My team built a Jiminy Cricket for AI coding agents
Summary
Fence is an open-source tool that prevents AI coding agents from deleting files or leaking API keys, currently functional with Claude Code.
Similar Articles
I built an OpenAI compatible firewall for AI agents. Try to break it.
Arc Gate is an OpenAI-compatible firewall that tracks authority across entire AI agent sessions, escalating from allow to block before tool calls execute. It is available as a live demo and open-source on GitHub.
AI agents still suck, so I built my own
The author built a custom AI agent application wrapping Claude Code and upcoming Codex support, focusing on composable workflows and seeking community feedback.
I built an open-source middleware to stop AI agents from exceeding spend/policy limits — v0.2 is now out
ActionFence is an open-source middleware that enforces spend caps, policy limits, and security checks for AI agents and MCP servers, with v0.2 adding rolling-window caps, circuit breaker, and schema drift detection.
We built an open-source authorization gate because our AI agent kept going rogue
The team released an open-source authorization gate to prevent AI agents from behaving unexpectedly or maliciously.
Is there any tool that clearly checks whether an AI coding agent stayed inside the task I gave it?
The author describes the problem of AI coding agents making unauthorized changes outside their approved task and introduces their local tool Ripple, which detects such boundary violations and suggests actions like continue, repair, or human review.