deep-research

An AI-powered research assistant that refines its topic focus over time using search engines, web scraping, and large language models.

GitHub

GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026

104views this month

20k stars2.0k forksLast push Apr 11, 2026 TypeScript MIT

Decision brief

Deep-research is an AI-powered research assistant that leverages search engines, web scraping, and large language models to conduct iterative and in-depth exploration of topics.

Good fit when

When you need a tool that can refine its topic focus over time through repeated iterations.
If your research project requires integration with both Firecrawl (for search/content extraction) and OpenAI APIs for enhanced capabilities.

Avoid when

When you prefer a language other than TypeScript, as deep-research specifically requires a Node.js environment.
If your use case does not necessitate the use of both Firecrawl and OpenAI APIs, preferring instead solutions with more API flexibility or that do not require API keys.

Requirements:: Requires Docker

Observed Jul 11, 2026 · Source: enrich:decision_facts

deep-research alternatives Trust report

deep-research vs gpt-researcher deep-research vs DeepResearch deep-research vs deep-searcher

Verify the decision

Adoption

Package downloads where a registry match exists. GitHub stars (19,571) are secondary evidence.

npm downloads (30d): 61·npm downloads API·Aug 19, 2026

Maintenance and security

Full trust report

Maintenance: Slowing (129d since push); As of Aug 19, 2026
Provenance: Not a fork · Personal account; As of Aug 19, 2026
Security (OSV): 39 low (39 low); As of Jul 11, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

npm install deep-research

npm

How it fits your stack(13)

Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.

Relationship graph

Optional deeper exploration of typed edges and category neighbours.

Similar tools

Same-category neighbours not already linked as typed edges.

gpt_academic

Provides practical interaction interfaces for GPT/GLM LLMs, optimized for academic paper reading, polishing, and writing.

71k★

academic-research-skills

Workflow for academic research and writing with AI tools

49k★

khoj

Self-hostable AI second brain for personalized research and automation

37k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

dzhng/deep-research offers a deep research agent implementation combining search functions with AI technologies for iterative and in-depth exploration of topics. It operates within a TypeScript environment, relying on Node.js to run and involving specific API keys (Firecrawl and OpenAI) for functionality via an easily adjustable Docker setup.

Capability facts

Deploy: Self-host
Source: dockerfile:Dockerfile · Aug 19, 2026
Docker: Dockerfile present
Source: dockerfile:Dockerfile · Aug 19, 2026
CLI: CLI entrypoint
Source: package.json:bin|scripts · Aug 19, 2026
MCP server: No MCP server detected
Source: repo_scan · Aug 19, 2026
Languages: typescript, javascript
Source: github.language+package.json · Aug 19, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Node.js runtimeNode.js

Source: README excerpt (regex_v1, Aug 19, 2026)

- Node.js environment

Source link

OpenAI APIOpenAI API

Source: README excerpt (regex_v1, Aug 19, 2026)

- OpenAI API (for o3 mini model)

Source link

README

Requirements Node.js environment API keys for: Firecrawl API (for web search and content extraction) OpenAI API (for o3 mini model) Docker 1. Clone the repository 2. Rename to and set your API keys 3. Run 4. Run the Docker image: 5. Execute in the docker service: License MIT Lice...

For agents

This page has a .md twin and JSON over the API.

/tools/dzhng-deep-research.md GET /api/graphcanon/tools/dzhng-deep-research GET /api/graphcanon/graph?tool=dzhng-deep-research