Show HN: Memv – Memory for AI Agents

[brgsk]

memv is an open-source Python library that gives AI agents persistent memory. Feed it conversations; it extracts knowledge.

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.

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).

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.

Procedural memory (agents learning from past runs) is next, deferred until there's usage data.

[brgsk]

Install with

  ```
  uv add "memvee[postgres]"
  ```

- Links:

  - GitHub: https://github.com/vstorm-co/memv

  - Docs: https://vstorm-co.github.io/memv

  - PyPI: https://pypi.org/project/memvee/

- Quickstart:

  ```python
  from memv import Memory
  from memv.embeddings import OpenAIEmbedAdapter
  from memv.llm import PydanticAIAdapter

  memory = Memory(
      db_url="postgresql://user:pass@host/db",
      embedding_client=OpenAIEmbedAdapter(),
      llm_client=PydanticAIAdapter("openai:gpt-4o-mini"),
  )
  ```

[rakeshd]

I'm curious about how it handles context window limitations and retrieval for very long histories.

[JaredCampbell]

I wish I was less dumb, to take advantage of this