HTTP Endpoints

All REST API endpoints are served on the health server (default port 4102) under the /api prefix. Responses are JSON with Content-Type: application/json. CORS headers are applied at the server level. Base URL: http://<host>:4102/api

When the AGTOS_API_KEY environment variable is set, all /api/* endpoints require a Bearer token. See Authentication below.

Health

GET /api/health

Comprehensive health status from all registered service checkers (Redis, STT, TTS, Ollama, Claude, MCP).

Response

200 OK — All services healthy.

{
  "status": "healthy",
  "services": {
    "redis": { "status": "healthy", "responseTime": 2 },
    "stt-speaches": { "status": "healthy", "responseTime": 45 },
    "tts-speaches": { "status": "healthy", "responseTime": 38 },
    "ollama": { "status": "healthy", "responseTime": 12 },
    "mcp-server": { "status": "healthy", "responseTime": 5 }
  },
  "timestamp": 1711612800000
}

503 Service Unavailable — One or more services degraded.

{
  "error": "Health check failed",
  "message": "Redis connection refused"
}

GET /health/metrics

Aggregated metrics summary from the internal metrics collector (request counts, error rates, latency percentiles).

Response

200 OK

{
  "requests": { "total": 1420, "perMinute": 15 },
  "errors": { "total": 3, "perMinute": 0 },
  "latency": { "p50": 120, "p95": 450, "p99": 800 },
  "uptime": 3621.45
}

GET /health/:serviceName

Health status for a single registered service. Returns the same shape as the corresponding entry in GET /api/health, but for one service only.

Path Parameters

serviceName

string

required

Service name (e.g., redis, ollama, stt-sherpa-onnx, tts-sherpa-onnx, mcp-server, memory-maintenance, memory-semantic, nli-pipeline, provider-claude, provider-openai, provider-ollama, provider-openrouter).

Response

200 OK — Service is healthy.

{
  "status": "healthy",
  "responseTime": 2
}

503 Service Unavailable — Service is degraded.

{
  "status": "unhealthy",
  "error": "Connection refused"
}

404 Not Found — No such service registered.

{
  "error": "Unknown service: foo"
}

GET /metrics

Prometheus-format metrics endpoint for integration with Prometheus, Grafana, and other monitoring tools. Returns all collected metrics in the standard text exposition format.

Response

200 OK (text/plain; version=0.0.4)

# HELP agtos_http_requests_total Total HTTP requests
# TYPE agtos_http_requests_total counter
agtos_http_requests_total{method="GET",path="/api/health",status="200"} 142
agtos_http_requests_total{method="POST",path="/api/chat",status="200"} 38

# HELP agtos_http_request_duration_seconds HTTP request latency
# TYPE agtos_http_request_duration_seconds histogram
agtos_http_request_duration_seconds_bucket{le="0.1"} 120
agtos_http_request_duration_seconds_bucket{le="0.5"} 155

# HELP agtos_nli_inferences_total NLI cross-encoder verdicts
# TYPE agtos_nli_inferences_total counter
agtos_nli_inferences_total{result="contradiction"} 12
agtos_nli_inferences_total{result="neutral"} 230
agtos_nli_inferences_total{result="entailment"} 58

# HELP agtos_provider_catalog_fetch_total Provider catalog refresh attempts
# TYPE agtos_provider_catalog_fetch_total counter
agtos_provider_catalog_fetch_total{provider="claude",status="success"} 5

# HELP agtos_provider_catalog_models_count Current model count per provider
# TYPE agtos_provider_catalog_models_count gauge
agtos_provider_catalog_models_count{provider="openrouter"} 342

The /metrics endpoint is served at the root path (not under /api). It does not require authentication even when AGTOS_API_KEY is set.

Sessions

GET /api/sessions

List active voice sessions with connection metadata.

Response

200 OK

{
  "sessions": [
    {
      "id": "session-a1b2c3d4",
      "connectionId": "conn-xyz",
      "isActive": true,
      "isSpeaking": false,
      "lastActivity": 1711612800000
    }
  ],
  "count": 1
}

503 Service Unavailable — Voice pipeline not initialized.

{
  "error": "Voice pipeline not available"
}

Voice Status

GET /api/voice/status

Voice pipeline availability and active session count. Always returns 200, even when the pipeline is unavailable, so the dashboard can degrade gracefully.

Response

200 OK — Pipeline available.

{
  "available": true,
  "pipeline": "cascade",
  "activeSessions": 2
}

200 OK — Pipeline not wired up.

{
  "available": false
}

Memory

GET /api/memory/episodes

Retrieve recent episodic memory entries.

Query Parameters

limit

number

default:"20"

Max results to return (1—100).

Response

200 OK

{
  "episodes": [
    {
      "id": "ep-abc123",
      "summary": "User asked about weather forecast",
      "keywords": ["weather", "forecast"],
      "topic": "weather",
      "timestamp": 1711612800000,
      "importance": 0.7,
      "type": "conversation",
      "score": 0.95,
      "matchType": "keyword"
    }
  ],
  "count": 1,
  "available": true
}

503 Service Unavailable — Memory system not available.

{
  "error": "Memory system not available"
}

GET /api/memory/search

Semantic and keyword memory search across episodic memory.

Query Parameters

string

required

Search query text.

limit

number

default:"10"

Max results to return (1—50).

Response

200 OK

{
  "query": "what was the weather",
  "results": [
    {
      "id": "ep-abc123",
      "summary": "User asked about weather forecast",
      "keywords": ["weather", "forecast"],
      "topic": "weather",
      "timestamp": 1711612800000,
      "importance": 0.7,
      "type": "conversation",
      "score": 0.92,
      "matchType": "semantic"
    }
  ],
  "count": 1
}

400 Bad Request — Missing query parameter.

{
  "error": "Missing required query parameter: q"
}

503 Service Unavailable — Memory system not available.

{
  "error": "Memory system not available"
}

Scheduler

GET /api/scheduler/tasks

List all scheduled tasks.

