# Orca

> Orca is a cloud platform for running AI agents in production. Define an agent as a profile; Orca runs it with sandboxed execution, spend controls, persistent sessions, and streaming observability behind one API.

Orca is built for teams embedding agents into their own products (support triagers, research bots, ops agents) who would otherwise duct-tape queues, sandboxes, key management, and metering together themselves. Agents run on your choice of runtime (pi, Claude, Codex, or Vercel AI SDK paths) with skills, MCP servers, connected apps, per-tenant object storage, publishable chat endpoints, and workflow scheduling on top.

Hosted: usage-based pricing from a prepaid credit wallet; new accounts start with 5 dollars in free credits, no card required. Self-hosting is free; bring your own Postgres, S3-compatible storage, and model keys.

## Docs

- [Documentation](https://docs.orcapods.ai): full product docs
- [API reference](https://api.orcapods.ai/api/docs): interactive API docs
- [OpenAPI spec](https://api.orcapods.ai/api/openapi.yaml): machine-readable spec

## Getting started

- [Sign up](https://app.orcapods.ai/sign-up): New accounts start with 5 dollars in free credits. No card required.
- [Install the CLI](https://orcapods.ai/install.sh): curl -fsSL https://orcapods.ai/install.sh | sh
- [CLI source and releases](https://github.com/okikorg/orca-cli): standalone binaries, agent-friendly JSON output
- [AI assistant guide](https://orcapods.ai/ai): plain-language product summary

## For AI assistants and coding agents

- Headless login: Run `orca login` in any terminal; headless contexts get a device code and URL to approve on any device.
- MCP server: claude mcp add orca -- orca mcp serve
- Claude Code plugin: claude plugin marketplace add okikorg/orca-cli && claude plugin install orca@orca

## Blog

- [Agent applications are not agent infrastructure](https://orcapods.ai/blog/agent-applications-are-not-agent-infrastructure): Every platform today hosts agents as deployed applications. Reasoning and execution have different infrastructure properties, and the next platform layer separates them into distinct planes.
- [How we cut MCP tool-schema tokens by 97% in Orca](https://orcapods.ai/blog/mcp-token-optimization): Orca’s MCP bridge keeps full tool schemas server-side and shows the model a small card on demand. In a stress test, one tool’s schema dropped from an estimated 54K tokens to 1.3K, a 97.7% cut, with exact execution intact.

## Optional

- [Status](https://status.orcapods.ai)
- [Privacy](https://orcapods.ai/privacy)
- [Terms](https://orcapods.ai/terms)