SkillOpt is a text-space optimizer that trains reusable natural-language skills for frozen LLM agents through trajectory-driven edits, validation-gated updates, and deployable best_skill.md artifacts.
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. Works with Claude Code, Codex, Cursor, OpenCode, Kiro, and more.
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.
AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation
Make your OpenClaw agents better, cheaper, and faster.
Group Evolving Agents: Open-Ended Self-Improvement via Experience Sharing
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.
Official codebase for the CVPR 2026 paper "Self-Evolving 3D Scene Generation from a Single Image"
[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
SSE-Bio: A Structured Self-Evolving Agent with Agentic Retrieval Policy for Multi-Hop Biomedical Reasoning.
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.
TypeScript cognitive runtime for self-evolving agents
Framework-agnostic ReasoningBank (Ouyang et al., ICLR 2026): agents that learn from successful AND failed trajectories, with MaTTS.
Token-Ignition — a selection gate for AI-native researchers. The task is the interview. Pass it, and you join the research.
A complete session management system for LLM API. Memory persistence, session handoffs, context awareness - extracted from a 650-node production AI system.
A position paper on the missing kernel layer between human judgment and self-evolving AI agents — provenance, drift protection, co-evolution.
Generate custom AI agent files tailored to your codebase that learn and improve autonomously over time.
Add a description, image, and links to the self-evolving-agents topic page so that developers can more easily learn about it.
To associate your repository with the self-evolving-agents topic, visit your repo's landing page and select "manage topics."