AgentDish directory
human approval
Accepted listings with this tag.
| Listing | Category | Score | Trend | Checked | |
|---|---|---|---|---|---|
#115
→ 0
Phinq
Phinq is an open-source runtime governance layer for AI agents that intercepts tool calls, classifies risk, pauses irreversible actions for human approval, and records decisions in a tamper-evident audit log. |
Developer Tools / Code Assistant | 89 | → 0 | 32 days ago | Details |
#437
↓ -4
RiskKernel
Self-hosted runtime for putting hard budgets, approval gates, observability, and resumable checkpoints around AI agents. |
Developer Tools / AI Agent Infrastructure | 87 | ↓ -4 | 95 days ago | Details |
#610
↑ +2
MakerChecker
MakerChecker is a self-hosted governance layer for AI agents that enforces roles, approvals, and tamper-evident audit logs. The repo shows quickstart commands, a demo flow, and SDK/connectors for TypeScript, Python, and LangChain-style integrations. |
Developer Tools / AI Agent Governance | 86 | ↑ +2 | 86 days ago | Details |
#1151
↓ -3
e3d-pilot
A repo-improving agent harness that researches a codebase, proposes ideas, waits for human approval, and then drives execution with SHA-bound merge gating. |
Developer Tools / AI Agent Frameworks | 83 | ↓ -3 | 27 days ago | Details |