Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

Agent Skills as a Memory Layer

🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents

[Survey] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

AgentEvolver: Towards Efficient Self-Evolving Agent System

🐙 Give your AI a life — open-source agent infrastructure for team collaboration.

QuantaAlpha transforms how you discover quantitative alpha factors by combining LLM intelligence with evolutionary strategies. Just describe your research direction, and watch as factors are automatically mined, evolved, and validated through self-evolving trajectories.

Live-SWE-agent: live, runtime self-evolving software engineering agent

🔬🦞 A self-evolving AI research colleague for scientists. 285 skills, zero hallucination, persistent memory.

Fully Autonomous AI Research System with Self-Evolution, built natively on Claude Code

AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution

a self-evolving intelligent companion

Designing Multi-Agent Systems with Zero Supervision

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

The code implementation for TTCS: Test-Time Curriculum Synthesis for Self-Evolving.

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

💁📲 Self-evolving customer service framework, SEAD, operates without any human-labeled data. It can be quickly launched just by changing the SOP and user profiles.

A self-evolving Claude Code plugin. Context routing, memory bootup, smart delegation, self-correction — out of the box.

[ACL 20205] Official respository for EvoPatient: LLMs Can Simulate Standardized Patients via Agent Coevolution

Self-evolving AI daemon in Go with fully generative UI. LLM generates unique HTML/ANSI interfaces from scratch for every response — not templates, not component catalogs. 10-stage pipeline, 4-level reflection, fractal agents, auto-generated code skills, 6 input channels.