# EvoForge

- **Event:** [Meta Global AI Developer Hackathon](https://cerebralvalley.ai/e/meta-ai-developer-hackathon)
- **When:** Oct 26, 12:00 PM – Nov 4, 9:00 PM (EST)
- **Where:** Online
- **Team:** [gunwoo kim](https://cerebralvalley.ai/u/hi_everyone)
- **GitHub:** https://github.com/itproanalysis/evoforge
- **Demo video:** https://github.com/itproanalysis/evoforge/releases/download/submission-evidence-2026-10-31/EvoForge_Evidence_Walkthrough.mp4
- **Gallery:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/207

EvoForge is a coding workspace that turns AI-written changes into results developers can inspect and verify. It addresses a practical problem: plausible code and a confident agent conversation are not evidence that a change works.

Muse Spark 1.3 is the principal Builder. GPT-6.1 Sol and Gemini 4 Argon provide independent implementation plans; Claude Opus 5.5 is the specification-first Critic. A separate Runner executes tests, PostgreSQL preserves scoped state and cost reservations, and Ed25519 certificates make recorded result bytes checkable. The workspace shows EvoForge and a single Spark call side by side, with model costs and disclosed allowances. Judges can try the server-funded defaults without entering API keys.

Live product: https://evoforge-web-230852112787.asia-northeast3.run.app/en
Recorded four-model run: https://evoforge-web-230852112787.asia-northeast3.run.app/en/share/job_306819b0b688
Verify: https://evoforge-web-230852112787.asia-northeast3.run.app/en/verify/job_306819b0b688

The recorded run passed 13/13 hidden checks in both lanes: a tie, not a superiority claim. Model API usage was 10 cents for EvoForge, 3 cents for the single call and 13 cents for the shared Judge; Runner compute is excluded. Separately, an earlier same-model, single-attempt experiment improved Spark from 22/36 to 35/36 tasks by changing only the patch harness, with non-overlapping 95% Wilson intervals. Historical measurements are not presented as results of the new four-model configuration.

Hackathon contributions include the deployed workspace, model orchestration, execution and evaluation paths, durable evidence and signed-proof workflow. Earlier design documents are background, not claimed as newly written implementation. The video is an edited, narrated walkthrough of recorded production evidence, not a live screen recording. Current limits: one shared project and a 20-run site-wide daily quota. Signatures authenticate certificate bytes; adversarial verifier hardening remains unfinished.

## More from Meta Global AI Developer Hackathon

- [PreFlight](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/204)
- [Take Two](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/205)
- [Causa](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/206)
- [Floodline](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/208)
- [ShopThread](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/209)
- [Zheng Zhang](https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/210)

---

Markdown version of https://cerebralvalley.ai/e/meta-ai-developer-hackathon/hackathon/gallery/207. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt