DeepResearch and deep-research

These are independent competitors offering similar architectures—both implement iterative deep research workflows combining LLMs with search and web scraping—with no direct technical integration or dependency relationship between them.

DeepResearch
55
Established
deep-research
48
Emerging
Maintenance 10/25
Adoption 10/25
Maturity 16/25
Community 19/25
Maintenance 2/25
Adoption 10/25
Maturity 16/25
Community 20/25
Stars: 18,422
Forks: 1,419
Downloads:
Commits (30d): 0
Language: Python
License: Apache-2.0
Stars: 18,562
Forks: 1,926
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
No Package No Dependents
Stale 6m No Package No Dependents

About DeepResearch

Alibaba-NLP/DeepResearch

Tongyi Deep Research, the Leading Open-source Deep Research Agent

Implements a 30.5B parameter sparse-activation model (3.3B per token) trained on synthetic agentic data through continual pre-training, supervised fine-tuning, and on-policy reinforcement learning with Group Relative Policy Optimization. Supports dual inference paradigms—ReAct for core capability evaluation and IterResearch-based "Heavy" mode for test-time scaling—with tool integrations for web search (Serper), page reading (Jina), code execution (SandboxFusion), and multi-modal document parsing.

About deep-research

dzhng/deep-research

An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the simplest implementation of a deep research agent - e.g. an agent that can refine its research direction overtime and deep dive into a topic.

Implements a recursive research loop with configurable depth and breadth parameters, using LLM-generated search queries fed through Firecrawl for web scraping and content extraction. The agent maintains context across iterations to refine research directions based on accumulated learnings, then synthesizes findings into structured markdown reports. Supports multiple LLM backends including OpenAI, DeepSeek R1 via Fireworks, and local OpenAI-compatible endpoints, with tunable concurrency limits for API rate management.

Scores updated daily from GitHub, PyPI, and npm data. How scores work