Run a configurable deep-research agent and inspect its report traces
At a glance
Open Deep Research provides a public LangGraph implementation with separate research, summarization, compression, and report roles, configurable search providers, MCP support, and an evaluation workflow. This workflow is listed under builder, open-deep-research, langgraph, research-agents, citations.
Agents / tools
Open Deep Research, LangGraph, LangSmith, Tavily, MCP
A LangChain sample demonstrates parallel trip-input preparation, a join barrier, weather research, a human interrupt for preferences, and itinerary assembly using the same graph locally and when deployed.
LangChain's enrichment template searches and reads the web, extracts facts into a supplied schema, and checks completeness, with configurable models and tools in LangGraph Studio.
Google's multimodal tutorial uses a LangGraph orchestrator to send files to specialist Gemini agents, gather their modality-specific findings, and synthesize whether a requested object is present.
MIT Python package signs every policy-gated tool call into a hash-chained .tkb file verifiable offline (Python+TS); works across Claude Code, OpenAI Agents, LangChain/LangGraph, MCP and more—agents can edit their own logs but not hide edits when the signer is out of reach.