MCP server that gives AI coding assistants persistent memory, semantic code search, and live telemetry.
AiDex is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view CSCSoftware/AiDex --webOpen the official README and confirm the supported install method.
Add the server entry to your MCP client config.
Restart your agent and verify that the server tools appear.
AiDex is a tool that helps AI coding assistants remember your project details across sessions. It indexes your code so the AI can search by meaning, not just keywords, and it can watch your app's logs in real time. This makes the AI much faster and more accurate, using up to 50 times fewer tokens than traditional grep searches.
AiDex is an MCP (Model Context Protocol) server designed to be the persistent brain for AI coding agents. It works with any MCP-compatible assistant including Claude Code, Claude Desktop, Cursor, Windsurf, Gemini CLI, and VS Code Copilot. The tool is built on three pillars: Memory (tasks, notes, and session history survive across chats), Search (three modes: exact, semantic, and hybrid fusion, with optional LLM layer for non-English queries and reranking), and Telemetry (LogHub receives live logs from any app via HTTP, allowing the AI to observe real application behavior). It indexes code using tree-sitter and stores data in SQLite, supporting 12 languages. With 33 tools, AiDex provides semantic search, identifier search, method signatures, project overview, cross-project global search, persistent guidelines, session tracking, task management with scheduling, a universal log receiver, cross-platform screenshots, and an interactive viewer. It is local-first, model-agnostic, and claims to be 50x more token-efficient than grep.
Looks usable, but maintenance, license, or security notes deserve a closer look.
Last commit was about 4 days ago.
34 GitHub stars indicate community interest.
6 open issues signal maintenance load.
MIT license detected.
Quickly locate a specific function or class across a large codebase without reading entire files.
Give an AI assistant persistent memory of project tasks, notes, and conventions across chat sessions.
Monitor live application logs and let the AI analyze real-time behavior for debugging.
Search across all your projects at once to find if a certain identifier has been used before.
Automate recurring tasks and scheduled reminders directly from the AI assistant.
The tool indexes your entire codebase locally; ensure sensitive files are excluded via configuration.
LogHub receives logs via HTTP; if exposed to network, logs could be intercepted. Use only in trusted environments.
Screenshot tool captures screen content; be mindful of privacy when used on shared machines.
34
Stars
9
Forks
6
Issues
MIT
License
A project template that turns your repository into stable infrastructure for AI-assisted development.
Local code intelligence MCP server and CLI for AI coding agents, providing semantic search and call graph analysis.
Up-to-date code documentation for LLMs and AI code editors, eliminating outdated or hallucinated API references.
3 security/trust notes recorded.
Setup difficulty is 3/5.