by Neuroscience-inspired memory system for AI agents. Unlike passive vector stores, MemForge treats memory quality as something that should actively improve over time. It runs a 10-phase 'sleep cycle' during idle periods: scoring, triage, conflict resolution, LLM-driven revision of low-confidence entries, graph maintenance, reflection, schema crystallization, meta-reflection, and gap analysis.
Scores 93.2% Recall@5 on LongMemEval (ICLR 2025) with p50 32ms / p95 47ms hybrid-search latency. Ships as a Docker standalone image, Python SDK, TypeScript SDK, and a 17-tool MCP server with integrations for Claude Desktop, Microsoft 365 Copilot, ChatGPT, LangChain, and CrewAI. Cleared 9 rounds of adversarial security review at MEDIUM+, with a published threat model, RLS, prompt-injection boundaries, SSRF prevention, and HMAC-chained audit logs.
Built on PostgreSQL + pgvector (halfvec float16) with local embeddings via Transformers.js and Ollama support for fully self-hosted deployments.
Scores 93.2% Recall@5 on LongMemEval (ICLR 2025) with p50 32ms / p95 47ms hybrid-search latency. Ships as a Docker standalone image, Python SDK, TypeScript SDK, and a 17-tool MCP server with integrations for Claude Desktop, Microsoft 365 Copilot, ChatGPT, LangChain, and CrewAI. Cleared 9 rounds of adversarial security review at MEDIUM+, with a published threat model, RLS, prompt-injection boundaries, SSRF prevention, and HMAC-chained audit logs.
Built on PostgreSQL + pgvector (halfvec float16) with local embeddings via Transformers.js and Ollama support for fully self-hosted deployments.
github.com/salishforge/memforge
github.com/salishforge/memforgeThu, 23 Apr 2026 06:12:14 UTC
There was a problem with this listing's funding.json manifest. If it is not fixed, the listing will be removed from the portal.
Crawl errormajor version should be v1 (current version is v1.0.0)