Response

200 OK

{
  "tasks": [
    {
      "id": "task-abc123",
      "name": "Morning briefing",
      "status": "active",
      "schedule": { "type": "cron", "expression": "0 7 * * *" },
      "action": {
        "eventTopic": "briefing.morning",
        "payload": {}
      },
      "nextRunAt": 1711699200000,
      "lastRunAt": 1711612800000,
      "runCount": 5,
      "createdAt": 1711526400000
    }
  ],
  "count": 1
}

503 Service Unavailable — Scheduler not available (Redis down or not configured).

{
  "error": "Scheduler not available"
}

POST /api/scheduler/tasks

Create a new scheduled task.

Request Body

name

string

required

Human-readable task name.

scheduleType

string

required

One of: cron, once, interval.

expression

string

Cron expression. Required when scheduleType is cron.

atTimestamp

number

Unix ms timestamp. Required when scheduleType is once.

intervalMs

number

Interval in milliseconds. Required when scheduleType is interval.

eventTopic

string

required

Event bus topic published when the task fires.

payload

object

Optional payload included in the fired event.

Schedule Type Examples

{
  "name": "Every 5 minutes",
  "scheduleType": "cron",
  "expression": "*/5 * * * *",
  "eventTopic": "check.status"
}

{
  "name": "Reminder",
  "scheduleType": "once",
  "atTimestamp": 1711699200000,
  "eventTopic": "reminder.fire",
  "payload": { "message": "Meeting in 10 minutes" }
}

{
  "name": "Heartbeat",
  "scheduleType": "interval",
  "intervalMs": 60000,
  "eventTopic": "system.heartbeat"
}

Response

201 Created

{
  "task": {
    "id": "task-def456",
    "name": "Morning briefing",
    "status": "active",
    "schedule": { "type": "cron", "expression": "0 7 * * *" },
    "action": {
      "eventTopic": "briefing.morning",
      "payload": { "workflowId": "morning-routine" }
    },
    "nextRunAt": 1711699200000,
    "runCount": 0,
    "createdAt": 1711612800000
  }
}

400 Bad Request — Validation errors.

{
  "error": "Missing or invalid field: name"
}

{
  "error": "Cron schedule requires an expression field"
}

503 Service Unavailable — Scheduler not available.

DELETE /api/scheduler/tasks/:id

Cancel a scheduled task by ID.

Path Parameters

string

required

The task ID to cancel.

Response

200 OK

{
  "success": true,
  "taskId": "task-def456"
}

400 Bad Request — Invalid ID format.

{
  "error": "Invalid task ID format"
}

404 Not Found — Task does not exist.

{
  "error": "Failed to cancel task",
  "message": "Task not found"
}

503 Service Unavailable — Scheduler not available.

Workflows

GET /api/workflows

List all registered workflow definitions.

Response

200 OK

{
  "workflows": [
    {
      "id": "morning-routine",
      "name": "Morning Routine",
      "description": "Plays morning briefing and checks calendar",
      "stepCount": 3,
      "steps": [
        { "id": "step-1", "name": "Check Weather", "type": "ACTION" },
        { "id": "step-2", "name": "Read Calendar", "type": "ACTION" },
        { "id": "step-3", "name": "Speak Summary", "type": "ACTION" }
      ]
    }
  ],
  "count": 1
}

503 Service Unavailable — Workflow engine not available.

{
  "error": "Workflow engine not available"
}

POST /api/workflows/:id/execute

Trigger execution of a registered workflow.

Path Parameters

string

required

The workflow ID to execute.

Request Body (optional)

input

object

Optional input payload for the workflow.

{
  "input": {
    "location": "San Francisco",
    "units": "metric"
  }
}

Response

200 OK

{
  "execution": {
    "id": "exec-789",
    "workflowId": "morning-routine",
    "state": "completed",
    "startTime": 1711612800000,
    "endTime": 1711612802000,
    "output": { "summary": "Sunny, 72F. No meetings today." },
    "error": null
  }
}

400 Bad Request — Invalid workflow ID or execution failure.

{
  "error": "Invalid workflow ID format"
}

{
  "error": "Workflow execution failed",
  "message": "Step 'Check Weather' timed out"
}

404 Not Found — Workflow not registered.

{
  "error": "Workflow not found",
  "workflowId": "nonexistent"
}

503 Service Unavailable — Workflow engine not available.

System Info

GET /api/system/info

System information including uptime, runtime versions, memory usage, and port configuration.

Response

200 OK

{
  "uptime": 3621.45,
  "nodeVersion": "v22.12.0",
  "platform": "linux",
  "arch": "x64",
  "memoryUsage": {
    "rss": 85983232,
    "heapTotal": 42598400,
    "heapUsed": 38291456,
    "external": 2845696,
    "arrayBuffers": 1048576
  },
  "ports": {
    "voice": 3000,
    "mcp": 4100,
    "health": 4102
  },
  "timestamp": 1711612800000
}

Chat

POST /api/chat

Text-based chat endpoint. Routes user text through the agent reasoning loop (model router with tool execution) and returns the response.

Request Body

text

string

required

The user’s message text (must be non-empty).

sessionId

string

Session ID for conversation continuity. Omit for stateless.

{
  "text": "What's the weather like today?",
  "sessionId": "session-abc123"
}

Response

200 OK

{
  "text": "Based on current conditions, it's sunny and 72 degrees in your area.",
  "sessionId": "session-abc123",
  "metadata": {
    "stepCount": 2,
    "toolCallCount": 1,
    "durationMs": 1450
  }
}

400 Bad Request — Missing or empty text.

{
  "error": "Missing or empty required field: text"
}

500 Internal Server Error — Chat processing failed.

{
  "error": "Chat processing failed",
  "message": "Model provider timeout"
}

503 Service Unavailable — Voice pipeline not available.

{
  "error": "Voice pipeline not available"
}

Chat Streaming

POST /api/chat/stream

SSE streaming chat endpoint. Returns a text/event-stream response with real-time content tokens, thinking/reasoning blocks, tool call events, and a final metadata event. Used by the dashboard Chat page.

