Burrow – Runtime Security for AI Agents

Name: Burrow – Runtime Security for AI Agents
Availability: InStock
Author: saranshrana

by saranshrana·Apr 14, 2026·3 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidSolve My ProblemSlick

Natural language policies block risky agent actions before they execute.

Strengths

•5-layer detection stack with sub-30ms neural classification
•Works across 7 CLI frameworks and 13 SDK adapters out of box
•Policy enforcement in plain English, not complex rule syntax

Weaknesses

•AI agent security is getting crowded with emerging competitors
•Commercial pricing at $79/mo may limit adoption vs open-source alternatives

Post Description

We use Claude Code, Cursor, and Copilot daily. These tools run shell commands, read files, and call APIs on their own. When something goes wrong you find out after.

A .env file gets read, a secret ends up somewhere it should not, a command runs that nobody approved. EDR sees process spawns. Cloud audit logs see API calls. Neither understands that the agent's chain of actions together is credential theft.

Burrow sits between the agent and the machine. You define policies in plain language, like "block any agent from deleting production resources" or "alert if an agent reads AWS credentials and then sends data to an external endpoint." Burrow maps those policies against the actual tools, MCP servers, and plugins in your environment, then intercepts tool calls at the framework level before they execute. Risky calls get dropped. Everything else passes through.

Works with Claude Code, Cursor, Copilot, Windsurf, CrewAI, LangChain, LangGraph, and a few more. CLI and SDK install in under a minute. Free tier for individuals, paid for teams.

I ran infrastructure security at a large media company before this. Going full time on Burrow later this month. Happy to answer anything, especially the "does this actually work in production" question.

try - https://burrow.run