Open source · self-hostable
Best open-source research & data agents
The open-source research & data agents in the index — self-hostable, inspectable, and free to run. Ranked by real maintained adoption (GitHub stars and recent commit activity), never by sponsorship. Open source buys you control, privacy, and no vendor lock-in; the trade-off is that you host and maintain it yourself. Right now it's led by firecrawl (186k stars), with Scrapling and TrendRadar close behind. Rankings shift as projects gain stars and ship commits.
firecrawlInfrastructureThe API to search, scrape, and interact with the web at scale.Open sourceTypeScript · AGPL-3.0Verified · Active 186kGitHub starsScraplingInfrastructureAn adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!Open sourcePython · BSD-3-ClauseVerified · Active 84kGitHub starsTrendRadarAgentAI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.Open sourcePython · GPL-3.0Verified · Active 63kGitHub starsBettaFishAgentA multi-agent public-opinion analysis assistant anyone can use -- reconstructs the real shape of public sentiment and forecasts where it is heading. Built from scratch, no framework dependencies.Open sourcePython · GPL-2.0Verified · Active 42kGitHub starskhojAgentYour AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research.Open sourcePython · AGPL-3.0Verified 38kGitHub starsstormAgentAn LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.Open sourcePython · MITVerified 32kGitHub starsWeKnoraPlatformOpen-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.Open sourceGoVerified · Active 31kGitHub starsFastGPTPlatformFastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI workflow orchestration,Open sourceTypeScriptVerified · Active 30kGitHub starsgpt-researcherAgentAn autonomous agent that conducts deep research on any data using any LLM providersOpen sourcePython · Apache-2.0Verified · Active 30kGitHub starshaystackFrameworkOpen-source AI orchestration framework for building context-engineered, production-ready LLM applications.Open sourcePython · Apache-2.0Verified · Active 27kGitHub starsDeepResearchAgentTongyi Deep Research, the Leading Open-source Deep Research AgentOpen sourcePython · Apache-2.0Verified 20kGitHub starslocal-deep-researchAgent~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google,...). 10+ search engines - arXiv, PubMed, your private documents.Open sourcePython · MITVerified · Active 9.1kGitHub stars
Make your product part of the discovery.Explore advertising 
MiroThinkerAgentMiroThinker 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.Open sourcePython · Apache-2.0Verified 8.4kGitHub starsdeep-searcherAgentOpen Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.Open sourcePython · Apache-2.0Verified · Active 8.3kGitHub starsunstractPlatformLLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline WorkflowsOpen sourcePython · AGPL-3.0Verified · Active 7.3kGitHub starsDeepAnalyzeAgentDeepAnalyze is the first agentic LLM for autonomous data science.Open sourcePython · MITVerified · Active 4.7kGitHub starsms-agentFrameworkMS-Agent: a lightweight framework to empower agentic execution of complex tasksOpen sourcePython · Apache-2.0Verified · Active 4.4kGitHub starsSidekickAgentA native macOS app that allows users to chat with a local LLM that can respond with information from files, folders and websites on your Mac without installing any other software.Open sourceSwift · MITVerified 3.3kGitHub starsMiroFlowFrameworkTop-1 on 5+ benchmarks | Web UI | Supports MiroThinker, Claude, Kimi, OpenAIOpen sourcePython · Apache-2.0Verified 3.1kGitHub starsAuto-Deep-ResearchAgent"Your Fully-Automated Personal AI Assistant"Open sourcePythonVerified 1.7kGitHub starsToolUniverseSDK / libraryDemocratizing AI scientists with ToolUniverseOpen sourcePython · Apache-2.0Verified · Active 1.7kGitHub starsAdalaFrameworkAdala: Autonomous DAta (Labeling) Agent frameworkOpen sourcePython · Apache-2.0Verified · Active 1.6kGitHub starsTrustRAGFrameworkTrustRAG：The RAG Framework within Reliable input,Trusted outputOpen sourcePythonVerified 1.3kGitHub stars
Frequently asked
- What are the best open-source research & data agents?
- The projects listed below, ranked by maintained adoption — GitHub stars plus recent activity — so you see what's genuinely used and still maintained, not abandoned.
- Are open-source research & data agents free?
- The software is free to run and self-host. You still pay for the infrastructure you run it on and any model or API usage it makes.
- Open-source or commercial research & data agents — which should I choose?
- Pick open source for control, privacy, and no lock-in when you're happy to host and maintain it; pick a commercial product for a managed, supported experience. You can compare both in the full research & data agents category.