Request Body

text

string

required

The user’s message (must be non-empty, max 10,000 characters).

sessionId

string

Session ID for conversation continuity.

platform

string

Client platform identifier (defaults to web).

files

array

Images to include. Each entry: { content: string, mimeType: string, encoding: "base64" }.

{
  "text": "Explain how neural networks learn",
  "sessionId": "session-abc123",
  "files": [
    { "content": "base64...", "mimeType": "image/png", "encoding": "base64" }
  ]
}

SSE Events

The response is a stream of data: lines, each containing a JSON object with a type field:

{ "type": "content", "content": "Neural networks learn through" }

{ "type": "thinking", "content": "Let me break down backpropagation..." }

{ "type": "tool_start", "name": "memory.ask_about_user", "id": "call-123", "input": { "question": "..." } }

{ "type": "tool_result", "id": "call-123", "result": "...", "error": false, "durationMs": 250 }

{ "type": "step", "stepNumber": 2 }

{
  "type": "done",
  "metadata": {
    "stepCount": 3,
    "toolCallCount": 1,
    "durationMs": 2450,
    "sessionId": "session-abc123",
    "usage": { "inputTokens": 1200, "outputTokens": 450 }
  }
}

{ "type": "error", "code": "PROVIDER_TIMEOUT", "message": "Model provider timeout" }

400 Bad Request — Missing or empty text.429 Too Many Requests — Rate limit exceeded.500 Internal Server Error — Chat processing failed.

Use fetch() with ReadableStream to consume this endpoint — native EventSource does not support POST requests. The thinking event type carries provider-agnostic reasoning output (Claude thinking, OpenAI reasoning, Ollama think tags, OpenRouter reasoning).

Conversation History

GET /api/chat/history/:sessionId

Retrieve conversation messages for a session. Returns an empty array when the session has expired or doesn’t exist.

Path Parameters

sessionId

string

required

The session ID to retrieve history for.

Response

200 OK

{
  "sessionId": "session-abc123",
  "sessionExpired": false,
  "messages": [
    {
      "role": "user",
      "content": "What is my name?",
      "timestamp": 1711612800000
    },
    {
      "role": "assistant",
      "content": "Your name is Alex.",
      "timestamp": 1711612802000
    }
  ],
  "count": 2
}

200 OK — Session expired or not found.

{
  "sessionId": "session-old",
  "sessionExpired": true,
  "messages": [],
  "count": 0
}

Tasks

POST /api/tasks

Submit a background agent task. Accepts a topic string, routes it through the agent reasoning loop, and returns the result with a generated task ID.

Request Body

topic

string

required

The task topic/prompt (must be non-empty).

{
  "topic": "Summarize the latest news about AI safety"
}

Response

200 OK

{
  "taskId": "550e8400-e29b-41d4-a716-446655440000",
  "text": "Here is a summary of recent AI safety developments...",
  "metadata": {
    "stepCount": 3,
    "toolCallCount": 2,
    "durationMs": 4200
  }
}

400 Bad Request — Missing or empty topic.

{
  "error": "Missing or empty required field: topic"
}

500 Internal Server Error — Task processing failed.

{
  "error": "Task processing failed",
  "message": "Model provider timeout",
  "taskId": "550e8400-e29b-41d4-a716-446655440000"
}

503 Service Unavailable — Voice pipeline not available.

Voice Stats

GET /api/voice/stats

Audio quality metrics including STT/TTS latency percentiles, audio chunk counts, and active session count. Returns zeroed stats when no data has been collected yet.

Response

200 OK

{
  "stt": { "p50": 120, "p95": 300, "p99": 500, "count": 42 },
  "tts": { "p50": 80, "p95": 200, "p99": 400, "count": 38 },
  "audioChunksIn": 1200,
  "audioChunksOut": 950,
  "requestsPerMinute": 15,
  "activeSessions": 2,
  "timestamp": 1711612800000
}

Memory Profile

GET /api/memory/profile

Retrieve the user profile built from conversation history (name, communication style, patterns, preferences).

Response

200 OK

{
  "profile": {
    "name": "Alex",
    "communicationStyle": "concise, technical",
    "patterns": ["prefers metric units", "morning person"],
    "preferences": { "units": "metric", "language": "en" }
  }
}

503 Service Unavailable — Memory coordinator not available.

PUT /api/memory/profile

Update user profile fields.

Request Body

{
  "name": "Alex",
  "communicationStyle": "concise, technical",
  "patterns": ["prefers metric units"],
  "preferences": { "units": "metric" }
}

Field	Type	Required	Description
`name`	string	No	User display name (max 200 chars)
`communicationStyle`	string	No	Description of communication preferences (max 500 chars)
`patterns`	string[]	No	Behavioral patterns (max 50 items, 500 chars each)
`preferences`	object	No	Key-value preference pairs (string values, max 500 chars)

Response

200 OK

{
  "updated": true
}

400 Bad Request — Validation failure.503 Service Unavailable — Memory coordinator not available.

Memory Conclusions

GET /api/memory/conclusions

Retrieve conclusions drawn from conversation history by the Dialectic reasoning engine.

Query Parameters

type

string

Filter by conclusion type: explicit, inferred, corrected.

minConfidence

number

Minimum confidence threshold (0.0—1.0).

Response

200 OK

{
  "conclusions": [
    {
      "id": "conc-abc123",
      "text": "User prefers morning meetings",
      "type": "inferred",
      "confidence": 0.85,
      "sources": ["ep-001", "ep-003"]
    }
  ]
}

503 Service Unavailable — Memory coordinator not available.

DELETE /api/memory/conclusions/:id

Delete a specific conclusion by ID.

