Discover the toolingbehind modern intelligence
The operating system for AI infrastructure discovery. Search a live map of MCP servers, AI agents, LLM tools, automation systems, and developer infrastructure.
agentset
The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.
2kstars
180forks
TypeScript
agentic-ragaiai-agentsai-sdkchatbotsembeddingsgenaillmsmemorymemory-managementragvercel-ai-sdk
Quality signals
ActiveNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
Open-source platform to build, evaluate, and deploy production-ready RAG and agentic applications with built-in citations and 22+ file formats.
Use this when
- Need citations for LLM responses
- Handling 22+ file formats (PDF, DOCX, etc.)
- Evaluating RAG performance before production
- Hosting RAG apps with custom domains
- Integrating with your preferred LLM or vector DB
Don't use when
- Building simple chatbots without retrieval
- Need a lightweight local-only solution
- Working with non-text data (images, audio)
Capabilities
- Built-in citations for retrieved sources
- Supports 22+ file formats for ingestion
- Model-agnostic (works with any LLM or vector DB)
- Production hosting with custom domains
- Built-in evaluation and benchmarking tools
- Multi-tenancy support for team projects
InstallMCP + SKILLInstall as a Claude Code skill
Universal installANY TOOL
$ npx skillcity@latest agentset-ai/agentsetAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor or Cline.
Requires Node.js 18+ (ships with npx).
Or install manually
# Install into ~/.claude/skills/ mkdir -p ~/.claude/skills/agentset curl -fsSL https://raw.githubusercontent.com/agentset-ai/agentset/main/SKILL.md -o ~/.claude/skills/agentset/SKILL.md
Loading README…
Ask a simulated agent to run this skill. It loads the real SKILL.md and reasons over your task with NVIDIA.
agentset — sandboxAI sandbox
Pick a quick prompt below or type your own — watch the agent execute this skill step by step.
guest@skillcity:~$Try a prompt