact matching
One-command install: codebase-memory-mcp install auto-detects Claude Code, Codex CLI, Cursor, and Windsurf, registers the MCP server, and installs task-specific skills
Self-update: codebase-memory-mcp update downloads the latest release, verifies checksums, and atomically swaps the binary
Task-specific skills: 4 skills (exploring, tracing, quality, reference) that prescribe exact tool sequences — Claude Code automatically uses graph tools instead of defaulting to grep
Fast: Sub-millisecond graph queries, incremental reindex 4x faster than full scan, optimized SQLite with LIKE pre-filtering for regex searches
Call graph: Resolves function calls across files and packages (import-aware, type-inferred)
Cross-service HTTP linking: Discovers REST routes (FastAPI, Gin, Express) and matches them to HTTP call sites with confidence scoring
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Cowork, and beyond.
⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 Say goodbye to information overload with your AI public opinion monitoring assistant and hot spot screening tool! Aggregates multi-platform hotspots + RSS subscriptions to support precise keyword filtering. AI translation + AI analysis briefings are pushed directly to mobile phones, and also support access to the MCP architecture, empowering AI natural language dialogue analysis, emotional insights and trend predictions, etc. Supports Docker, data is self-sustained locally/in the cloud. Integrate intelligent push via channels such as WeChat/Feishu/DingTalk/Telegram/Mail/ntfy/bark/slack.
CowAgent is a super AI assistant based on large models that can proactively think and plan tasks, access the operating system and external resources, create and execute Skills, have long-term memory and continue to grow. It also supports access to Feishu, DingTalk, enterprise WeChat applications, WeChat public accounts, web pages, etc. You can choose OpenAI/Claude/Gemini/DeepSeek/Qwen/GLM/Kimi/LinkAI. It can process text, voice, pictures and files, and can quickly build personal AI assistants and enterprise digital employees.