agent-custody
No liveness check has reached it yet; it has been in the index since 10 Oct 2026. How this is checked
agent-custody is an open-source developer tool for auditing and governing AI agent tool calls. It provides signed receipts, Cedar policy enforcement through an MCP gateway, tamper-evident logging, and a browser-based verification interface.
Inferred · not functionally tested
Overview
6 featuresPurpose: Proving what AI agents did and enforcing policies around their tool calls.
Inferred · not functionally tested
Audience: AI infrastructure and security developers
Inferred · not functionally tested
Functions: monitoring, agents
Inferred · not functionally tested
Interfaces: API: indicated (inferred, not tested) · MCP: indicated (inferred, not tested) · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)
Recorded constraints: pricing: open_source · license: Open Source · platforms: API, CLI, WEB · deployment: browser, cli, api_only, self_hosted
Constraint provenance is unknown; confirm requirements with the publisher.
Record sources: github.com. These links do not verify the individual claims.
In the AI security & guardrails space, agent-custody takes a focused approach. Inferred · not functionally tested: It focuses on proving what AI agents did and enforcing policies around their tool calls. Inferred · not functionally tested: agent-custody is an open-source project aimed at AI infrastructure and security developers. Basis unknown · not verified: The project is open source (Open Source). Basis unknown · not verified: It ships for the web, the command line, and API, and it can be self-hosted.
It is developed by svayatta. Inferred · not functionally tested: Among its 6 catalogued features are signed receipts, tool-call auditing, and cedar policies. Inferred · not functionally tested: Catalogued interfaces include an MCP server.
Summary written by a language model from the project’s public pages.
Tasks: Inferred · not functionally tested
- Signed receipts
- Tool-call auditing
- Cedar policies
- MCP gateway
- Tamper-evident logs
- Browser verifier
Topics: Inferred · not functionally tested
Built with & integrations
- multiple
- bLangChain in the HTML
Trust & compliance
Indexing history
1What PulseGate has recorded for this listing
- Indexed10 Oct · 12:03 UTCagent-custody seen via MCP Registry (official)Source: MCP Registry (official) · Open
Frequently asked questions about agent-custody
- What does agent-custody do?
- Inferred · not functionally tested: Agent-custody focuses on proving what AI agents did and enforcing policies around their tool calls. It is catalogued under AI security & guardrails on PulseGate.
- Who should use agent-custody?
- Inferred · not functionally tested: agent-custody is an open-source project built for AI infrastructure and security developers.
- Does agent-custody have a free plan?
- Basis unknown · not verified: Yes — agent-custody is open source under the Open Source license and free to use.
- What platforms does agent-custody run on?
- Basis unknown · not verified: agent-custody runs on the web, the command line, and API. It can also be self-hosted.
- Is agent-custody still maintained?
- Unverified. agent-custody has not been re-checked since it entered the index, so there is no finding either way — and only a positive finding would say otherwise.
- What projects are similar to agent-custody?
- Similar projects tracked by PulseGate include agent-audit-ledger, agentseal-gateframe, and agentgate.agent-audit-ledgeragentseal-gateframeagentgate
- Who develops agent-custody?
- agent-custody is developed by svayatta.
- Is agent-custody open source?
- Basis unknown · not verified: Yes — agent-custody is open source under the Open Source license.
Similar projects
Closest matches by what these projects do