AI & Agents
Forecast AI
Last updated 2026-07-31 · benchmark measured 2026-08-09 — deterministic & reproducible
Open-source multi-agent AI infrastructure for prediction market forecasting and trade hand-off.
Is Forecast AI production-ready?
Legit.Show scores Forecast AI 59 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on Forecast AI (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Reliability; its weakest is Privacy. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — 46/100
- Accessibility — 96/100
- Security — 25/100
- Privacy — 25/100
- Reliability — 100/100
- Standards — 89/100
- Discoverability — 35/100
What we measured
- No Content-Security-Policy and no HSTS.
- Served over HTTPS with a valid certificate.
- Real Lighthouse performance run — 640 ms to first byte.
- Returns a proper 404 for unknown routes.
- 3 of 3 sampled routes reachable.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
Who built it
Ollie Grimes · product account @forecast_agents
Who it's for
Traders · AI developers · Prediction market participants · Robinhood users · Open-source enthusiasts
Pricing
Free and open-source (Apache 2.0 License)
Visit Forecast AI → · Alternatives to Forecast AI → · How this was measured →