Highlights
Pinned Loading
-
general-liquidity/sharpebench
general-liquidity/sharpebench PublicSharpeBench is the luck-robust benchmark for AI trading agents, which ranks risk-adjusted skill that survives deflation, not raw return. The SWE-bench moment for capital markets.
Rust 2
-
harnesscad
harnesscad PublicThe verifier-first text-to-CAD agent harness, with a CUA for 3D CAD generation in real GUIs and Parts-Driven Development.
Python
-
gamengen-v2
gamengen-v2 PublicGameNGen v2 is a research implementation of an action-conditioned neural game engine using diffusion models and ViZDoom for real-time playable world simulation.
Python 1
-
theoremata
theoremata PublicThe verification-first agentic math harness: falsify before proving, kernel-recheck every proof across six proof assistants, and emit certificates a separate checker can re-verify offline.
Python 1
If the problem persists, check the GitHub status page or contact support.

