# Valkor

> The open-source AI command center for your company. Every agent, skill, and memory is a file in one versioned repo you own — a workforce of AI agents that does real work, shared across your whole team from Slack, Teams, the web, or the CLI. Self-hostable, any model, your keys.

Canonical site: https://beeuni.ai
Full corpus: https://beeuni.ai/llms-full.txt
Structured content index: https://beeuni.ai/api/ai

## Core pages
- [Valkor – The AI Command Center for Your Company](https://beeuni.ai/markdown/index.md): The open-source AI command center for your company. Every agent, skill, and memory is a file in one versioned repo you own — a workforce of AI agents that does real work, shared across your whole team from Slack, Teams, the web, or the CLI. Self-hostable, any model, your keys.
- [Valkor for developers](https://beeuni.ai/markdown/developers.md): Build, test, and ship software with Valkor's agent workspace.

## Documentation
- [Accounts & access](https://beeuni.ai/markdown/docs/accounts.md): An account holds your projects, your teammates, and one access model.
- [Valkor as a Backend](https://beeuni.ai/markdown/docs/backend.md): Start and manage Valkor sessions from your backend with explicit connector, model, context, and secret scope.
- [CLI](https://beeuni.ai/markdown/docs/cli.md): The valkor command line, its auth model, the dev loop, and every command.
- [Computer Tunnel](https://beeuni.ai/markdown/docs/connect/computers.md): Connect your machine through the permissioned Valkor Agent Tunnel.
- [Connectors](https://beeuni.ai/markdown/docs/connect/connectors.md): How connectors and connections give agents scoped access to external tools.
- [Connect & automate](https://beeuni.ai/markdown/docs/connect.md): Connectors, Slack, computers, and triggers reach outside a project.
- [Slack & channels](https://beeuni.ai/markdown/docs/connect/slack.md): Connect Slack to a project and control sessions from a channel.
- [Triggers](https://beeuni.ai/markdown/docs/connect/triggers.md): A trigger starts a session on a schedule, from a webhook, or from a monitor.
- [Apps](https://beeuni.ai/markdown/docs/feature-flags/apps.md): Deploy static sites, bundles, Dockerfiles, and OCI images to stable Valkor URLs.
- [Feature flags](https://beeuni.ai/markdown/docs/feature-flags.md): Turn a Valkor surface on for one project, and read what every flag gates.
- [Self-hosting architecture](https://beeuni.ai/markdown/docs/host/architecture.md): How the self-hosted Docker Compose stack fits together, on the box and off it.
- [Self-hosting](https://beeuni.ai/markdown/docs/host.md): Run your own Valkor instance with Docker Compose, on a VPS or for evaluation.
- [Valkor](https://beeuni.ai/markdown/docs/index.md): Valkor is the AI command center for your company.
- [Agents](https://beeuni.ai/markdown/docs/project/agents.md): An agent is a markdown file that OpenCode runs; the manifest only governs its access.
- [Your project](https://beeuni.ai/markdown/docs/project.md): A project is a git repository that holds your agent's config and state.
- [Legacy valkor.toml](https://beeuni.ai/markdown/docs/project/legacy-toml.md): Support status and the migration path from v1 valkor.toml to v2 valkor.yaml.
- [Manifest reference](https://beeuni.ai/markdown/docs/project/manifest.md): Every valkor.yaml v2 key, with defaults, limits, and validation rules.
- [Models](https://beeuni.ai/markdown/docs/project/models.md): How Valkor picks a model, and how billing works for managed vs. your-own-key models.
- [Secrets](https://beeuni.ai/markdown/docs/project/secrets.md): How Valkor stores project credentials, and how it controls whether agent code can read each value.
- [Quickstart](https://beeuni.ai/markdown/docs/quickstart.md): Install the CLI, run a session, and merge your first change request.
- [Apps](https://beeuni.ai/markdown/docs/sdk/apps.md): Create, deploy, and control Valkor Apps from the SDK and from React.
- [Authentication](https://beeuni.ai/markdown/docs/sdk/auth.md): Authenticate the SDK with a personal access token or a service account.
- [Full example](https://beeuni.ai/markdown/docs/sdk/example.md): One file that lists projects, starts a session, and streams a reply.
- [TypeScript SDK](https://beeuni.ai/markdown/docs/sdk.md): Install, authenticate, and send your first message with the typed SDK.
- [React hooks](https://beeuni.ai/markdown/docs/sdk/react.md): Run a Valkor session in React with the useSession hook.
- [SDK reference](https://beeuni.ai/markdown/docs/sdk/reference.md): The full @valkor/sdk API surface — client methods, modules, turns, and distribution.
- [Sessions](https://beeuni.ai/markdown/docs/sdk/sessions.md): Run a session, stream its events, and handle the errors it can throw.
- [Sign in with Valkor](https://beeuni.ai/markdown/docs/sdk/sign-in.md): Gate your own app behind Valkor identity with one route, and act as the signed-in user through the SDK.
- [Change requests](https://beeuni.ai/markdown/docs/work/change-requests.md): How session work reaches the default branch through review.
- [Running work](https://beeuni.ai/markdown/docs/work.md): How work moves from prompt to merged change, and the three ways it starts.
- [Runtime & sandbox](https://beeuni.ai/markdown/docs/work/runtime.md): Sandbox lifecycle, injected environment, token families, and the image a session boots from.
- [Sessions](https://beeuni.ai/markdown/docs/work/sessions.md): A session is a git branch and a sandbox where the agent works.