coldstart
Self-maintaining and persistent codebase memory for AI coding agents — a deterministic AST index plus agent-written notes that flag themselves stale when the code changes. Works with Claude Code, Cursor, and Codex via MCP + CLI.
No README could be loaded. View the project on GitHub for full documentation.
Frequently asked questions
What is coldstart?
coldstart is Self-maintaining and persistent codebase memory for AI coding agents — a deterministic AST index plus agent-written notes that flag themselves stale when the code changes. Works with Claude Code, Cursor, and Codex via MCP + CLI.
How do I install coldstart?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is coldstart open source?
Yes — it is hosted on GitHub at https://github.com/AkashGoenka/coldstart and has 9 stars.
Related MCP tools
Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro, OpenCode, and Trae.
Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI
Open-source coding agent memory. Records issues, attempts, fixes and decisions, then warns your agent before it repeats an approach that already failed. Native MCP server for Claude Code, Cursor, Antigravity and Codex. 100% local, no cloud, no telemetry. MIT.
Code search MCP for Claude Code. Make entire codebase the context for any coding agent. TypeScript-based implementation. Trusted by 4100+ developers.
A super light-weight embedded code search engine CLI (AST based) that just works - improves speed and efficiency for coding agent 🌟 Star if you like it!
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP