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

# FAQ

> Frequently asked questions about klaw

## General

<AccordionGroup>
  <Accordion icon="circle-question" title="What is klaw?">
    klaw is enterprise AI agent orchestration — like kubectl, but for AI agents.

    ```bash theme={null}
    klaw get agents          # List all agents
    klaw describe agent      # Inspect an agent
    klaw logs agent          # View logs
    klaw cron create         # Schedule tasks
    ```

    If you know kubectl, you already know klaw.
  </Accordion>

  <Accordion icon="circle-question" title="Why 'kubectl for AI Agents'?">
    Because the operational challenges are identical:

    | Challenge                   | Kubernetes         | klaw               |
    | --------------------------- | ------------------ | ------------------ |
    | Where does my workload run? | Scheduler → Nodes  | Dispatcher → Nodes |
    | How do I isolate workloads? | Namespaces         | Namespaces         |
    | How do I configure them?    | ConfigMaps/Secrets | Config/Secrets     |
    | How do I monitor them?      | `kubectl logs`     | `klaw logs`        |
    | How do I schedule work?     | CronJob            | `klaw cron`        |

    Kubernetes solved this for containers. klaw solves it for AI agents.
  </Accordion>

  <Accordion icon="circle-question" title="Who is klaw for?">
    Enterprises running AI agents in production. If you have multiple agents doing different jobs (lead scoring, competitor monitoring, support automation, report generation) and need:

    * Visibility into what agents are doing
    * Isolation between teams
    * Scheduling and automation
    * Easy scaling

    klaw is for you.
  </Accordion>

  <Accordion icon="circle-question" title="Is klaw production-ready?">
    klaw is in public beta. It's being used in production by early adopters. Expect some rough edges before 1.0.
  </Accordion>
</AccordionGroup>

## Comparison

<AccordionGroup>
  <Accordion icon="circle-question" title="How is klaw different from OpenClaw?">
    OpenClaw is powerful but complex:

    * Node.js + multiple services
    * Difficult deployment
    * Hard to scale

    klaw is a single Go binary with:

    * Same agent capabilities
    * kubectl-style operations
    * Deploy in seconds
    * Scale by adding nodes

    Think of klaw as "OpenClaw, but simple."
  </Accordion>

  <Accordion icon="circle-question" title="How is klaw different from LangChain/CrewAI?">
    Those are **frameworks for building agents** — they help you chain LLM calls together.

    klaw is **infrastructure for operating agents** — it helps you deploy, schedule, monitor, and scale those agents in production.

    You could build agents with LangChain and deploy them on klaw.
  </Accordion>

  <Accordion icon="circle-question" title="How is klaw different from Google ADK?">
    ADK provides abstractions for building agents. klaw provides the runtime and control plane for running them. Different layers of the stack.
  </Accordion>

  <Accordion icon="circle-question" title="How is klaw different from Claude Code?">
    Claude Code is a single-user interactive coding assistant.

    klaw is multi-agent orchestration for enterprises — multiple agents, multiple teams, namespaces, scheduling, Slack control, distributed mode.
  </Accordion>
</AccordionGroup>

## Technical

<AccordionGroup>
  <Accordion icon="circle-question" title="What LLM providers are supported?">
    300+ models via:

    * **each::labs Router** — single API for all models
    * **OpenRouter** — multi-provider gateway
    * **Direct providers** — Anthropic, OpenAI, Google, Azure
    * **Local models** — Ollama, any OpenAI-compatible endpoint
  </Accordion>

  <Accordion icon="circle-question" title="Is this about sandboxing agents?">
    **Partial.** Namespaces provide *logical* isolation:

    * **Scoped secrets** — sales can't access support's API keys
    * **Tool permissions** — agents only get the tools you allow
    * **Resource isolation** — each namespace is independent

    **However:** Non-containerized agents have **no filesystem sandboxing**. They run under your user account and can access any file you can.

    **For true sandboxing, use Podman containers:**

    ```bash theme={null}
    klaw run myagent --task "..."
    ```

    Containers provide process isolation, filesystem restrictions, and network controls.
  </Accordion>

  <Accordion icon="circle-question" title="Can I run klaw on-prem?">
    Yes. Single binary, no external dependencies. Run on your servers, your VPC, air-gapped environments. You control everything.
  </Accordion>

  <Accordion icon="circle-question" title="How does distributed mode work?">
    1. Start a controller on one machine
    2. Worker nodes join the cluster
    3. Tasks are automatically dispatched to available nodes

    ```bash theme={null}
    # Controller
    klaw controller start --port 9090

    # Workers
    klaw node join controller:9090 --token $TOKEN

    # Dispatch
    klaw dispatch "analyze leads" --agent lead-scorer
    ```
  </Accordion>

  <Accordion icon="circle-question" title="Do I need Docker or Kubernetes?">
    No. klaw is a single binary with no external dependencies. You can optionally use Podman for containerized agents, but it's not required.
  </Accordion>
</AccordionGroup>

