> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.panicly.lol/llms.txt.
> For full documentation content, see https://docs.panicly.lol/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.panicly.lol/_mcp/server.

# What is Panicly?

Panicly sits between your application and upstream AI providers. It authenticates project traffic, evaluates policy, records the decision, and forwards only approved requests.

Panicly is a gateway and control layer that enforces policy before provider spend happens.

Requests pass through authentication, quota, and policy checks before reaching OpenAI, Anthropic, or OpenRouter.

The dashboard centers request decisions, Workspace Audit, usage, credits, and forensics.

Sentry Mode gives operators a direct kill switch for protected project traffic.

## What Panicly is not

The product notes distinguish Panicly from OpenRouter: Panicly is about protection, limits, policy, evidence, and spend control. OpenRouter is about model discovery and routing breadth.

Panicly can forward to provider-compatible endpoints, but its primary value is not "more models." Its value is making model traffic controllable.

## Core product story

<img src="https://files.buildwithfern.com/panicly.docs.buildwithfern.com/2cbb4d993df88b2321c69f9bfe62c50831daf81fcc465090242979a697927ac4/docs/assets/panicly-flow.svg" alt="Panicly request flow from client app to gateway, controls, provider, and evidence ledger" />

The public story should stay grounded in five claims:

* Requests are authenticated with a Panicly project key.
* Rules and plan state are checked before provider forwarding.
* Only approved traffic reaches the upstream provider.
* Decision metadata is logged for later inspection.
* Provider credentials are stored as encrypted project secrets.

Prefer concrete operator language: request evidence, control layer, Sentry Mode, Network Controls, Region Rules, Usage, Credits, and Workspace Audit.

## Where to go next

Create a project, connect a provider, generate a Panicly key, and route a first call.

See the full request lifecycle from key authentication through policy and logging.