GitHub repo leaderboard by stars, growth rate and activity.
Reference architecture for AI agents that propose actions but cannot authorize them — immutable intent capture, an independent Decionis policy verdict (ALLOW/ESCALATE/BLOCK), verified human approval, and a SafeExecutor that consumes a single-use intent-bound grant.
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | Reference architecture for AI agents that propose actions but cannot authorize them — immutable intent capture, an independent Decionis policy verdict (ALLOW/ESCALATE/BLOCK), verified human approval, and a SafeExecutor that consumes a single-use intent-bound grant. | TypeScript | 532 | last pushed 8 hours ago |
All · 11,658