# Deep Research Langchain

> Run LangChain Open Deep Research or LangGraph-based iterative research workflows with configurable retrieval, reflection, and server-backed execution. Use when a benchmark or task needs inspectable graph orchestration rather than a single hosted research API.

- Skill: `closedloop-technologies/deep-research-langchain` (Agent Skill, multi-file: 5 files)
- Install (CLI): `npx skillmds@latest add closedloop-technologies/deep-research-langchain`
- Raw SKILL.md: https://api.skillmd.com/api/skills/closedloop-technologies/deep-research-langchain/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: closedloop-technologies (https://skillmd.com/u/closedloop-technologies)
- Updated: 2026-09-10
- Page: https://skillmd.com/skills/closedloop-technologies/deep-research-langchain

---


# LangChain Open Deep Research

Use this skill when you need an inspectable graph workflow with iterative
research, reflection, and configurable retrieval.

## Environment

```bash
op run --env-file .env.climbhill -- python .agents/skills/deep-research-langchain/scripts/research.py \
  --query "AI for Science agents: current systems and evidence" \
  --max-iterations 2
```

Common 1Password-backed variables:

- `OPENAI_API_KEY` or `ANTHROPIC_API_KEY`
- `TAVILY_API_KEY`

## Cost Controls

- Keep `--max-iterations` at 1 or 2 for benchmark tasks.
- Use a low-cost model for reflection and summarization.
- Skip this benchmark when the local LangGraph server is not running.

## Source Link

- https://github.com/langchain-ai/open_deep_research

