ScottRBK/forgetful
Opensource Memory for Agents
Implements semantic memory retrieval using FastEmbed for local embeddings and cross-encoder reranking, storing notes as vectors queryable via natural language. Enforces atomic Zettelkasten-style memories with automatic knowledge graph linking based on semantic similarity, plus support for entities, skills, projects, and multi-agent task coordination. Runs as an MCP server over STDIO or HTTP with SQLite or PostgreSQL backends, integrating with Claude, Cursor, VS Code, and other MCP-compatible AI agents.
194 stars.
Stars
194
Forks
16
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/ScottRBK/forgetful"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
kayba-ai/agentic-context-engine
🧠 Make your agents learn from experience. Now available as a hosted solution at kayba.ai
MemMachine/MemMachine
Universal memory layer for AI Agents. It provides scalable, extensible, and interoperable memory...
knowns-dev/knowns
The memory layer for AI-native development — giving AI persistent understanding of your software...
Dicklesworthstone/cass_memory_system
Procedural memory for AI coding agents: transforms scattered session history into persistent,...
rexdivakar/HippocampAI
HippocampAI — Autonomous Memory Engine for LLM Agents