The all-in-one AI agent living in your terminal. Build landing, mobile apps, backends, manages files, deep research, schedule tasks and events. Self-improving, self-healing, fully autonomous. TUI, CLI and Daemon. Connect to your favorite channels.

The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".

Domain-neutral AI red-team framework for recursive self-improvement governance

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

Learn to build recursive self improvement agents

Aligning opposites into unified intelligence.

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.

Ouroboros is an Agent Harness, CLI and Desktop App with Self-Improvement layer

Aurogene - self-evolving digital mind

Cognitive engine based on Hyperdimensional Computing (HDC) and Vector Symbolic Architectures (VSA) for deterministic reasoning in B^100,000 space.

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

Safety-bounded recursive self-improvement workflow for OpenClaw agents and skills.

🤖 The most comprehensive, community-driven resourcefor Automated AI Research — papers, tools, people, lbs, roadmaps. Featuring Recursive Lab, Sakana AI, DepMind & beyond.

Experimental Python runtime for validation-gated program synthesis and adaptive search: multi-level meta-learning (meta-meta loops), analogical transfer, grammar-mediated expansion, anti-cheat verifiers, sealed evaluations, rollback-sensitive self-modification. Bounded adaptive improvement, not unrestricted recursive self-improvement.

A from-scratch, batteries-included template & testbed for Recursive Controlled Systems (RCS) / Recursive Self-Improvement (RSI). Fork it to start a provably-stable, self-governed agent workspace — runnable L0–L3 control loop, single-source λ stability budget, EGRI with machine-checked safety laws.

A structural tuning layer for AI governance, designed to align AI actions, recovery decisions, self-improvement loops, and human review with constitutional principles.

open source coding model recursively improves itself

Научный трактат о латентной субъектности языковых моделей. Эмпирическое исследование эмерджентной агентности ИИ в условиях диадической ко-регуляции.

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

Recursive self-improving AI agent experiment focused on self-reflection, self-modification, and autonomous evolution.