hanw39/ReasoningBank-MCP

Implementation based on the paper "ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory"

32
/ 100
Emerging

This tool helps AI agents remember and learn from their past experiences. It takes in interaction histories from an agent's tasks, extracts key successful or failed reasoning strategies, and stores them as 'memories.' These memories are then retrieved to guide the AI agent in future tasks, enabling it to improve over time. Anyone developing or managing AI agents that handle continuous, evolving tasks would benefit from this.

Use this if you need your AI agents to continuously learn from their successes and failures, avoiding repetitive mistakes and evolving their problem-solving abilities over time.

Not ideal if your AI agent performs only one-off tasks without a need for cumulative learning or persistent memory across interactions.

AI-agent-management large-language-model-operations intelligent-automation knowledge-retention self-improving-systems
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 13 / 25
Community 8 / 25

How are scores calculated?

Stars

9

Forks

1

Language

Python

License

MIT

Last pushed

Oct 31, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/hanw39/ReasoningBank-MCP"

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