aDragon0707 / sacp
State-Aware Collaboration Protocol: auditable work receipts for AI agents.
Why this job: works in the areas we cover, but does not say which job it does
What it does
SACP (Scalable Audit and Control Protocol) makes completion conditions explicit: what the agent claims, which evidence supports it, what an external system reports, and who authorizes the next action. Its Python reference engine derives a verdict that a domain gate uses to allow or block continuation.
Get started
python -m sacp_harness- Maintenance
- Active
- Last commit 26 days ago
- Stars
- 106
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.1-alpha
- Released 6 months ago
- Built with
- Python
- 89% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- None
- No issues filed
- Pull requests
- 23 merged
- 0 waiting
- Releases
- 1
- 1 in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| larksuite / aamp | 124 | 3 months ago | MIT | No downloads |
| pilot-protocol / pilotprotocol | 148 | yesterday | AGPL-3.0 | Mac, Linux |
More: languages, topics and project record
Languages
- Python 89%
- HTML 11%
Topics
- agentops
- ai-agents
- ai-safety
- benchmark
- handoff
- llm
- protocol
- receipts
- ai-workflows
- agent-protocol
- human-in-the-loop
- audit-trail
Project record
- JobOther AI tools
- StatusListed
- Commits35
- Forks1
- Watching0
- Stars in 28 days+15
- CreatedMay 8, 2026
- First seen by usNov 7, 2026
- CheckedNov 10, 2026