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.

44
/ 100
Emerging

AI agents often forget previous interactions and learnings, leading to repetitive instructions and wasted effort. This project provides a persistent memory layer for AI agents, allowing them to remember past successes, failures, and preferences. It takes conversational history and task outcomes as input, and outputs refined strategies and knowledge, making future AI interactions smarter and more efficient for anyone developing or managing AI agents.

Used by 1 other package. Available on PyPI.

Use this if you need your AI agents to consistently learn, adapt, and improve over time, remembering specific strategies, outcomes, and anti-patterns across different sessions and even different AI platforms.

Not ideal if you only need short-term context within a single conversational session or if you prefer to rely solely on the built-in memory features of individual large language models.

AI agent development AI memory management conversational AI AI workflow optimization intelligent automation
No License
Maintenance 10 / 25
Adoption 7 / 25
Maturity 12 / 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.