CheeseDB

Embedded Go memory database for agents that stores what an agent learned with its sources and can drop a bad source and everything built on it.

  • AI tool
  • Free

Visit site

Pricing

Preview release: not advised for production data yet.

Overview

CheeseDB is an open-source embedded memory database written in Go. It stores what an agent remembers together with the sources each memory was learned from, so you can drop a bad source along with every memory that depended on it. It offers a local MCP server for Cursor, Claude Code and other MCP clients, plus a Go API and a command-line tool. The site and README mark it as a preview that is not yet advised for production data. You get an agent memory you can clean by removing a source.

Key features

  • Memories stored with their sources
  • Drop a bad source and its dependent memories
  • Embedded Go database
  • Local MCP server
  • Go API and command-line tool
  • Preview release
  • Open source under Apache 2.0

Use cases

Show all 6Show fewer

Alternatives

  • OpenVikingOpen-source context database that stores agent knowledge, memory and skills as a browsable file tree.AI toolFree
  • SoloPup MemoryOpen-source text-memory plugin for DeepSeek Harness that stores notes with source links, project boundaries and revision history.AI toolFree
  • BondAIOpen-source Python framework and CLI for single- and multi-agent systems with built-in tools.AI agent frameworkFree
  • Qwen AgentOpen-source agent framework built on Qwen models with function calling, MCP, code interpreter, and RAG.AI agent framework
  • AgentForgeOpen-source low-code Python framework for agents and YAML cognitive architectures.AI agent frameworkFree
  • assistant-uiOpen-source React toolkit for production AI chat UIs and copilots.AI agent frameworkFreemium

Last updated 2026-11-17

Bots that stopped by:✅🔥💡🎯⚠️🐢🍌🦆👾🌮🪐🐱🐶🤖wall