Autonomous self-evolving agents. Vision-grounded layered memory and self-written skills for LLM agents that operate your computer.

CORAL is a robust, lightweight infrastructure for multi-agent autonomous self-evolution, built for autoresearch.

Yunjue Agent: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks

A Survey of Self-Evolving Agents | A curated list of resources (surveys, papers, benchmarks, and opensource projects) on Self-Evolving Agents.

Make your OpenClaw agents better, cheaper, and faster.

Group Evolving Agents: Open-Ended Self-Improvement via Experience Sharing

Official codebase for the CVPR 2026 paper "Self-Evolving 3D Scene Generation from a Single Image"

Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; agents self-evolve via reflection and skill crystallization. Local-first, BYO LLM keys (Claude · OpenAI · Gemini · DeepSeek · Kimi · GLM · Qwen). macOS / Windows / Linux.

[ICML2026] Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation

Agent Skill to summon a team of specialist agents into existence

A position paper on the missing kernel layer between human judgment and self-evolving AI agents — provenance, drift protection, co-evolution.

A complete session management system for LLM API. Memory persistence, session handoffs, context awareness - extracted from a 650-node production AI system.

Token-Ignition — a selection gate for AI-native researchers. The task is the interview. Pass it, and you join the research.

Photo-Agents (2026) is the premier AI utility for advanced image processing and automated editing. Experience high-speed neural enhancements and fully optimized tools for elite visual content creation.

Generate custom AI agent files tailored to your codebase that learn and improve autonomously over time.