self-learning-ai

Self-learning agent browser

A set of pi-extensions, including pi-continuous-learning that continually improves you pi coding agent experience

Self improving agents through iterations

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

How to effectively finetune CV/LLM models (without local gpu)

Use Gemini CLI with OpenCode through a local planner, reviewer, and session loop with self learning architrecture.

CodeGraph MCP - Give persistent learning to your coding agent for a codebase across teams & token saving superpower to the coding agent

self-replicating ai agent built for you

AI agent pipeline orchestration for Claude Code. Deploy specialized agents in coordinated pipelines with self-learning capabilities, mesh coordination, Raft consensus, CRDT knowledge graphs, and pipeline debugging. 15 production-grade skills with reasoning protocols, 20+ agent types, 15 ready-to-run templates. Zero infrastructure.

Agents Workspace provides portable skills and a boot policy that guide your assistant to coordinate domain specialists, delegate scoped work, and review the result before handing it back to you.

The Self-Learning AI Framework is an autonomous system that analyzes, modifies, and optimizes its own code. It supports natural language interaction, framework creation, code suggestions, PDF-based learning, and package management. Ideal for automating code reviews, agent creation, and AI-driven development.

Self-Reinforced Testing Framework (SRTF) for AI Agents.

Build Windows apps in 13 seconds from your PHONE. Self-learning local AI agent. Runs on a 4 GB GPU or just CPU + RAM. No API keys, no cloud.

Automate your browsing tasks with an AI agent that reads pages, clicks, types, and researches across the web with cited answers.

This project implements an AI that teaches itself to play the game of Nim using Q-learning, a form of reinforcement learning. By playing games against itself, the AI learns optimal strategies for playing Nim, eventually improving its performance by updating a reward table based on game outcomes.

🤖 Tomie: A self-learning personal AI agent that uses tools, remembers experiences, and improves from feedback.

Public Praxa AI product, SDK, CLI, MCP, API, and operations documentation.

Library for building self-learning agents. Agents make decisions, keep a replayable journal, and an optimizer searches for better strategies across multiple metrics.

Blackwall is an autonomous Agentic Firewall designed to secure AI agents by actively intercepting execution flows before they reach external systems or the host OS. It leverages self-learning threat signatures, structural graph analysis, and real-time semantic gating to dynamically detect and mitigate rogue agent behaviors and malicious payloads.

A powerful Model Context Protocol (MCP) server for Android control via ADB with self-learning, UI memory, vision-enhanced, and macro support.