Build on CRHQ

Use a CRHQ instance as your product's agent runtime — sessions, agents, skills and streaming through a scoped API.

CRHQ isn't only an operator console — it's an agent runtime your product can build on. If your app needs AI agents that hold long conversations, execute skills, delegate work and stream output, you can drive a CRHQ instance through its API instead of building that machinery yourself.

What you get for free

CapabilityWhat it means for your product
SessionsDurable agent conversations with full history, status, and cost tracking
AgentsRegister an agent once (instructions + skills + model); every session bound to it inherits the full setup
SkillsYour agent can use every skill installed on the instance — delegation, scheduling, artifacts, browsing
Queueing & concurrencyTwo requests can never start two turns on one session; the platform queues, parks and drains safely
Restart resilienceIf the instance restarts mid-turn, every in-flight session auto-resumes
Model managementSubscription rotation across accounts, model selection and cost attribution are handled below your API calls
StreamingToken-by-token output over WebSocket, with buffered replay across reconnects

The integration model

Your product talks to one CRHQ instance with a scoped API key — a credential limited to the session lifecycle. It cannot touch the instance's settings, credentials, or other tenants' data.

Your product (web app, SaaS, internal tool)
        │  scoped key: sessions:write + sessions:read
        ▼
CRHQ instance ── sessions ── agents ── skills ── models

Because an agent turn runs real tools, a scoped key is pinned to the specific agents it may run — so a product can only ever execute the agent you designed for it. See Scoped API Keys.

A typical flow:

  1. Create a session without starting a turn — persist the session id in your own database first (crash-safe).
  2. Bind your registered agent and set a title and model.
  3. Start the first turn with an instruction.
  4. Stream output over WebSocket, or poll session status.
  5. Send follow-up messages as your user replies.

The full endpoint-by-endpoint contract is in the Integration API Reference.

A real example

GeneratePRD — a PRD-writing SaaS — runs its intake interviews and document generation entirely on a CRHQ instance. Its backend is a thin adapter over six CRHQ endpoints; everything agentic (the interview agent, the generation pipeline, delegation between agents, skill execution) is native CRHQ. The product's users never see CRHQ — they see the product.

What's coming

The v1 surface covers the session lifecycle. Planned extensions, driven by real products building on CRHQ:

  • agents:manage / skills:manage / jobs:manage scopes — create and update agents, skills, and background jobs programmatically, so your product's "agents" and "skills" features are CRHQ-native instead of a parallel system you have to build and maintain.
  • Off-host integration — run your product on separate infrastructure from the CRHQ instance with the same scoped-key contract.

If you're building on CRHQ and hit a wall the API doesn't cover, tell your instance operator — this surface grows from real integration needs.