> ## Documentation Index
> Fetch the complete documentation index at: https://docs.caveman.so/llms.txt
> Use this file to discover all available pages before exploring further.

# Caveman Cloud: Managed LLM Gateway for AI Workloads

> Caveman Cloud is a managed LLM gateway with workload telemetry, evals, and improvement tooling that proves savings with labeled evidence before shipping.

Caveman Cloud is a managed LLM gateway plus workload telemetry, evaluation, and improvement tooling built for teams running AI agents and LLM traffic at scale. It connects request-level usage to workload-level decisions so you can understand costs, prove improvements, and deploy changes with evidence.

Caveman Cloud is self-driving software for your LLM stack. Built-in agents observe your traffic, evaluate candidate changes, prove them with evidence, and propose improvements. You stay in control and approve what ships. The loop runs continuously: **Observe, Diagnose, Generate, Evaluate, Deploy, Learn**.

What sets Caveman apart is that it proves its own claims. Every number carries a label (measured, inferred, tested, or verified), changes ship only after they clear eval gates, the default path is byte-safe, and verified savings start at an honest \$0. Read [Why Caveman](/why-caveman) for the full picture.

## Choose your path

<CardGroup cols={3}>
  <Card title="Developers" icon="code" href="/solutions/developers">
    Integrate in one line, label traffic, control optimizations per request, and debug with traces, SQL, and evals.
  </Card>

  <Card title="CTOs and Platform Leads" icon="sitemap" href="/solutions/engineering-leaders">
    Govern AI spend across teams, agents, and coding tools with eval-gated rollouts, RBAC, and audit.
  </Card>

  <Card title="CFOs and Finance" icon="chart-line" href="/solutions/finance">
    Understand what each number means, which savings are verified, and how to report them with confidence.
  </Card>
</CardGroup>

<CardGroup cols={3}>
  <Card title="30-Day Adoption Playbook" icon="calendar-check" href="/solutions/adoption-playbook">
    Connect, diagnose, prove, and report in four weeks.
  </Card>

  <Card title="Security Review" icon="shield-halved" href="/solutions/security-review">
    Hosting, encryption, key custody, tenant isolation, and data policy.
  </Card>

  <Card title="Deployment Options" icon="server" href="/solutions/deployment-options">
    Hosted Cloud, your own VPC, on-prem, or local-only tools.
  </Card>
</CardGroup>

## Let AI drive

<CardGroup cols={2}>
  <Card title="Connect Your Coding Agent" icon="robot" href="/guides/connect-coding-agent">
    Give Claude Code, Codex, or Cursor access to your project over MCP.
  </Card>

  <Card title="Automated AI Setup" icon="wand-magic-sparkles" href="/guides/ai-setup">
    Paste one prompt and let your coding agent wire up the gateway, evals, and baseline.
  </Card>

  <Card title="Built-in AI" icon="sparkles" href="/concepts/built-in-ai">
    See how Ask Caveman, Improvements, judges, and rollouts work together.
  </Card>

  <Card title="Improvements" icon="arrows-rotate" href="/guides/improvements">
    Review agent-generated changes backed by Evidence reports before they ship.
  </Card>
</CardGroup>

## Get started

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/quickstart">
    Send your first request through the Gateway and see it in Traces within minutes.
  </Card>

  <Card title="Connect a Workload" icon="plug" href="/guides/connect-workload">
    Route agent or application traffic with a base-URL swap and two headers.
  </Card>

  <Card title="How It Works" icon="book-open" href="/concepts/how-it-works">
    Understand the Observe to Learn loop and how Caveman Cloud handles your traffic.
  </Card>

  <Card title="OpenAI Integration" icon="code" href="/integrations/openai">
    Point the OpenAI SDK (TypeScript or Python) at the managed gateway.
  </Card>

  <Card title="TypeScript SDK" icon="brackets-angle" href="/sdks/typescript">
    Trace workflows, search tools, and export telemetry from your application.
  </Card>

  <Card title="CLI" icon="terminal" href="/cli/cvm">
    Query traces, run SQL, and operate the control plane from the terminal.
  </Card>
</CardGroup>

## Onboarding

<Steps>
  <Step title="Sign in to the console">
    Open your Caveman Cloud console and sign in. If you were invited to a project, you land directly in that workspace.
  </Step>

  <Step title="Create a project and API key">
    Go to **Gateway, Connect** to create a project, then generate a Cave API key. Copy the key and your gateway URL. The gateway URL has no trailing slash.
  </Step>

  <Step title="Set environment variables">
    Export `CAVE_API_KEY` with your Cave key and `CAVE_GATEWAY_URL` with your gateway origin. Keep your upstream provider key separate.
  </Step>

  <Step title="Swap the base URL">
    Change the `baseURL` on your OpenAI or Anthropic client to `${CAVE_GATEWAY_URL}/openai/v1` or the matching provider path. Add the `x-cave-upstream-key` header when the provider key is not stored in Caveman Cloud.
  </Step>

  <Step title="Send a request and view the trace">
    Run one chat completion or agent turn. Open **Traces** in the console to inspect the request, model, usage, and latency.
  </Step>
</Steps>

## Core surfaces

| Surface | What you do with it |
| - | - |
| Gateway | Route traffic, apply optimizations per request, and record usage with provider-compatible endpoints. |
| Traces | Inspect every request, its cost, latency, and outcome. Search by agent, workflow, model, and time. |
| Workloads | Register and observe the agents and applications sending traffic to your project. |
| Improvements | Run improvement attempts against recorded traffic, evaluate changes with test cases, and review Evidence reports. |
| Ask Caveman | Investigate traces and workloads with an agent-assisted conversational interface. |
| Automation | Configure monitors and rules that watch traffic and surface decisions in the Inbox. |
| Inbox | Review what Caveman noticed, what it did, and what needs your decision across every subsystem. |
| SQL | Run read-only ClickHouse SELECT over your project's requests, spans, tool events, evals, and logs. |

## Savings evidence

Caveman Cloud reports three kinds of numbers, and it keeps them separate:

* **Measured spend** records observed usage and its pricing basis.
* **Inferred savings** describe an estimate or counterfactual, not a guaranteed invoice reduction.
* **Verified savings** require a supported accounting method and qualifying evidence. They stay zero when that evidence is absent.

See [Savings Evidence](/concepts/savings-evidence) for the full contract, [Optimization Catalog](/concepts/optimizations) for what each optimization changes, and [Reporting Savings](/solutions/reporting-savings) for turning these numbers into a monthly finance report.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.