RBKunnela/ALMA-memory

Persistent memory for AI agents - Learn, remember, improve. Alternative to Mem0 with scoped learning, anti-patterns, multi-agent sharing, and MCP integration.

42
/ 100
Emerging

Implements a **vector-backed memory system with 7 storage backends** (SQLite, PostgreSQL, Qdrant, Pinecone, Chroma, Azure Cosmos DB, file-based) and multi-factor scoring that combines semantic similarity with recency, success rate, and confidence metrics. Provides **22 native MCP tools for Claude integration**, hierarchical multi-agent knowledge sharing via `inherit_from`/`share_with` relationships, and explicit anti-pattern tracking with structured failure reasoning. Includes memory lifecycle management (decay, compression, consolidation, archival) and workflow checkpointing for stateful agent sequences across session boundaries.

Used by 1 other package. Available on PyPI.

No License
Maintenance 10 / 25
Adoption 7 / 25
Maturity 10 / 25
Community 15 / 25

How are scores calculated?

Stars

20

Forks

4

Language

Python

License

Last pushed

Mar 03, 2026

Commits (30d)

0

Dependencies

2

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/vector-db/RBKunnela/ALMA-memory"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.