maat-benchmarks — tool profile and history
Runtime governance for agentic AI: Maat validates every agent-to-agent handoff against versioned business contracts, inline and deterministically with no model in the verdict path. Produces reproducible decision logs for audit. Benchmarks across six regulated-domain multi-agent workflows.
- Language
- Python
- Created
- Last activity
- Topics
- agent-reliability
- agent-to-agent
- agentic-ai
- agentic-workflow
- agents
- ai-agents
- ai-governance
- ai-safety
- ai-safety-research
- deterministic-ai
- fleet
- guardrails
- handoff
- llm
- multi-agent-systems
- payload
Current measurement
0GitHub starsstable
measured growthMomentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.
Reading history
| Date | Value | Metric |
|---|---|---|
| 0 | GitHub stars | |
| 0 | GitHub stars | |
| 0 | GitHub stars | |
| 0 | GitHub stars | |
| 0 | GitHub stars | |
| 0 | GitHub stars | |
| 0 | GitHub stars | |
| 0 | GitHub stars | |
| 0 | GitHub stars | |
| 0 | GitHub stars | |
| 0 | GitHub stars | |
| 0 | GitHub stars | |
| 0 | GitHub stars | |
| 0 | GitHub stars | |
| 0 | GitHub stars | |
| 0 | GitHub stars | |
| 0 | GitHub stars | |
| 0 | GitHub stars |
Classifications
- Domains
- Type
- Agents
- Use cases
- No declared use case
Neighbouring tools
These entries declare the same topics. No similarity is inferred: only the shared topics are stated.