Pinned Loading

1. undobench undobench Public

   UndoBench: Separating Task Competence from Recovery Capability in Tool-Using AI Agents

   Python 2

2. evoundo/evoundo evoundo/evoundo Public

   State recoverability, crash reconciliation, and selective undo for autonomous AI agents.

   Python 3

3. tdlabs-ai/tanml tdlabs-ai/tanml Public

   Automated validation toolkit for tabular ML models in finance and regulated domains.

   Python 9 1

4. ai-agents-zero-to-hero ai-agents-zero-to-hero Public

   Learn AI agents from first principles to production. Zero mandatory dependencies, pure standard Python 3.11+, and no magic frameworks.

   Python 17 4

5. research-agent research-agent Public

   Autonomous, local-first deep research agent with multi-source evidence synthesis, PDF upload, and executive web dashboard.

   Python 2 1

6. InvariantOne InvariantOne Public

   InvariantOne: High-Assurance Permutation-Equivariant Natural-Language Decision Model

   Python 2