deep-research-agent

Dependency freshness

Declared = lowest version the kit's dependency file (package.json, pyproject.toml or requirements.txt) allows. Latest = the npm "latest" tag or the newest PyPI release. TypeScript, the Stripe SDK, FastAPI and other 0.x packages are shown but not counted in the verdict.

What's in the stack

AI

LangChain, LangGraph

API layer

Pydantic

Detected from declared dependencies. A listed package means it's installed, not necessarily fully wired up.

What the README says you get

• AI
  Multi-agent research systemFour specialized autonomous agents orchestrated by LangGraph's StateGraph
• AI
  Autonomous search agentSearch agent dynamically decides queries, sources, and extraction depth
• AI
  Quality validation with retrySection-level validation with retry logic and exponential backoff
• AI
  Citation formattingAdds proper citations (APA, MLA, Chicago, IEEE)
• AI
  Local and cloud modelsLocal models (Ollama, llama.cpp) and Cloud APIs (Google Gemini, OpenAI)
• API
  Search provider abstractionExtensible search backend (DuckDuckGo, with easy addition of others)
• Content
  Multi-format report exportReports in Markdown, HTML, and plain text
• Data
  Research caching7-day TTL file-based caching with MD5 topic hashing
• Deploy
  Connection poolingHTTP/2 with persistent connections via httpx
• Deploy
  Workflow checkpointingWorkflow state persistence for crash recovery
• UI
  Chainlit web interfaceInteractive Chainlit UI with real-time progress

Extracted from the kit's README by a local AI model (deepseek-flash) on Sep 29, 2026. Every item is checked against an exact README quote; 3 unverifiable items were discarded. A README claim is the maker's description, not something we tested.