omdivyatej/Self-Learning-Agents

A lightweight Python library that allows any LLM agent to self-improve through feedback, without retraining models.

36
/ 100
Emerging

This is a lightweight Python library designed for developers who are building applications powered by large language models (LLMs). It allows you to build agents that can improve their responses over time by learning from user feedback. You provide an LLM agent's output and explicit feedback on it, and the library then uses this feedback to enhance future prompts for similar tasks, making the agent's performance better without needing to retrain the underlying LLM.

No commits in the last 6 months.

Use this if you are developing LLM-powered applications and want your agents to learn and adapt from user feedback to improve their performance for future, similar requests.

Not ideal if you are an end-user looking for a pre-built application or a low-code solution; this is a developer tool requiring Python coding.

LLM-development AI-agent-improvement prompt-engineering developer-tool feedback-loops
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 8 / 25
Maturity 15 / 25
Community 11 / 25

How are scores calculated?

Stars

62

Forks

6

Language

Python

License

MIT

Last pushed

Jun 27, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/omdivyatej/Self-Learning-Agents"

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