by Shiyao-Huang · Agent Tool · ★ 171
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
Awesome Self-Evolving AI Agents 一份面向 AI Agent 自进化研究与实践的开放 Survey：帮你判断一个系统是真能从反馈中改进，还是只是在 demo 里看起来聪明。 中文主入口 项目报告 GitHub Topics: , , , , , , , , , , . GitHub topic 收录证据（2026-06-05）：GitHub Topic Indexing Readiness 已验证远端 topics、GitHub Search 和 topic 页面均返回本仓库；如果网页 topic 页短暂滞后，按 GitHub search/API 作为更新鲜证据。 一句话 想判断一个 AI Agent 是不是“真自进化”，先问五件事：改了什么、为什么改、谁验证、是否保留、能否回滚。 三句话 这份 Survey 不先堆链接，而是先给判断表：一个系统到底改变了 prompt、memory、workflow、code、weights，还是只换了说法。 读项目时不要先看名字、stars 或 demo；先看它有没有 Observe - Interpret - Modify - Verify - Retain 的闭环。 Evolve-AGI Index 目前只是工作型证据指数原型，用来提示 benchmark、闭环、迁移、治理这些证据是否足够，不是 AGI 分数，也不是单个项目判决。 五句话 这不是普通 Awesome List，而是一份围绕“AI Agent 如何可靠地改进自己”的开放 Survey。 在本 Survey 的严格口径下，自进化系统需要说明可变对象、反馈信号、更新算子、独立评估器、保留机制和回滚路径。 当前读者最容易复查的机制骨架是五类进化回路：规范到执行、搜索、评估器、反思/记忆、种群/归档。 Evolve-AGI Index 把 benchmark、闭环、证据、迁移、可运行性、动量和治理放在一张可讨论的表里，但权重仍是 editorial/proposed，还需要外部验证和敏感性分析。 读者可以从这里快速进入定义、五类回路、代码自改进 benchmark、项目 model card、公开报告和论文，而不是被几百个链接
| Stars | 171 |
| Forks | 9 |
| Language | JavaScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 45.96/100 |
| Open Issues | 4 |
| Last Updated | 2026-06-21 |
| Created | 2026-05-22 |
| Platforms | node |
| Est. Tokens | ~17k |
These tools work well together with awesome-agent-evolution for enhanced workflows:
Looking for a awesome-agent-evolution alternative? If you're comparing awesome-agent-evolution with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A curated list of AI Agent evolution, memory systems, multi-agent architectures, and self-improvement projects
The Library for LLM-based multi-agent applications
Agent Waystation · Agent 驿站 — a stopover for AI agents, builders, tools, and field reports
Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory,
[NAACL2025] LiteWebAgent: The Open-Source Suite for VLM-Based Web-Agent Applications
The agent OS that evolves itself. 51 workers, 18 security layers, self-improving functions. Built on iii-engin
Explore other popular agent tool tools:
awesome-agent-evolution is Open survey and evidence map for AI agent evolution, self-evolving agents, memory, skills, harnesses, benchmarks, and agent-swarm systems.. It is categorized as a Agent Tool with 171 GitHub stars.
awesome-agent-evolution is primarily written in JavaScript. It covers topics such as agent-evolution, agent-framework, agent-swarm.
You can find installation instructions and usage details in the awesome-agent-evolution GitHub repository at github.com/Shiyao-Huang/awesome-agent-evolution. The project has 171 stars and 9 forks, indicating an active community.
awesome-agent-evolution is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to awesome-agent-evolution on Agent Skills Hub include awesome-agent-evolution, LiteMultiAgent, openclaw-qa. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.