DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.
1,180+ deals tracked · 22 AI investment memos · Updated daily
Show HN: Memv – Memory for AI Agents
memv is an open-source Python library that gives AI agents persistent memory. Feed it conversations; it extracts knowledge.<p>The extraction mechanism is predict-calibrate (Nemori paper): given existing knowledge, it predicts what a new conversation should contain, then extracts only what the prediction missed.<p>v0.1.2 adds the production path: - PostgreSQL backend (pgvector for vectors, tsvector for text search, asyncpg pooling). Single db_url parameter — file path for SQLite, connection string for Postgres. - Embedding adapters: OpenAI, Voyage, Cohere, fastembed (local ONNX).<p>Other things it does: - Bi-temporal validity: event time (when was the fact true) + transaction time (when did we learn it), following Graphiti's model. - Hybrid retrieval: vector similarity + BM25 merged with Reciprocal Rank Fusion. - Episode segmentation: groups messages before extraction. - Contradiction handling: new facts invalidate old ones, with full audit trail.<p>Procedural memory (agents learning from past runs) is next, deferred until there's usage data.
Memv addresses a critical bottleneck in the AI agent ecosystem with a sophisticated technical approach, specifically implementing bi-temporal validity and research-backed extraction methods. While the product shows high technical competence, the lack of current traction and team data makes it a high-risk, early-stage prospect in a crowded market.