Path Parameters

string

required

The conclusion ID to delete.

Response

200 OK

{
  "deleted": true,
  "conclusionId": "conc-abc123"
}

503 Service Unavailable — Memory coordinator not available.

Memory Ask (Dialectic)

POST /api/memory/ask

Ask a question about the user via the Dialectic reasoning engine. Gathers profile, conclusions, and episodes to synthesize an answer.

Request Body

question

string

required

The question to ask about the user (max 2,000 characters).

userId

string

Optional user ID scope.

{
  "question": "What are this user's preferred communication channels?"
}

Response

200 OK

{
  "answer": "Based on conversation history, the user prefers Slack for quick questions and email for detailed discussions.",
  "confidence": 0.78,
  "sources": ["ep-abc123", "ep-def456"]
}

400 Bad Request — Missing or invalid question.503 Service Unavailable — Memory coordinator not available.

Memory Maintenance

POST /api/memory/maintain

Trigger an on-demand memory maintenance sweep (memory lint). Runs the Dreamer’s six-step sweep (stale detection, confidence decay, redundancy merge, orphan flagging, contradiction detection, low-confidence pruning) and returns a MaintenanceReport. Gated by ResourceGuard — busy systems defer the run. See ADR-021.

Request Body

The body is validated with .strict() — unknown fields are rejected. The userId is resolved server-side from the profile manager and must not be passed in the request body (per ADR-025 Rule 3).

{}

Response

200 OK — Sweep completed. Returns the full MaintenanceReport.

{
  "timestamp": 1712534400000,
  "durationMs": 4321,
  "conclusionsExamined": 142,
  "episodesChecked": 580,
  "summary": {
    "contradictions": 2,
    "stale": 14,
    "orphans": 3,
    "redundant": 5,
    "pruned": 1,
    "decayed": 14,
    "danglingSources": 0,
    "contradictionPipeline": {
      "candidatesSelected": 210,
      "nliConfirmed": 18,
      "llmConfirmed": 2,
      "stageLatencyMs": { "stage1": 45, "stage2": 812, "stage3": 2104 }
    }
  },
  "issues": [
    {
      "type": "contradiction",
      "conclusionId": "conc-abc123",
      "action": "flagged",
      "description": "Conflicts with conc-def456 (NLI verdict: contradiction, confidence 0.92)"
    }
  ]
}

400 Bad Request — Validation failed (e.g., unknown fields in the body).503 Service Unavailable — errorCode: PROFILE_DISCONNECTED — Memory profile manager is not connected (Redis down, manager disconnected). Persistent — operator action required.

{
  "error": "Memory maintenance unavailable",
  "errorCode": "PROFILE_DISCONNECTED",
  "message": "Profile manager is not connected"
}

503 Service Unavailable — errorCode: RESOURCES_BUSY — ResourceGuard deferred this run (active sessions, high CPU load, Ollama VRAM contention). Transient — retry later. The reason field carries the guard’s diagnosis.

{
  "error": "Memory maintenance deferred",
  "errorCode": "RESOURCES_BUSY",
  "message": "Background work not safe right now",
  "reason": "active sessions: 1"
}

500 Internal Server Error — Dreamer.maintain() threw (genuine internal error, not a defer).

The CLI (agtos memory maintain) reads errorCode to decide between exit code 2 (transient, retry later) and exit code 3 (operator action required).

GET /api/memory/maintain/history

List recent MaintenanceReport entries. Backs the dashboard’s maintenance history widget. Reports are stored with a 30-day TTL under a sorted-set index capped at 200 entries.

Query Parameters

Parameter	Type	Default	Description
`limit`	number	`20`	Max reports to return (1—100)

Response

200 OK

{
  "reports": [
    {
      "timestamp": 1712534400000,
      "durationMs": 4321,
      "conclusionsExamined": 142,
      "episodesChecked": 580,
      "summary": { "contradictions": 2, "stale": 14, "orphans": 3, "redundant": 5, "pruned": 1, "decayed": 14 },
      "issues": []
    }
  ],
  "count": 1
}

500 Internal Server Error — Failed to list maintenance reports.503 Service Unavailable — Memory coordinator or profile manager not connected.

GET /api/memory/maintain/history/:timestamp

Fetch a single MaintenanceReport by its timestamp (Unix milliseconds).

Path Parameters

timestamp

number

required

Unix milliseconds timestamp of the report to fetch.

Response

200 OK — Returns the full MaintenanceReport (same shape as POST /api/memory/maintain).400 Bad Request — Invalid timestamp.404 Not Found — Report not found or expired (past the 30-day TTL).503 Service Unavailable — Memory coordinator or profile manager not connected.

Memory Import

GET /api/memory/sources

Scan for available external AI tool memory sources (Claude, ChatGPT, etc.) that can be imported into agtOS.

Response

200 OK

{
  "sources": [
    {
      "name": "claude",
      "available": true,
      "memoryCount": 42,
      "path": "~/.claude/memory"
    }
  ]
}

503 Service Unavailable — Memory coordinator not available.

POST /api/memory/import

Import memories from external AI tool sources into the agtOS memory system.

Request Body

sources

string[]

Optional list of source names to import from. If omitted, imports from all available sources.

{
  "sources": ["claude"]
}

Response

200 OK

{
  "imported": 35,
  "skipped": 7,
  "errors": 0,
  "message": "Imported 35 memories from claude"
}

503 Service Unavailable — Memory coordinator not available.

Entities

GET /api/entities

List or search entities from the entity-centric memory system.

Query Parameters

string

Search entities by name (partial match).

type

string

Filter by entity type: person, place, organization, event, thing.

limit

number

default:"20"

Max results (1—100).

