Same iterative deep-research loop; choose if you prefer a Node/TypeScript implementation with SSE/MCP endpoints.
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
- 4.7k
- JavaScript
- MIT
deep research / web research agent
Fully local web research assistant that iteratively searches, summarizes, reflects, and re-searches using Ollama/LMStudio-hosted LLMs to produce a markdown report with sources.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Same iterative deep-research loop; choose if you prefer a Node/TypeScript implementation with SSE/MCP endpoints.
Use any LLMs (Large Language Models) for Deep Research. Support SSE API and MCP server.
Same iterative deep-research loop; choose if you want it built on the OpenAI Agents SDK.
An implementation of iterative deep research using the OpenAI Agents SDK
Same LangChain-based deep research with citation-backed credibility scoring.
Multi-agent autonomous research system using LangGraph and LangChain. Generates citation-backed reports with credibility scoring and web search
Same progressive search and cross-evaluation deep research framework.
A deep research framework based on progressive search and cross-evaluation.
Mature, widely used deep research agent with many LLM provider integrations.
An autonomous agent that conducts deep research on any data using any LLM providers
Full-featured open-source deep research agent from Alibaba; good if you want a production-grade system.
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Deep research agent optimized for complex/prediction tasks; choose for stronger benchmark performance.
MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.
Lightweight TypeScript iterative deep researcher; choose if you want a minimal Node-based implementation.
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.
Simpler iterative deep research agent; choose if you want a minimal codebase.
Deeper Seeker is an simpler OSS version of OpenAI's latest Deep Research feature in ChatGPT.It is an agentic research tool to reason , create multi step tasks , synthesize data from multiple online resources and create neat reports
Cloud-oriented sibling from the same org; choose if you want the non-local version of this agent.
TypeScript alternative to Gemini Deep Research; choose for a Node-based iterative research agent.
Open source alternative to Gemini Deep Research. Generate reports with AI based on search results.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Deep research over private data instead of the web; use when your sources are internal documents.
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
Broader local-first personal AI with deep research as one capability; choose if you want a full assistant platform.
Your Personal AI super intelligence. A brain that builds a local-first memory of your life, a fantastic orchestrator of agent fleets and workflows, and a deep researcher.
General long-horizon agent harness that includes research, coding, and creation; choose for a broader agent system.
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
Knowledge-curation approach to report generation from multiple perspectives; choose for academic-style synthesis.
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Autonomous research-to-paper pipeline; choose when you need a full academic paper rather than a markdown summary.
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. ๐ฆ
Self-hostable AI second brain with deep research among many features; choose if you want an integrated personal AI.
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.
Fully local Manus-like autonomous agent that browses and codes; choose if you want a broader agent.
Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity.
These projects were analysed and named local-deep-researcher among their alternatives. The relationship is not symmetric โ how local-deep-researcher rates them is a separate judgement, made when local-deep-researcher is analysed in its own right.
calls local-deep-researcher โsame deep research agent optimized for fully local and private research.โ
An autonomous agent that conducts deep research on any data using any LLM providers
calls local-deep-researcher โfully local iterative web research and report writing with LangChainโ
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.
calls local-deep-researcher โUse when you need fully local research without sending data to cloud APIs, accepting the need for local LLM hardware.โ
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
calls local-deep-researcher โfully local deep research with local LLMs; choose it if you require private, offline research.โ
Tongyi Deep Research, the Leading Open-source Deep Research Agent
calls local-deep-researcher โUse if you need fully local web research and report writing without external API calls.โ
MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.
calls local-deep-researcher โChoose for fully local web research with no external APIs, if you need to run everything offline and do not need vector-DB private data features.โ
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
calls local-deep-researcher โWhen you want a fully local Python research report writer and don't need memory/orchestration.โ
Your Personal AI super intelligence. A brain that builds a local-first memory of your life, a fantastic orchestrator of agent fleets and workflows, and a deep researcher.
calls local-deep-researcher โnarrower: local-only web research and report writing, no experiments.โ
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. ๐ฆ