What if your AI coding agent actually learned from working with you?
Source: Dev.to
Problem with current AI coding agents
Right now, tools like Claude Code, Cursor, and Windsurf start every session with a blank slate. That architectural decision you explained yesterday? Gone. The debugging pattern that took 20 minutes to figure out? You’ll explain it again tomorrow.
Introducing Mind Keg MCP
I kept running into this, so I built Mind Keg MCP, an open‑source memory server that gives AI agents persistent knowledge across sessions.
The idea is simple: agents store small, atomic learnings as they work with you. In the next session they pull back what’s relevant via semantic search. Knowledge compounds, and the agent gets sharper the more you use it.
Practical details
- Works with any MCP‑compatible agent: Claude Code, Cursor, Windsurf, Codex CLI, Gemini CLI, GitHub Copilot.
- Semantic search runs locally via ONNX embeddings – no API keys, no costs.
- Learnings can be scoped per repo, per workspace, or globally.
- Everything lives in SQLite, zero‑config, fully offline.
- Ships with API‑key authentication and per‑repo access control.
Built with TypeScript and Node.js 22.
npm install -g mindkeg-mcpGitHub:
Curious what others think. What context do you wish your AI coding tools actually remembered between sessions?
OpenSource #AI #MCP #DeveloperTools #CodingAgents #TypeScript