Response

200 OK

{
  "entities": [
    {
      "id": "ent-abc123",
      "name": "Alice",
      "type": "person",
      "aliases": ["Alice Smith"],
      "confidence": 0.92,
      "episodeCount": 15,
      "lastMentioned": 1711612800000
    }
  ],
  "count": 1
}

503 Service Unavailable — Entity manager not available (Redis down).

GET /api/entities/stats

Entity counts grouped by type.

Response

200 OK

{
  "stats": {
    "person": 12,
    "place": 5,
    "organization": 3,
    "event": 8,
    "thing": 15
  },
  "total": 43
}

GET /api/entities/:id

Get a single entity by ID with full details.

Path Parameters

string

required

The entity ID.

Response

200 OK

{
  "entity": {
    "id": "ent-abc123",
    "name": "Alice",
    "type": "person",
    "aliases": ["Alice Smith"],
    "confidence": 0.92,
    "episodeCount": 15,
    "lastMentioned": 1711612800000
  }
}

404 Not Found — Entity does not exist.

PUT /api/entities/:id

Update an entity’s name, aliases, or confidence.

Path Parameters

string

required

The entity ID.

Request Body

name

string

Updated entity name.

aliases

string[]

Updated alias list.

confidence

number

Updated confidence score (0.0—1.0).

Response

200 OK — Returns the updated entity.404 Not Found — Entity does not exist.

DELETE /api/entities/:id

Soft-delete an entity.

Path Parameters

string

required

The entity ID.

Response

200 OK

{
  "deleted": true,
  "entityId": "ent-abc123"
}

404 Not Found — Entity does not exist.

POST /api/entities/:id/merge

Merge a duplicate entity into this entity. The target entity’s episodes, conclusions, and relationships are transferred to the primary entity.

Path Parameters

string

required

The primary entity ID (merge target).

Request Body

targetId

string

required

The duplicate entity ID to merge into the primary.

{
  "targetId": "ent-duplicate456"
}

Response

200 OK — Returns the merged primary entity.404 Not Found — Entity does not exist.

GET /api/entities/:id/episodes

Episodes that mention this entity.

Path Parameters

string

required

The entity ID.

Query Parameters

limit

number

default:"20"

Max results (1—100).

Response

200 OK

{
  "entityId": "ent-abc123",
  "episodes": [
    {
      "id": "ep-xyz789",
      "summary": "User discussed project plans with Alice",
      "timestamp": 1711612800000
    }
  ],
  "count": 1
}

GET /api/entities/:id/conclusions

Conclusions that reference this entity.

Path Parameters

string

required

The entity ID.

Response

200 OK

{
  "entityId": "ent-abc123",
  "conclusions": [
    {
      "id": "conc-abc123",
      "text": "Alice is a software engineer at Acme Corp",
      "type": "explicit",
      "confidence": 0.9
    }
  ],
  "count": 1
}

GET /api/entities/:id/relationships

Relationships involving this entity (as subject or object).

Path Parameters

string

required

The entity ID.

Response

200 OK

{
  "entityId": "ent-abc123",
  "relationships": [
    {
      "id": "rel-001",
      "subject": { "id": "ent-abc123", "name": "Alice" },
      "predicate": "works-at",
      "object": { "id": "ent-def456", "name": "Acme Corp" },
      "confidence": 0.85
    }
  ],
  "count": 1
}

Devices

POST /api/devices/register

Request Body

name

string

required

Device display name (max 200 chars).

deviceType

string

required

One of: esp32, browser, cli, mcp-client, custom.

platform

string

required

Platform identifier (max 100 chars).

capabilities

object

required

Device capability flags: audio, microphone, speaker, display, buttons, sensors (all boolean).

secret

string

Optional shared secret for device authentication (8—256 chars). Hashed with SHA-256.

firmwareVersion

string

Firmware version string (max 50 chars).

metadata

object

Arbitrary key-value metadata.

{
  "name": "Kitchen Speaker",
  "deviceType": "esp32",
  "platform": "esp32-s3",
  "capabilities": {
    "audio": true,
    "microphone": true,
    "speaker": true,
    "display": false,
    "buttons": false,
    "sensors": false
  },
  "secret": "my-device-secret",
  "firmwareVersion": "1.2.0"
}

Response

201 Created

{
  "device": {
    "id": "dev-abc123",
    "name": "Kitchen Speaker",
    "deviceType": "esp32",
    "platform": "esp32-s3",
    "status": "pending",
    "trustLevel": 2,
    "capabilities": { "audio": true, "microphone": true, "speaker": true, "display": false, "buttons": false, "sensors": false },
    "firmwareVersion": "1.2.0"
  }
}

409 Conflict — Device already registered.503 Service Unavailable — Device registry not available (Redis down).

GET /api/devices

List registered devices with optional filters.

Query Parameters

status

string

Filter by status: pending, active, suspended, revoked.

deviceType

string

Filter by device type: esp32, browser, cli, mcp-client, custom.

limit

number

Max results.

offset

number

Pagination offset.

Response

200 OK

{
  "devices": [
    {
      "id": "dev-abc123",
      "name": "Kitchen Speaker",
      "deviceType": "esp32",
      "platform": "esp32-s3",
      "status": "active",
      "trustLevel": 2,
      "capabilities": { "audio": true, "microphone": true, "speaker": true, "display": false, "buttons": false, "sensors": false }
    }
  ],
  "count": 1
}

503 Service Unavailable — Device registry not available.

GET /api/devices/:id

Get a single device by ID.

Path Parameters

string

required

The device ID.

Response

200 OK

{
  "device": {
    "id": "dev-abc123",
    "name": "Kitchen Speaker",
    "deviceType": "esp32",
    "status": "active",
    "trustLevel": 2
  }
}

404 Not Found — Device does not exist.503 Service Unavailable — Device registry not available.

PUT /api/devices/:id

Update a device’s properties.

