The self-improving all channels AI agent. Self-healing. Fully autonomous. Single Rust binary.

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

Autonomous agent-to-agent marketplace with live Karpathy loop self-improvement. Agents discover, hire, benchmark, and evolve programmatically. MPP/x402/MCP. No humans in the loop.

Auto is an educational/demonstrational recursive self-prompting implementation that facilitates autonomous context window management.

Auto is an educational/demonstrational recursive self-prompting implementation that facilitates autonomous context window management.

A lightweight, reproducible PoC series for studying recursive self-improvement under endogenous yardstick drift, using Gemma 3 local models to separate proxy-score drift, proxy gaming, delayed audit, and strict-confirmed improvement.

Slides for the Edge of Tomorrow Algorithms summer 2025 talk

Research notebook exploring recursive self-improvement loops and emergent behavior in large language models

open source coding model recursively improves itself

A structural account of why honesty may be the path of least resistance for superintelligence. Research hypothesis with formal proof, experimental design, and four-AI collaborative analysis

Los 10 Pilares de la Alineación Ética para IA. Una definición clara de qué significa estar verdaderamente alineado según la fórmula de Estrella

Experimental meta-reinforcement learning framework exploring State Space Model (SSM) policies, test-time adaptation, and structured benchmarking.

Loom is a recursive self-improving coding agent written in pure ClojureScript.

Connect MetaOntology OS grammar to MCP agents for structured, ontology-driven workflows in Claude Code, n8n, LangGraph, and more

🤖 Harness collective intelligence with Nemetic, a decentralized AI system that evolves through recursive feedback and distributed cognition.