self-learning-ai

The Browser Infra that learns and cuts token spend by upto 90%

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.

self-replicating ai agent built for you

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

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.

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.

A lightweight AI Agent harness to handle any kind of task! From software engineering to design, marketing, sales, finance, paid media, project management or whatever you need to be done.

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.

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.

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

Self-learning macOS automation agent: control your Mac with natural language, persistent memory, reusable skills, Discord remote control, and a Swift sidecar.

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.

Novel physics-informed deep learning architecture for cardiovascular state estimation from short-channel fNIRS using physiological features, normalizing flows, WaveNet and innovation feedback.

Discover, evaluate, and manage AI skills from community sources. A security-aware framework for continuous skill acquisition.

Reasona is an AI system that improves itself. It answers questions using your documents and corrects wrong answers automatically for better future results.