Pinned Loading

1. doombot doombot Public

   Experimental Discord agent project for autonomous interaction and narrative-style response generation.

   Python

2. frontier-ai-risk-pomg-dsd frontier-ai-risk-pomg-dsd Public

   Working paper codebase and artifact bundle for a systems-dynamics and POMG-DSD framework for frontier AI risk.

   Python

3. SafeData SafeData Public

   Auditable training-data safety filtering stack for toxicity, PII, bias, poisoning, and robustness evaluation.

   Python

4. orchestrator orchestrator Public

   Multi-agent orchestration and reliability research stack with DAG scheduling, async execution, critic evaluation, and trajectory analysis.

5. Horizon-Eval Horizon-Eval Public

   Horizon-Eval: evaluation-integrity framework for portable long-horizon agent benchmarks, with QA gates, trajectory auditing, replayable run bundles, and safety-gap analysis.

   Python

6. qualia-lab qualia-lab Public

   Behavioral evaluation framework for sentience-, emotion-, and welfare-related AI claims, with anti-sandbagging analysis.

   Python