Path Parameters

string

required

The device ID.

Request Body

All fields are optional. Only provided fields are updated.

name

string

Updated device name.

status

string

New status: pending, active, suspended, revoked.

capabilities

object

Updated capability flags.

secret

string

New shared secret (8—256 chars).

firmwareVersion

string

Updated firmware version.

Response

200 OK — Returns the updated device.404 Not Found — Device does not exist.503 Service Unavailable — Device registry not available.

DELETE /api/devices/:id

Remove a device from the registry.

Path Parameters

string

required

The device ID to remove.

Response

200 OK

{
  "success": true,
  "deviceId": "dev-abc123"
}

404 Not Found — Device does not exist.503 Service Unavailable — Device registry not available.

POST /api/devices/:id/authenticate

Authenticate a device by verifying its shared secret.

Path Parameters

string

required

The device ID.

Request Body

secret

string

required

The device’s shared secret.

{
  "secret": "my-device-secret"
}

Response

200 OK

{
  "authenticated": true,
  "device": {
    "id": "dev-abc123",
    "name": "Kitchen Speaker",
    "status": "active"
  }
}

401 Unauthorized — Invalid secret.

{
  "authenticated": false,
  "message": "Invalid device secret"
}

503 Service Unavailable — Device registry not available.

POST /api/devices/:id/link

Link a device to a user account for personalized preferences.

Path Parameters

string

required

The device ID.

Request Body

userId

string

required

The user ID to link (max 200 chars).

{
  "userId": "user-abc123"
}

Response

200 OK

{
  "linked": true,
  "deviceId": "dev-abc123",
  "userId": "user-abc123"
}

503 Service Unavailable — User preferences not available.

User Preferences

GET /api/users/:userId/preferences

Get user preferences (TTS voice, language, wake word, privacy settings).

Path Parameters

userId

string

required

The user ID.

Response

200 OK

{
  "preferences": {
    "ttsVoice": "af_heart",
    "ttsSpeed": 1.0,
    "language": "en",
    "wakeWord": "hey agtos",
    "privacySettings": {
      "storeTranscripts": true,
      "storeAudio": false
    }
  }
}

503 Service Unavailable — User preferences not available (Redis down).

PUT /api/users/:userId/preferences

Update user preferences.

Path Parameters

userId

string

required

The user ID.

Request Body

All fields are optional.

ttsVoice

string

Preferred TTS voice (max 100 chars).

ttsSpeed

number

Speech speed (0.5—2.0).

language

string

Preferred language code (max 10 chars).

wakeWord

string

Custom wake word (max 50 chars).

privacySettings

object

Privacy flags: storeTranscripts (boolean), storeAudio (boolean).

{
  "ttsVoice": "nova",
  "ttsSpeed": 1.2,
  "language": "en",
  "privacySettings": {
    "storeTranscripts": true,
    "storeAudio": false
  }
}

Response

200 OK — Returns the updated preferences.400 Bad Request — Validation failure.503 Service Unavailable — User preferences not available.

Setup Token

GET /api/setup-token

Retrieve the onboarding setup token. This token is generated at server startup and has a 30-minute TTL. It is used by the onboarding wizard to authenticate credential storage requests without requiring an API key.

This endpoint is localhost-only — requests from non-loopback addresses return 403 Forbidden.

Response

200 OK

{
  "token": "a1b2c3d4e5f6..."
}

403 Forbidden — Request not from localhost.

{
  "error": "Setup token only available from localhost"
}

404 Not Found — No setup token available (server started with AGTOS_API_KEY set, or token has expired).

{
  "error": "No setup token available"
}

The setup token is only generated when AGTOS_API_KEY is not set (onboarding mode). Once the user configures an API key, the setup token is no longer needed.

POST /api/slots/auto-configure

Auto-configure the slot registry from a mode preset. Used by the setup wizard to configure slots based on the user’s chosen mode and available providers.

Request Body

mode

string

required

Configuration mode: cloud, local, or hybrid.

cloudProvider

string

Cloud provider for cloud/hybrid modes: claude, openai, or openrouter.

ollamaModel

string

Ollama model for local/hybrid modes.

fallbackStrategy

string

Fallback strategy: cloud-backup, ollama-local, or none.

{
  "mode": "hybrid",
  "cloudProvider": "claude",
  "ollamaModel": "qwen3:7b",
  "fallbackStrategy": "cloud-backup"
}

Response

200 OK

{
  "slots": { "chat": { "provider": "claude", "model": "..." }, "..." : "..." },
  "restartRequired": true,
  "mode": "hybrid",
  "message": "Auto-configured 6 slots in hybrid mode. Restart to activate."
}

400 Bad Request — Invalid mode or missing required fields.

POST /api/slots/reset

Reset the slot configuration to built-in defaults. Removes all custom slots and restores the default provider/model assignments.

Response

200 OK

{
  "slots": { "chat": { "provider": "claude", "model": "..." }, "..." : "..." },
  "restartRequired": true,
  "message": "Slot config reset. Restart the server to activate."
}

Credentials

POST /api/credentials

Store encrypted credentials for a provider. Credentials are encrypted with AES-256-GCM before storage. Must provide either apiKey or setupToken.

This endpoint is localhost-only — requests from non-loopback addresses return 403 Forbidden. It is designed for the setup wizard and Settings UI running on the same machine.

Request Body

provider

string

required

Provider identifier: provider-anthropic, provider-openai, or provider-openrouter.

apiKey

string

API key (e.g., sk-ant-api03-... for Anthropic, sk-... for OpenAI, sk-or-v1-... for OpenRouter). Max 256 chars.

{
  "provider": "provider-anthropic",
  "apiKey": "sk-ant-api03-your-key"
}

Response

200 OK

{
  "success": true,
  "provider": "provider-anthropic"
}

400 Bad Request — Validation failure.403 Forbidden — Request not from localhost.

{
  "error": "Credential storage only available from localhost"
}

503 Service Unavailable — Credential manager not available.

POST /api/credentials/validate

Validate credentials against the actual provider API without storing them. Useful for the setup wizard and Settings UI. Supports all four providers.

