agentskills vs Awesome-Self-Evolving-Agents
Curated LLM agent resources compared
agentskills and Awesome-Self-Evolving-Agents are curated directories for exploring research and resources related to LLM agents. agentskills spans skills, MCP, tool use, and computer-use agents, while Awesome-Self-Evolving-Agents focuses on how agents improve through model, environment, or combined evolution.
agentskills: Explore Resources for Building LLM Agent Skills
A curated directory of papers, tools, frameworks, and learning resources for LLM skills and agents. Use it to survey the ecosystem, find relevant projects, and follow research across skills, MCP, tool use, and computer-use agents.
Awesome-Self-Evolving-Agents: Explore Research on Evolving Agents
A curated research index and survey companion covering self-evolving AI agents. It organizes papers, benchmarks, libraries, and applications for researchers and practitioners exploring how agents improve through model, environment, and combined evolution.
| agentskills | Awesome-Self-Evolving-Agents | |
|---|---|---|
| Language | not specified | — |
| License | MIT | — |
| Stars | 89 | 463 |
| Forks | 18 | 38 |
| Last analyzed | Oct 3, 2026 | Oct 3, 2026 |
Key differences
- agentskills covers a broad set of agent topics, including MCP, GUI agents, tool use, frameworks, and benchmarks; Awesome-Self-Evolving-Agents centers its catalog on agent evolution.
- agentskills groups documentation, tutorials, courses, projects, papers, and benchmarks; Awesome-Self-Evolving-Agents organizes papers, benchmarks, libraries, and applications by evolution approach and research theme.
- Awesome-Self-Evolving-Agents accompanies a survey on self-evolving agents, while agentskills is an annotated resource directory associated with a survey citation.
- agentskills lists an MIT license; Awesome-Self-Evolving-Agents has no license detail in the supplied project information.
- The supplied metadata lists 89 stars and 18 forks for agentskills, and 463 stars and 38 forks for Awesome-Self-Evolving-Agents.
Choose agentskills if you…
- need a broad starting point across agent skills, MCP, tool use, and computer-use resources.
- want tutorials, courses, documentation, and implementation examples alongside research links.
- are comparing agent frameworks, projects, and benchmarks across several adjacent topics.
Choose Awesome-Self-Evolving-Agents if you…
- want a taxonomy focused on model-centric, environment-centric, and combined agent evolution.
- are mapping papers, benchmarks, libraries, and applications for a literature review on self-evolving agents.
- want to explore research themes such as self-correction, online learning, memory, skills, and tools.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.