NullRun is the runtime policy engine for AI agents. Drop in a one-line decorator, set a budget, and govern cost, tool use, and workflow state before a runaway agent turns into an incident.

• Stop runaway costs. Hard budget policies stop a workflow at the cap. Soft policies can allow a bounded overdraft for an active chain, up to the configured overdraft limit.
• Catch loops and retry storms. Repeated tool calls and retry storms are detected during a run so the gate can block or flag them before the API bill does the talking.
• Control from the dashboard. Pause or kill a workflow through the WebSocket control plane. If the socket is unavailable, the SDK falls back to HTTP polling; signals are applied at the next gate or yield boundary, typically within about a second.
• Govern sensitive tools safely. Database writes, shell, file deletes, and external actions can be blocked by ToolBlock policies or routed through human approval, with a full audit trail.

• 🟢 nullrun.io — managed control plane and dashboard in one place. Start with the Lite plan, no credit card.
• 🐍 pip install nullrun — Python SDK with one-line instrumentation for OpenAI, Anthropic, OpenAI Agents, LangGraph, LangChain, LlamaIndex, CrewAI, AutoGen, Mistral, Gemini, Cohere, and AWS Bedrock. Pass your nr_live_... API key to init() to start tracking and enforcing policy.
• 📖 docs.nullrun.io — install, quickstart, concepts, and recipes.

• nullrun-sdk-python — the Python SDK (pip install nullrun).
• nullrun-docs — the documentation site.
• nullrun-examples — copy-paste-runnable examples for the most common agent frameworks.

• 🐛 Bug or feature? Open an issue in the relevant repo.
• 🔒 Security? See SECURITY.md — please don't file public issues.
• 💬 General questions: Discord is the fastest channel.
• ✉️ Email support: support@nullrun.io.