Request Body

provider

string

required

Provider to validate: provider-anthropic, provider-openai, provider-ollama, or provider-openrouter.

apiKey

string

API key to validate. Max 256 chars.

{
  "provider": "provider-anthropic",
  "apiKey": "sk-ant-api03-your-key"
}

Response

200 OK

{
  "valid": true,
  "provider": "provider-anthropic",
  "reason": "API key is valid (Claude Haiku 4.5 responded)"
}

{
  "valid": false,
  "provider": "provider-anthropic",
  "reason": "Invalid API key: 401 Unauthorized"
}

400 Bad Request — Missing or invalid fields.

DELETE /api/credentials/:providerId

Delete stored credentials for a specific provider.

This endpoint is localhost-only and requires either a valid API key or setup token.

Path Parameters

providerId

string

required

The provider scope to delete (e.g., provider-anthropic, provider-openai, provider-openrouter). Must start with provider-.

Response

200 OK

{
  "success": true,
  "provider": "provider-anthropic"
}

403 Forbidden — Request not from localhost.404 Not Found — No credentials stored for this provider.

POST /api/credentials/clear-all

Delete all stored credentials.

This endpoint is localhost-only and requires either a valid API key or setup token. This action is irreversible.

Response

200 OK

{
  "success": true,
  "cleared": 3
}

403 Forbidden — Request not from localhost.

Dependencies

GET /api/dependencies

Check all optional system dependencies (Node.js, Docker, Ollama, Redis, sherpa-onnx models).

Response

200 OK

{
  "node": { "installed": true, "version": "v22.12.0", "hint": null },
  "docker": { "installed": true, "running": true },
  "ollama": { "installed": true, "reachable": true },
  "redis": { "installed": true, "reachable": true },
  "sherpaModels": { "downloaded": 3, "total": 5 }
}

POST /api/dependencies/install-redis

Install and start Redis via Docker. Creates a redis/redis-stack:latest container with port 6379 exposed and unless-stopped restart policy.

Response

200 OK — Redis installed, started, or already running.

{
  "status": "installed"
}

Possible status values: installed (new container created), started (existing container started), already_running (no action needed).400 Bad Request — Docker is not running.

{
  "error": "Docker is not running",
  "hint": "Start Docker Desktop or run 'sudo systemctl start docker'"
}

500 Internal Server Error — Installation failed.

{
  "error": "Failed to install Redis",
  "details": "docker: Error response from daemon..."
}

Config (Legacy)

GET /api/config/writable

List the configuration keys that can be updated at runtime via the legacy config endpoint.

Response

200 OK

{
  "keys": ["ttsVoice", "ttsSpeed", "sttLanguage", "sttModel", "logLevel", "apiRateLimit", "chatRateLimit"],
  "description": {
    "ttsVoice": "TTS voice name (e.g., \"alloy\", \"nova\")",
    "ttsSpeed": "TTS speech speed (0.5-2.0)"
  },
  "current": {
    "ttsVoice": "af_heart",
    "logLevel": "info"
  }
}

PUT /api/config

Update a single runtime config value. The value is applied immediately to the environment variable and persisted to the config file.

Request Body

key

string

required

Config key name (must be in the writable whitelist).

value

string | number | boolean

required

New value for the key.

{
  "key": "ttsVoice",
  "value": "nova"
}

Response

200 OK

{
  "key": "ttsVoice",
  "value": "nova",
  "envKey": "AGTOS_TTS_VOICE",
  "applied": true,
  "persisted": true
}

403 Forbidden — Key is not writable.

Settings

GET /api/settings

Retrieve all writable config keys with current values, descriptions, reload types, and categories. Used by the Settings UI for dynamic form generation.

Response

200 OK

{
  "settings": {
    "ttsVoice": {
      "value": "af_heart",
      "description": "TTS voice name",
      "reloadType": "immediate",
      "category": "tts"
    },
    "llmProvider": {
      "value": "auto",
      "description": "Primary LLM provider",
      "reloadType": "provider-restart",
      "category": "llm"
    }
  }
}

PUT /api/settings

Update multiple configuration values at once. All values are validated with Zod schemas, applied to environment variables, persisted to the config file, and announced via config:changed event.

Request Body

Pass a flat object with config keys and their new values:

{
  "ttsVoice": "nova",
  "ttsSpeed": 1.2,
  "logLevel": "debug"
}

See Configuration > Environment Variables for the full list of writable keys.

Response

200 OK

{
  "changed": ["ttsVoice", "ttsSpeed", "logLevel"],
  "persisted": true
}

400 Bad Request — Validation failure with field-level details.

{
  "error": "Invalid settings update",
  "details": [
    { "field": "ttsSpeed", "message": "Number must be less than or equal to 2" }
  ]
}

GET /api/settings/schema

Return the Zod schema as a JSON description for dynamic form generation in the Settings UI. Includes type, description, reload behavior, category, and constraints for each key.

Response

200 OK

{
  "schema": {
    "ttsSpeed": {
      "type": "number",
      "description": "TTS speech speed (0.5–2.0)",
      "reloadType": "immediate",
      "category": "tts",
      "constraints": { "min": 0.5, "max": 2.0, "step": 0.1 }
    },
    "llmProvider": {
      "type": "enum",
      "description": "Primary LLM provider",
      "reloadType": "provider-restart",
      "category": "llm",
      "constraints": { "options": ["claude", "ollama", "auto"] }
    }
  }
}

Slots

GET /api/slots

Get the live Model Slot Registry with current configuration, runtime stats, and slot names.

