himanshu748/AgentBench
Fail the build when your AI prompt regresses. Behavior tests across models via MeshAPI.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| suite | Path to the suite YAML in your repo (or a built-in suite id) | yes | — |
| models | Comma-separated MeshAPI model ids | yes | — |
| url | AgentBench server URL | no | https://agentbench-three.vercel.app |
Outputs
no outputs