9 open-source agents tracked · Ranked by trust score · Updated 2026-06-04 18:04 UTC
HVTracker independently evaluates 9 open-source research & data using daily signals from GitHub, package registries, and security databases. Each agent is scored on activity, adoption, transparency, safety, and identity. The top-ranked research & data is Docling with a trust score of 88.8/100 (Grade A). Other leading projects include Unstructured and Firecrawl.
| # | Agent | Trust | Stars | Language |
|---|---|---|---|---|
| 1 | Docling A Listed Get your documents ready for gen AI | 88.8 | 61.0k | Python |
| 2 | Unstructured A Listed Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex doc | 84.7 | 14.8k | HTML |
| 3 | Firecrawl B Listed The API to search, scrape, and interact with the web at scale. 🔥 | 73.1 | 128.5k | TypeScript |
| 4 | DeerFlow B Listed An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories | 70.5 | 70.4k | Python |
| 5 | GPT Researcher B Listed An autonomous agent that conducts deep research on any data using any LLM providers | 69.0 | 27.5k | Python |
| 6 | Crawl4AI B Listed 🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN | 67.7 | 67.8k | Python |
| 7 | WrenAI B Listed Give AI agents the context to query business data correctly through the open context layer that gives AI agents grounded | 65.1 | 15.4k | Python |
| 8 | Maxun C Listed 🔥 The open-source no-code platform for web scraping, crawling, search and AI data extraction • Turn websites into struct | 61.0 | 15.7k | TypeScript |
| 9 | STORM D Listed An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations. | 42.3 | 28.3k | Python |