AI agents
Instructions, permissions and limits for agents that work on servers.
An AI agent that edits code or runs commands works best with clear boundaries: what it may touch, which commands need approval and how much compute it may use. This category is where tools that write those boundaries down are listed.
The output is plain files you review and keep in your repository. Nothing here connects to an agent or to a server for you.
A path through this category
- Describe the project
Write down the stack, the commands and the rules an agent needs to follow.
- Set the limits
Decide which actions are allowed, which need approval and which are off limits.
- Hand it over
Give the agent the files and keep them next to the code they describe.
Tools in this category
- Agent Permissions GeneratorChoose an agent and a preset and get its permission file with strict defaults: what the agent may do on its own, what it must ask, and what it may never do. Written in your browser, with the tool version and documentation it follows.Open the tool
- Agent Infra Risk AssessmentAnswer twelve questions about where your AI agent runs and what it can reach, and get findings by severity, each with a recommendation and the source behind it. Scored in your browser; your answers stay in the link.Open the tool
- AGENTS.md generatorDescribe your project and get an AGENTS.md that Codex, Cursor, GitHub Copilot, Claude Code and other coding agents read, with a CLAUDE.md that imports it if you want one. Every section comes from what you write, and nothing leaves your browser.Open the tool
- MCP Server Deploy KitDescribe your MCP server and get the files to run it on a VPS behind a TLS proxy that streams and checks a bearer token: Compose, Dockerfile, proxy configuration, .env.example and a runbook. Written in your browser; no token is ever written.Open the tool
Background: Compute for AI agents