by openguardrails · Codex 技能 · ★ 338
OpenThomas An open-source Bayesian trading worker for prediction markets, named after Thomas Bayes. v0 scope: forecast 2026 World Cup match moneyline markets on Polymarket with statistical priors (Elo → Poisson), de-vigged market prices, and a transparent blend — then keep every belief on an append-only ledger and work as a forecaster on a WorkPnP pool. Trade decisions are computed dry-run only. Hard limits in v0 (by design, see §6): No LLM calls. Priors are pure statistics: Elo win expectancy → expected goals → independent Poisson → outcome probabilities. No private keys, no real orders.
| Stars | 338 |
| Forks | 49 |
| Language | TypeScript |
| Category | Codex 技能 |
| Quality Score | 66.9196476878015/100 |
| Last Updated | 2026-04-19 |
| Created | 2025-10-22 |
| Platforms | node |
| Est. Tokens | ~677k |
These tools work well together with thomas-security for enhanced workflows:
Explore other popular codex 技能 tools:
thomas-security is Security checkups and red-team tests for AI agents.. It is categorized as a Codex 技能 with 338 GitHub stars.
thomas-security is primarily written in TypeScript. It covers topics such as ai-agent-security, ai-gateway, ai-security-gateway.
You can find installation instructions and usage details in the thomas-security GitHub repository at github.com/openguardrails/thomas-security. The project has 338 stars and 49 forks, indicating an active community.