Skip to content
Agent Search Engine

System class · No. 07

Research & Data Agents

Agents that search, analyze, and synthesize information, documents, and data.

27 records · independent index · how we rank

Research and data agents search, read, and synthesize information — across the open web, academic sources, or your own documents — into answers you can act on, ideally with citations. The decision comes down to source quality and coverage, how transparently the agent cites what it used, and whether it can work over your private or internal data as well as the public web. For anything high-stakes, verifiable citations you can click and check matter far more than fluent prose: the failure mode of these tools is confident synthesis of wrong or outdated sources, so treat them as accelerators, not authorities. Look at how the agent handles conflicting sources, whether it distinguishes primary from secondary material, and how it deals with recency on fast-moving topics.

If you're pointing it at your own corpus, evaluate the connectors, how it chunks and retrieves, and whether answers stay grounded in your documents rather than drifting to the model's memory. Pricing ranges from free open-source pipelines you run yourself to usage-based hosted products, and deeper research runs cost more in tokens and time. The most useful tools make their reasoning and sources inspectable so you can audit an answer instead of just trusting it — verify anything consequential before you rely on it, and prefer transparency over confidence.

Building one yourself? How to build a RAG knowledge assistant

Commercial products

Alphabetical — stars don't measure commercial adoption

Open-source index

→ See the best open-source research & data agents, ranked

By language: Python research & data agents

Rank by
firecrawlInfrastructureThe API to search, scrape, and interact with the web at scale.TypeScript · 168k stars · AGPL-3.0 · Aug 2026ScraplingInfrastructureAn 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 2025FastGPTPlatformFastGPT 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,TypeScript · 29k stars · Aug 2026gpt-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 2026WeKnoraPlatformOpen-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.Go · 20k stars · 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 2026
Signal inventory open — put your agent in front of people choosing oneReserve a signal slot →
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.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 2026DeepAnalyzeAgentDeepAnalyze 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 2026SidekickAgentA 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.Swift · 3.3k stars · MIT · May 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 is a research agent?
A research agent gathers and synthesizes information across many sources — web, papers, or your documents — and produces summarized, ideally cited, answers.
How do I choose a research agent?
Weigh source coverage and quality, how transparently it cites, whether it can search your private data, and how it handles conflicting or uncertain information.
Can research agents be trusted?
Treat them as accelerators, not authorities: prefer tools that cite sources you can check, and verify anything consequential.