MachineWisdomAI/fava-trails
🫛👣 FAVA Trails — versioned, auditable memory for AI agents via MCP. Backed by Jujutsu VCS.
Stores agent thoughts as markdown files with YAML frontmatter in a Jujutsu-backed monorepo, exposing stateless MCP tools that hide VCS complexity from agents. Supersession tracking automatically hides outdated beliefs, while a Trust Gate uses LLM-based review (via OpenRouter or any-llm-sdk) to validate thoughts before promotion to shared visibility, preventing hallucinations from polluting the knowledge base.
Available on PyPI.
Stars
5
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 10, 2026
Monthly downloads
658
Commits (30d)
0
Dependencies
6
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/MachineWisdomAI/fava-trails"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related servers
doobidoo/mcp-memory-service
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude....
mnemox-ai/tradememory-protocol
MCP server for AI trading memory — outcome-weighted cognitive memory with 10 tools, 399 tests.
Dataojitori/nocturne_memory
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to...
mordechaipotash/brain-mcp
Your AI has amnesia. Persistent memory and cognitive context for AI. 25 MCP tools. 12ms recall.
nonatofabio/local_faiss_mcp
Local FAISS vector store as an MCP server – Agent Memory, drop-in local semantic search for...