Arbor is an AI agent that autonomously handles the full research workflow—from designing experiments and finding literature to running tests and refining solutions—specifically for researchers.
983 upvotes
Tracked by Kanon since Aug 1, 2026
🤖 Agent teardown · research
Job to be doneResearchers need to automate the end-to-end process of exploring new topics, designing experiments, gathering evidence, and optimizing solutions, but manual execution is slow and resource-intensive.
Who it is forResearchers in academic and applied science fields, particularly those working on complex, exploratory projects.
Prerequisitesopen source · self-hostable · no API key needed
PricingFree + $20/mo for advanced features
Traction · why it is risingGained 983 votes on Product Hunt, indicating strong early interest from technical and research communities.
Why it matters
It demonstrates advanced multi-step autonomy in a real-world research context, offering a blueprint for how AI agents can orchestrate complex workflows in scientific discovery.
Signal source: GitHub
Visit official site →
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.