feynman is a research AI agent for Automate literature reviews, experiment design, and data analysis to accelerate scientific research. Pricing: Free. As of 2026-10-25, KanonAgent records 1.2k upvotes. First indexed by KanonAgent on 2026-09-07.
An open-source AI agent that autonomously handles literature reviews, experiment design, and data analysis for researchers.
1.2k upvotes
Tracked by Kanon since Sep 7, 2026
Status basis: npm_downloads_7d momentum fell to -153 per 3d from 24 (<= 40% of the prior window)
📈 Timelinewhat changed, and when
- Cooling npm_downloads_7d momentum fell to -153 per 3d from 24 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -101 per 3d from 30 (<= 40% of the prior window)
- Anomaly daily change -48.0 is -3.0 standard deviations from this entity's own prior mean (10.2±19.4, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to -54 per 3d from 30 (<= 40% of the prior window)
- Anomaly daily change -48.0 is -3.0 standard deviations from this entity's own prior mean (10.2±19.4, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to -20 per 3d from 18 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -44 per 3d from 54 (<= 40% of the prior window)
- Cooling npm_downloads_7d momentum fell to -44 per 3d from 54 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 18 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to -36 per 3d from 54 (<= 40% of the prior window)
- Accelerating npm_downloads_7d gained 54 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Accelerating npm_downloads_7d gained 54 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 107 (<= 40% of the prior window)
- Anomaly daily change 73.0 is 8.4 standard deviations from this entity's own prior mean (21.8±6.1, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 182 (<= 40% of the prior window)
- Anomaly daily change 73.0 is 8.4 standard deviations from this entity's own prior mean (21.8±6.1, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change 73.0 is 8.4 standard deviations from this entity's own prior mean (21.8±6.1, baseline excludes this point) — unusual, not necessarily adoption
- Cooling npm_downloads_7d momentum fell to 0 per 3d from 182 (<= 40% of the prior window)
- Anomaly daily change 73.0 is 8.4 standard deviations from this entity's own prior mean (21.8±6.1, baseline excludes this point) — unusual, not necessarily adoption
- Accelerating npm_downloads_7d gained 182 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- Anomaly daily change 73.0 is 8.4 standard deviations from this entity's own prior mean (21.8±6.1, baseline excludes this point) — unusual, not necessarily adoption
- Anomaly daily change 73.0 is 8.4 standard deviations from this entity's own prior mean (21.8±6.1, baseline excludes this point) — unusual, not necessarily adoption
- Accelerating npm_downloads_7d gained 182 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- first observed Kanon started keeping permanent history for this agent
🔎 Known / Unknown
14 of 23 fields unknown
| Machine-callable | — | unknown | — |
| Open source | 1 | verified | 1 quote(s) |
| Self-hostable | 1 | inferred | 1 quote(s) |
| Bring your own key | — | unknown | — |
| Autonomy level | — | unknown | — |
| Pricing model | — | unknown | — |
| Integrations | — | unknown | — |
“Unknown” means we have not verified it — it is not a “no”. Hard filters never treat unknown as false.
🤖 Agent teardown · research
Job to be doneAutomate literature reviews, experiment design, and data analysis to accelerate scientific research.
Who it is forResearchers, academic scientists, and AI research teams.
Prerequisitesopen source · self-hostable
PricingFree
Traction · why it is rising262 PH votes, indicating strong community interest and recognition.
Why it matters
As the first open-source AI research agent with multi-step reasoning and tool use, it represents a significant step toward autonomous scientific discovery.
Evidence quotesverbatim, from the product’s own materials
“public GitHub repository (README fetched)”— structural
“curl -fsSL https://feynman.is/install | bash”— readme
“Local models are supported through the setup flow.”— readme
Signal source: GitHub
Visit official site →
📛 Official badgefor your site / README
Building feynman? Pick a style above — the embed code updates live. Deep color control via URL params: bg= / fg= / accent= (hex). It links back to this page.
On mobile tap Share for WeChat / RED (Xiaohongshu) / X; on desktop use Copy text and paste into the app.
FAQ
What is feynman?
An open-source AI agent that autonomously handles literature reviews, experiment design, and data analysis for researchers.
What does feynman do?
Automate literature reviews, experiment design, and data analysis to accelerate scientific research.
Why does feynman matter?
As the first open-source AI research agent with multi-step reasoning and tool use, it represents a significant step toward autonomous scientific discovery.
How much does feynman cost?
Free
Is feynman free?
Yes — feynman has a free tier. Pricing as stated on its own page: Free
Is feynman open source?
Yes — feynman is open source.
Can I self-host feynman?
Yes — feynman can be self-hosted.
How popular is feynman?
As tracked by KanonAgent: 1.2k upvotes (first indexed 2026-09-07).
What are the best feynman alternatives?
Similar AI agents tracked by KanonAgent: Winninghunter, Stealth Venture, Hidden Business, ragflow, Dropkiller, RankAI.