API and Integrations

Edited by Lawrence Beckwith on February 22, 2026 at 4:40 AM UTC

Coordinator API (OpenAI-Compatible)

The coordinator exposes an OpenAI-compatible API at http://127.0.0.1:8080/v1.

Authorization: Bearer local-dev-key

Chat Completions

POST /v1/chat/completions

Available models:

Model Description
otheru-core Full routing stack (default)
otheru-council Council deliberation mode
otheru-coder Routes directly to coder agent
otheru-researcher Routes directly to researcher agent
otheru-architect Routes directly to architect agent

Health & Status Endpoints

Endpoint Method Description
/health GET Basic liveness check
/status GET Full system status
/dependencies/health GET Health of all dependencies (bridge, LEANN, Redis, etc.)
/agents/status GET Loaded agents and memory usage
/agents/usage GET Token usage statistics
/models/telemetry GET Per-model performance metrics

Agent Management

Endpoint Method Description
/agents/{role}/load POST Load agent into memory
/agents/{role}/unload POST Unload agent to free memory

Agent roles: orchestrator, responder, reasoner, coder, fara, observer

Desktop / KVM Endpoints

Endpoint Method Description
/fara/desktop POST Run Fara vision-action loop with a goal string
/fara/status GET Current Fara task state

Memory / RAG Endpoints

Endpoint Method Description
/memory/search POST Semantic search across indexed memory
/lightrag/status GET LightRAG index health and stats

Hardware Bridge API

http://127.0.0.1:8005

Endpoint Method Description
/stats GET Bridge status: frame count, resolution, frame age
/screenshot GET Capture desktop screenshot — returns base64 JPEG + metadata
/record POST Start video recording (output_path, duration, fps, scale)
/record/status GET Recording progress
/record/stop POST Stop current recording
/edid POST Set EDID profile on JetKVM (edid_name)
/mouse/move POST Move mouse to (x, y) in real screen coordinates
/mouse/click POST Click at (x, y) with button
/keyboard/type POST Type a text string
/keyboard/press POST Press one or more keys

Screenshot response schema:

{
  "image_base64": "...",
  "width": 1920,
  "height": 1080,
  "timestamp": "2026-02-22T02:00:00Z",
  "letterbox_scale": 0.74375,
  "letterbox_padding": [0, 46],
  "mouse_position": {
    "real": {"x": 960, "y": 540},
    "fara": {"x": 713, "y": 447},
    "confidence": 1.0
  }
}

GSD API

http://127.0.0.1:8090

Endpoint Method Description
/gsd/status GET Full state JSON
/gsd/report GET Human-readable summary
/gsd/metrics GET Performance timers and statistics
/gsd/start POST Start autonomous loop
/gsd/pause POST Pause loop
/gsd/set-objective POST Set goal {"objective": "..."}
/gsd/reset POST Reset state to defaults

LEANN RAG API

http://127.0.0.1:9621

Endpoint Method Description
/health GET Service health
/search POST Semantic search {"query": "...", "k": 5}
/ingest POST Add a document to the index
/ask POST RAG-grounded Q&A (requires researcher agent running)

OpenClaw Integration

Connect OpenClaw to OtherU Core as a custom LLM provider:

Provider type: openai-compatible
Base URL:      http://127.0.0.1:8080/v1
API Key:       local-dev-key
Default model: otheru-core

OpenClaw handles channel routing (Telegram, Signal, WhatsApp), heartbeat scheduling, memory indexing, and skill execution — OtherU Core provides the intelligence layer.

Integration Notes

  • All services communicate over localhost; no public ports are exposed by default
  • The coordinator calls LEANN, LightRAG, the bridge, and Redis directly over the internal Docker network
  • Tool routing is handled internally by the orchestrator — callers only need the OpenAI-compatible /v1/chat/completions endpoint