agentralabs/agentic-memory

Persistent cognitive graph memory for AI agents — facts, decisions, reasoning chains, corrections. 16 query types, sub-millisecond. Rust core + Python SDK + MCP server.

33
/ 100
Emerging

This project helps AI agent developers overcome the challenge of agents forgetting past conversations and decisions. It provides a persistent, structured memory that stores facts, decisions, reasoning chains, and corrections in a single file. Developers can use this to build more capable AI agents that retain context and learn over time, enabling them to make more informed decisions across many sessions.

Use this if you are developing AI agents and need them to reliably remember past interactions, decisions, and reasoning paths over extended periods, across different models or sessions.

Not ideal if you only need simple, short-term conversational recall or if your agent's memory requirements do not necessitate complex causal tracing or persistent knowledge graphs.

AI agent development conversational AI knowledge management AI memory reasoning systems
No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 11 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Rust

License

MIT

Last pushed

Mar 08, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/agentralabs/agentic-memory"

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