# langchain-ai/open_deep_research

Repository: https://github.com/langchain-ai/open_deep_research
Canonical: https://ross.abutalabs.com/products/open_deep_research
Language: Python
License: MIT
License Family: permissive
Archived: true
Last push: 2026-08-10T18:13:37+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 35, longevity 46
- inputs: {"age_days": 651, "days_push": 23, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 12673, forks 1815 (observed 2026-08-28T04:10:59.587545+00:00)

## What it is
An open-source deep research agent built with LangGraph that performs multi-step web research using configurable LLM providers, search tools, and MCP servers. It runs as a local LangGraph server with a Studio UI and API, and ranks competitively on the Deep Research Bench leaderboard.

## Use cases
- run an open-source deep research agent on my own models
- automate multi-step web research reports
- compare deep research agents across LLM providers
- build a research assistant with MCP tool integration
- self-host a deep research alternative to OpenAI Deep Research
- evaluate agent performance on deep research benchmarks

## When to choose
- you want a configurable, self-hosted deep research agent
- you need support for many LLM providers, search tools, and MCP servers
- you want to study or extend a well-regarded research agent codebase

## When to avoid
- you need a fully managed hosted research product with no setup
- you want a simple single-shot search rather than an agentic multi-step workflow
- you are not prepared to supply your own model and search API keys

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, rag, search-engine, llm-inference, web-scraping
- domain: artificial-intelligence, large-language-models, developer-tools
- platform: python, self-hosted
- tags: deep-research, langgraph, mcp, multi-provider-llm, research-agent, ai-agents, retrieval-augmented-generation, search, web-server, docker

## Member repositories
- langchain-ai/open_deep_research (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:59.587545+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:13:52.142624+00:00, confidence not recorded.
  - readme: https://github.com/langchain-ai/open_deep_research (fetched 2026-08-28T04:10:59.587545+00:00, sha 88cb127c27d8)
- Data as of 2026-08-30T08:39:29.467469+00:00.