oleg-vdv/kepil
by Various
Accountability layer for AI agents: passport, mandate, action gateway, tamper-evident journal — and undo
MCP
oleg-vdv/kepil
Added 21 Sept 2026
Overview
Kepil is an accountability layer for AI agents. It provides a passport, mandate, action gateway, tamper-evident journal, and undo functionality. Written in Python, it helps track and control agent actions.
Best for
Best for
Developers building accountable AI agent systems
Use cases
- Enforce action permissions for AI agents
- Maintain tamper-evident audit logs
- Enable undo of agent actions
How to use
Install
npx proofbyte-agent-trace verify data/journal.jsonl Notes
Kepil is an accountability layer for AI agents. It provides a passport, mandate, action gateway, tamper-evident journal, and undo functionality. Written in Python, it helps track and control agent actions.
3 stars on GitHub. Last updated 2026-09-20. Licensed AGPL-3.0.
Use cases
- Enforce action permissions for AI agents
- Maintain tamper-evident audit logs
- Enable undo of agent actions
Pros
- Provides structured accountability with passport and mandate
- Includes tamper-evident journaling
- Offers undo capability for agent actions
Cons
- Low adoption with only 3 stars
- Python only, limiting cross-language use
- Vendor is various, suggesting no dedicated support
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Provides structured accountability with passport and mandate
- Includes tamper-evident journaling
- Offers undo capability for agent actions
Cons
- Low adoption with only 3 stars
- Python only, limiting cross-language use
- Vendor is various, suggesting no dedicated support
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
