luckyPipewrench/pipelock
Firewall for AI agents. DLP scanning, SSRF protection, bidirectional MCP scanning, tool poisoning detection, and workspace integrity monitoring.
Operates as a proxy middleware implementing capability separation—the agent process is network-isolated while Pipelock (holding no secrets) inspects all outbound traffic through an 11-layer scanner. Supports three proxy modes (fetch, forward, WebSocket) deployable zero-code via environment variables or container networking policies. Integrates with Claude Code, OpenAI Agents SDK, AutoGen, CrewAI, and LangGraph through standard HTTP/MCP transports, with Ed25519-signed community rule bundles for extensible detection patterns.
217 stars.
Stars
217
Forks
14
Language
Go
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/luckyPipewrench/pipelock"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Featured in
Higher-rated alternatives
microsoft/agent-governance-toolkit
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and...
ucsandman/DashClaw
🛡️Decision infrastructure for AI agents. Intercept actions, enforce guard policies, require...
mattijsmoens/sovereign-shield
AI security framework: tamper-proof action auditing, prompt injection firewall, ethical...
vstorm-co/pydantic-ai-middleware
Middleware layer for Pydantic AI — intercept, transform & guard agent calls with 7 lifecycle...
Dicklesworthstone/destructive_command_guard
The Destructive Command Guard (dcg) is for blocking dangerous git and shell commands from being...