Skip to content
Agent Search Engine

Open source · Python

Best Python research & data agents

The open-source research & data agents written in Python, from the Agent Search Engine index — ranked by real maintained adoption (GitHub stars and recent commit activity), never by sponsorship. Every project here is Python-first, self-hostable, and free to run; the trade-off is you host and maintain it yourself. Right now it's led by Scrapling (75k stars), with TrendRadar and BettaFish close behind. Rankings shift as projects gain stars and ship commits.

19 open-source records · all research & data agents · more best-of lists · how we rank

ScraplingInfrastructureAn adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!Python · 75k stars · BSD-3-Clause · Aug 2026TrendRadarAgentAI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.Python · 62k stars · GPL-3.0 · Jul 2026BettaFishAgent微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。Python · 42k stars · GPL-2.0 · Aug 2026khojAgentYour AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research.Python · 37k stars · AGPL-3.0 · Aug 2026stormAgentAn LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.Python · 31k stars · MIT · Sep 2025gpt-researcherAgentAn autonomous agent that conducts deep research on any data using any LLM providersPython · 29k stars · Apache-2.0 · Jul 2026haystackFrameworkOpen-source AI orchestration framework for building context-engineered, production-ready LLM applications.Python · 26k stars · Apache-2.0 · Aug 2026DeepResearchAgentTongyi Deep Research, the Leading Open-source Deep Research AgentPython · 20k stars · Apache-2.0 · Feb 2026local-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.Python · 8.9k stars · MIT · Aug 2026MiroThinkerAgentMiroThinker 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.Python · 8.4k stars · Apache-2.0 · Jul 2026deep-searcherAgentOpen Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.Python · 8.1k stars · Apache-2.0 · Nov 2025unstractPlatformLLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline WorkflowsPython · 7.1k stars · AGPL-3.0 · Aug 2026
Signal inventory open — put your agent in front of people choosing oneReserve a signal slot →
DeepAnalyzeAgentDeepAnalyze is the first agentic LLM for autonomous data science. 你的AI数据分析师，自动分析大量数据，一键生成专业分析报告！Python · 4.5k stars · MIT · Jul 2026ms-agentFrameworkMS-Agent: a lightweight framework to empower agentic execution of complex tasksPython · 4.4k stars · Apache-2.0 · Aug 2026MiroFlowFrameworkTop-1 on 5+ benchmarks | Web UI | Supports MiroThinker, Claude, Kimi, OpenAIPython · 3.1k stars · Apache-2.0 · Jul 2026Auto-Deep-ResearchAgent"Your Fully-Automated Personal AI Assistant"Python · 1.7k stars · Oct 2025ToolUniverseSDK / libraryDemocratizing AI scientists with ToolUniversePython · 1.6k stars · Apache-2.0 · Aug 2026AdalaFrameworkAdala: Autonomous DAta (Labeling) Agent frameworkPython · 1.6k stars · Apache-2.0 · Aug 2026TrustRAGFrameworkTrustRAG：The RAG Framework within Reliable input,Trusted outputPython · 1.3k stars · Jan 2026

Frequently asked

What are the best Python research & data agents?
The Python projects listed below, ranked by maintained adoption — GitHub stars plus recent commit activity — so you see what's genuinely used and still maintained, not abandoned.
Are these Python research & data agents open source and free?
Yes — every project on this page is open source and written primarily in Python. 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.
Why choose Python research & data agents specifically?
Staying in your team's primary language — Python — makes self-hosting, extending, and debugging far easier, because you can read and modify the source directly instead of treating it as a black box.