awesome-ai-agents vs agentskills
AI agent directories compared
awesome-ai-agents and agentskills are curated directories for people building or studying AI agents. awesome-ai-agents surveys a broad range of agent tools and infrastructure, while agentskills centers on Anthropic Agent Skills and related MCP resources, research, and benchmarks.

awesome-ai-agents: Discover AI Agent Tools and Research
A community-curated directory of AI agent frameworks, tools, platforms, research papers, and learning resources. Use it to explore the fast-changing agent ecosystem and compare options by category.

agentskills: Explore Agent Skills, Research, and Tools
A curated directory for exploring LLM skills, papers, tools, frameworks, benchmarks, and learning resources. Centered on Anthropic Agent Skills, it also covers MCP and the broader agent ecosystem.
| awesome-ai-agents | agentskills | |
|---|---|---|
| License | CC0-1.0 | MIT |
| Stars | 81 | 89 |
| Forks | 99 | 18 |
| Last analyzed | Nov 3, 2026 | Oct 21, 2026 |
Key differences
- awesome-ai-agents spans frameworks, platforms, infrastructure, safety, evaluation, research, and learning resources; agentskills focuses on skills, MCP, papers, tools, and related agent projects.
- awesome-ai-agents groups frameworks by uses such as multi-agent orchestration, coding, personal, browser, and research agents; agentskills highlights computer-use, browser, and coding projects alongside skill learning.
- awesome-ai-agents lists both open-source projects and hosted services; agentskills emphasizes Agent Skills documentation, MCP resources, research, and benchmarks.
- awesome-ai-agents is licensed CC0-1.0, while agentskills is licensed MIT.
- agentskills is marked quiet, with no commits in the last 90 days and activity concentrated in one contributor; no comparable activity details are given for awesome-ai-agents.
Choose awesome-ai-agents if you…
- need to survey a broad range of agent frameworks, infrastructure, and safety resources.
- want to compare open-source projects with hosted services across different deployment approaches.
- are looking for resources spanning agent building, evaluation, governance, and learning.
Choose agentskills if you…
- want to explore Anthropic Agent Skills documentation, examples, and community resources.
- are researching MCP implementations, skill learning, tool use, or computer-use benchmarks.
- need tutorials and papers focused on skills and related LLM agent technologies.
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.