gordonkjlee/facthouse
by Various
A local memory engine any AI tool can use.
MCP
gordonkjlee/facthouse
Added 8 Sept 2026
Overview
A local memory engine designed for AI tools, providing persistent storage and retrieval of context or facts. It runs locally, allowing AI applications to access shared memory without relying on external services.
Best for
Best for
Developers experimenting with local memory for AI tools who prioritize privacy and simplicity over mature ecosystem support.
Use cases
- Give AI assistants persistent memory across sessions
- Store and retrieve contextual facts for AI agents
- Build local-first AI tools with shared knowledge
Notes
A local memory engine designed for AI tools, providing persistent storage and retrieval of context or facts. It runs locally, allowing AI applications to access shared memory without relying on external services.
2 stars on GitHub. Last updated 2026-09-08. Licensed MIT.
Use cases
- Give AI assistants persistent memory across sessions
- Store and retrieve contextual facts for AI agents
- Build local-first AI tools with shared knowledge
Pros
- Runs locally, keeping data private and offline
- Simple integration for any AI tool or framework
- Lightweight TypeScript implementation
Cons
- Very low adoption (2 stars) suggests early-stage or unproven reliability
- Limited documentation and community support
- May lack advanced features like vector search or distributed sync
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Runs locally, keeping data private and offline
- Simple integration for any AI tool or framework
- Lightweight TypeScript implementation
Cons
- Very low adoption (2 stars) suggests early-stage or unproven reliability
- Limited documentation and community support
- May lack advanced features like vector search or distributed sync
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
