Pinned Loading

1. pipelock pipelock Public

   Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action …

   Go 826 95

2. agent-egress-bench agent-egress-bench Public

   Open Apache-2.0 corpus, runner, scoring, and result-verification contracts for measuring AI-agent egress controls. A PipeLab open project.

   Go 16 2

3. pipelock-rules pipelock-rules Public

   Official community detection rules for Pipelock - the open-source agent firewall

   Python 3

4. agent-evidence-levels agent-evidence-levels Public

   Agent Evidence Level (AEL): an open standard for grading AI-agent audit evidence by what an independent party can verify, with a reference checker and conformance corpus. Maintained by PipeLab; gov…

   Go 1 1

5. pipelock-verify-python pipelock-verify-python Public

   Python verifier for Pipelock action receipts (Ed25519-signed, chain-linked)

   Python 2

6. pipelock-agent-egress-action pipelock-agent-egress-action Public

   GitHub Action for running agent-driven CI jobs through Pipelock with verifiable egress evidence.

   Shell 1