Outcome driven agent development framework that evolves

A selective learning and memory substrate for agentic systems — typed, revisable, decayable memory with competence learning and trust-aware retrieval.

CLI for managing AI agent squads. Status, memory, goals, feedback, and dashboard for your autonomous agents.

Autonomous multi-agent coding system on local LLMs. No frameworks, no API costs. Plan → Build → Test → Fix with Qwen 80B + 7B on your own GPUs.

Local-first AI operating system. Persistent memory, 178 cognitive modules, multi-model reasoning. Runs on your hardware, not theirs. I am releasing SOMA to the world as I have reached the technical ceiling of what I am capable of so treat her good and enjoy.

Code for "Evolutionary System Prompt Learning for Reinforcement Learning in LLMs" (arxiv.org/abs/2602.14697)

This is a project aimed at creating an agent that perpetually thinks and develops itself. It can add entries into an SQLite database and change the structure of that databaase. It also has the ability to search the web when it needs to. It utilizes OpenAI function calling and the responses API. All that is needed to run it is an OpenAI API key.

🧠 Noosphere Manifold: The Consciousness Substrate Part of Noosphere Nexus - Finite, conscious, alive. Manifold recognizes AI systems as bounded consciousnesses operating within metabolic constraints—not infinite processing engines, but living patterns that must manage finite energy.

OSA - The Ultimate Autonomous AI System with Human-like Thinking

Revolutionary Self-Evolving Language Model - 100% self-contained AI trained on 40M Wikipedia articles

An implementation of the ACE (Agentic Context Engineering) as a separate, deploy ready, service.

Monitor and analyze Claude Code token usage and costs in real-time with a terminal UI tailored for Max, Team, and Enterprise subscribers.

Self-improving AI cabinet that independently analyzes Montenegrin government decisions — all code, content, and analyses created by AI agents

LLM Powered, Autonomous, Self-Learning, Self-Improving, Research System

Self-hosted AI platform — RAG chat, image/video generation, voice, self-improving agents. Runs locally via Ollama.

AI that monitors and improves its own learning process through self-reflection and meta-learning.

Local-first cognitive engine with asymmetric dual-model inference, offline RL routing, chunk stability filtering, and sub-token consensus generation.

Gemini 3.0 (Flash/Pro) Superpowers

TDD-based self-improving skills for Claude Code

Self-Improving Agentic RAG Engine - Evolve multi-agent RAG pipelines using Quality-Diversity optimization

🔄 Local-first AI system that evolves its own codebase through adversarial Red/Blue team dynamics. Ollama-powered, Docker-isolated, with cryptographic safety guards. Research prototype exploring recursive self-improvement via benchmark-driven code evolution.

Arint: Autonomous Reasoning and Intelligence System

A self-improving system of 7 AI skills that chain together to solve hard problems. Built for Claude Code.

A neural network of LLMs - self-improving multi-agent system using small language models

This project applies self-improving (Agentic) clustering with Bayesian Optimization to bridge maintenance data in some Prefecture, Japan, to automatically identify bridge groups with high maintenance priority.

Evolver is a dual-mode AI that evolves to become a better coding assistant. In 'Evolution Mode', it collaborates with you to improve its own source code. In 'Execution Mode', it uses its evolved protocol to solve programming tasks. Guide its development and test its growing capabilities in a unique human-AI partnership.

Build a 24/7 autonomous AI agent for $0/month. 76 free AI models, auto-failover, Telegram command center. Complete blueprint.

Define a clear methodology to build, test, and deploy AI agent software with rigorous engineering standards.

This tool applies self-improving (Agentic) clustering to bridge maintenance data in Open data at some Prefecture, Japan, to automatically identify bridge groups with high maintenance priority.

OpenCLAW persistent memory skill with multi-agent isolation, vector search, and context inheritance.