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.
deep-research
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
4.6kstars
1.1kforks
JavaScript
anthropicdeep-researchdeep-research-apideepresearchdeepseekgeminigrokmcp-serverollamaopenai
Quality signals
StaleNo testsNo CIThin docsNo licensePopular
AI summary
Auto-generated overview of what this skill does and when to reach for it.
Generate detailed research reports using any LLM with local data processing and web search support.
Use this when
- Need fast, structured research on niche topics
- Want to analyze uploaded documents or PDFs locally
- Prefer privacy-focused AI research without cloud dependencies
- Require web search integration for LLMs without browsing
- Need to refine research iteratively with knowledge graphs
Don't use when
- For simple Q&A tasks (use chatbots instead)
- When real-time collaboration is required
- If you need strict compliance with enterprise data policies
Capabilities
- Generates research reports in ~2 minutes using LLMs
- Supports 10+ LLMs (Gemini, OpenAI, DeepSeek, etc.)
- Local file processing (PDFs, Office docs) for private knowledge bases
- Web search integration for LLMs without native browsing
- Knowledge graph generation for report visualization
- Research history preservation with iterative refinement
InstallSKILLInstall as a Claude Code skill
Universal installANY TOOL
$ npx skillcity@latest u14app/deep-researchAuto-detects the skill or MCP server in this repo and installs it for Claude Code, Codex, Cursor, Cline, OpenCode, Gemini CLI, Anti-Gravity, OpenClaw and Hermes.
Requires Node.js 18+ (ships with npx).
Or install manually
# Install into ~/.claude/skills/ mkdir -p ~/.claude/skills/deep-research curl -fsSL https://raw.githubusercontent.com/u14app/deep-research/main/SKILL.md -o ~/.claude/skills/deep-research/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.
deep-research — 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