## Usage

<AccordionGroup>
  <Accordion icon="circle-question" title="What's the difference between `klaw chat` and `klaw start`?">
    * `klaw chat`: Interactive CLI session for one user
    * `klaw start`: Full platform with Slack integration, cron scheduler, and multi-user support
  </Accordion>

  <Accordion icon="circle-question" title="How do I control agents from Slack?">
    1. Set up Slack bot and app tokens
    2. Run `klaw start`
    3. Use `@klaw` in Slack

    ```
    @klaw status              # List agents
    @klaw run lead-scorer     # Trigger agent
    @klaw logs ticket-handler # View logs
    ```

    See [Slack Integration Guide](/docs/guides/slack-integration) for full setup.
  </Accordion>

  <Accordion icon="circle-question" title="Can I schedule recurring tasks?">
    Yes. Use the cron system:

    ```bash theme={null}
    klaw cron create daily-report \
      --schedule "0 9 * * *" \
      --agent reporter \
      --task "Generate daily status report"
    ```
  </Accordion>

  <Accordion icon="circle-question" title="How do agents communicate with each other?">
    Agents can spawn sub-agents using the `agent_spawn` tool, share context through workspace files, or communicate via Slack channels in team deployments.
  </Accordion>
</AccordionGroup>

## Deployment

<AccordionGroup>
  <Accordion icon="circle-question" title="What are the system requirements?">
    * Any 64-bit Linux, macOS, or Windows
    * \~20MB disk space for the binary
    * Internet access for LLM API calls (unless using local models)

    That's it. No runtime dependencies.
  </Accordion>

  <Accordion icon="circle-question" title="How do I update klaw?">
    ```bash theme={null}
    curl -fsSL https://klaw.sh/install.sh | sh
    ```

    The installer always gets the latest version.
  </Accordion>

  <Accordion icon="circle-question" title="Can I run klaw in containers?">
    Yes. klaw supports running agents in isolated Podman containers:

    ```bash theme={null}
    klaw build
    klaw run myagent --task "..."
    ```
  </Accordion>

  <Accordion icon="circle-question" title="What's the difference between clusters and namespaces?">
    * **Cluster**: Top-level isolation (per organization)
    * **Namespace**: Sub-division within a cluster (per team/project)

    Similar to Kubernetes: namespaces provide logical isolation within a cluster.
  </Accordion>
</AccordionGroup>

## Security

<AccordionGroup>
  <Accordion icon="circle-question" title="Are my API keys secure?">
    API keys are stored in environment variables or config files. They're never sent to klaw servers—all LLM calls go directly to the provider.
  </Accordion>

  <Accordion icon="circle-question" title="What can agents access on my system?">
    **Important:** Non-containerized agents run under the same user as the klaw process with **no filesystem restrictions**. They can access any file your user can access (including `~/.ssh`, `~/.aws`, etc.).

    By default, agents can:

    * Read/write **any files** your user can access
    * Execute bash commands with your user's permissions
    * Make web requests

    **For filesystem isolation, run agents in Podman containers:**

    ```bash theme={null}
    klaw run myagent --task "..."
    ```

    Containers provide actual sandboxing. Non-containerized agents should be treated like any process running under your user account.
  </Accordion>

  <Accordion icon="circle-question" title="How do I restrict agent permissions?">
    Configure namespaces in `~/.klaw/config.toml`:

    ```toml theme={null}
    [namespace.sales]
    secrets = ["HUBSPOT_KEY"]
    allowed_tools = ["hubspot", "web_search"]

    [namespace.support]
    secrets = ["ZENDESK_KEY"]
    allowed_tools = ["zendesk", "slack"]
    ```
  </Accordion>
</AccordionGroup>

## Licensing

<AccordionGroup>
  <Accordion icon="circle-question" title="Is klaw open source?">
    klaw is source-available under the each::labs License.

    **Free** for:

    * Internal business use
    * Personal projects
    * Consulting and professional services

    **License required** for:

    * Multi-tenant SaaS offerings
    * White-label/OEM distribution
  </Accordion>

  <Accordion icon="circle-question" title="How do I get an enterprise license?">
    Contact [enterprise@eachlabs.ai](mailto:enterprise@eachlabs.ai)
  </Accordion>
</AccordionGroup>

## Contributing

<AccordionGroup>
  <Accordion icon="circle-question" title="How can I contribute?">
    See [CONTRIBUTING.md](https://github.com/klawsh/klaw.sh/blob/main/CONTRIBUTING.md). Contributions welcome for:

    * Bug fixes
    * New features
    * Documentation
    * Tools and skills
  </Accordion>

  <Accordion icon="circle-question" title="Where do I report bugs?">
    [GitHub Issues](https://github.com/klawsh/klaw.sh/issues)

    Include:

    * klaw version (`klaw version`)
    * OS and architecture
    * Steps to reproduce
    * Relevant logs
  </Accordion>
</AccordionGroup>