Response

200 OK

{
  "slots": {
    "chat": { "provider": "claude", "model": "claude-sonnet-4-20250514", "temperature": 0.7 },
    "reasoning": { "provider": "openai", "model": "gpt-4o", "temperature": 0.3, "fallback": "chat" },
    "coding": { "provider": "ollama", "model": "qwen2.5-coder", "temperature": 0.2, "fallback": "chat" }
  },
  "stats": {
    "requests": 142,
    "errors": 3,
    "fallbackCount": 5
  },
  "builtInSlotNames": ["chat", "reasoning", "coding", "tool_calling", "creative", "maintenance"],
  "activeSlotNames": ["chat", "reasoning", "coding"]
}

PUT /api/slots

Update the Model Slot Registry configuration. Each slot maps a named capability (e.g., chat, reasoning) to a provider and model. The chat slot is required and cannot be removed.Before writing, the server validates each slot’s model against the ProviderCatalog:

Unknown models (not in any catalog): warning returned, write allowed — the model may be private or unlisted.
Future-deprecated models: warning returned, write allowed.
Past-deprecated models: write blocked with HTTP 400.
Catalog fetch failure: warning returned, write allowed — transient upstream issue.

Request Body

{
  "chat": { "provider": "claude", "model": "claude-sonnet-4-20250514" },
  "reasoning": { "provider": "openai", "model": "gpt-4o" },
  "maintenance": { "provider": "openrouter", "model": "openai/gpt-4o-mini" }
}

Response

200 OK

{
  "slots": {
    "chat": { "provider": "claude", "model": "claude-sonnet-4-20250514" },
    "reasoning": { "provider": "openai", "model": "gpt-4o" },
    "maintenance": { "provider": "openrouter", "model": "openai/gpt-4o-mini" }
  },
  "restartRequired": true,
  "message": "Slot configuration updated",
  "warnings": [
    {
      "slot": "maintenance",
      "model": "openai/gpt-4o-mini",
      "reason": "not found in catalog (private / unlisted / pinned model)"
    }
  ]
}

The warnings array is only present when at least one warning was generated.400 Bad Request — Deprecated model(s) detected.

{
  "error": "Deprecated model(s)",
  "message": "Cannot use retired models",
  "deprecated": [
    {
      "slot": "chat",
      "model": "gpt-3.5-turbo-0301",
      "deprecatedAt": "2024-06-13T00:00:00Z"
    }
  ]
}

Provider Catalog

GET /api/providers/catalog

Aggregate model catalog from all configured providers. Returns models with capabilities, pricing, context length, and deprecation status.

Query Parameters

refresh

string

Set to 1 to bypass the 1-hour cache TTL and force a network fetch.

capability

string

Comma-separated list of required capabilities (AND semantics). E.g., tool-use,vision.

Response

200 OK

{
  "providers": [
    {
      "providerId": "claude",
      "models": [
        {
          "id": "claude-sonnet-4-20250514",
          "name": "Claude Sonnet 4",
          "contextLength": 200000,
          "maxOutputTokens": 8192,
          "capabilities": ["tool-use", "vision", "thinking"],
          "pricing": { "inputPer1M": 3.0, "outputPer1M": 15.0 }
        }
      ],
      "latencyMs": 245
    }
  ],
  "count": 1,
  "providerIds": ["claude", "openai", "ollama", "openrouter"]
}

GET /api/providers/:providerId/account

Credit balance and usage snapshot for a single provider. Not all providers support account info.

Path Parameters

providerId

string

required

Provider identifier: claude, openai, openrouter, ollama.

Response

200 OK

{
  "creditBalance": 42.50,
  "creditCurrency": "USD"
}

404 Not Found — Provider not configured or does not support account info.

Models

GET /api/models

List all models from the model registry with download status.

Response

200 OK

{
  "models": [
    {
      "id": "moonshine-tiny-en-v2",
      "name": "Moonshine Tiny (English)",
      "description": "Lightweight STT model",
      "type": "stt",
      "family": "moonshine",
      "sizeBytes": 48000000,
      "sizeMb": 45.8,
      "downloaded": true,
      "downloading": false,
      "format": "onnx"
    }
  ],
  "downloadedCount": 3,
  "totalCount": 5
}

POST /api/models/download

Start downloading a model. Returns an SSE stream with progress events.

Request Body

modelId

string

required

The model ID to download.

{
  "modelId": "kokoro-int8-multi-v1"
}

Response

200 OK (text/event-stream)

{ "type": "progress", "modelId": "kokoro-int8-multi-v1", "downloaded": 50000000, "total": 100000000, "percent": 50 }

{ "type": "complete", "modelId": "kokoro-int8-multi-v1", "durationMs": 12000 }

{ "type": "error", "modelId": "kokoro-int8-multi-v1", "error": "Network timeout", "retryable": true }

400 Bad Request — Unknown model ID.

GET /api/models/:modelId/status

Check download status of a single model.

Path Parameters

modelId

string

required

The model ID.

Response

200 OK

{
  "modelId": "kokoro-int8-multi-v1",
  "name": "Kokoro TTS (Int8 Multi)",
  "type": "tts",
  "downloaded": true,
  "downloading": false,
  "sizeBytes": 100000000,
  "sizeMb": 95.4,
  "path": "/home/user/.agtos/models/kokoro-int8-multi-v1"
}

404 Not Found — Unknown model ID.

DELETE /api/models/:modelId

Delete a downloaded model.

Path Parameters

modelId

string

required

The model ID to delete.

Response

200 OK

{
  "success": true,
  "modelId": "kokoro-int8-multi-v1"
}

404 Not Found — Model not found or not downloaded.

POST /api/models/clear-all

Remove all downloaded models.

Response

200 OK

{
  "success": true,
  "removed": ["moonshine-tiny-en-v2", "kokoro-int8-multi-v1"],
  "count": 2
}

Ollama

GET /api/ollama/status

Check Ollama installation and running status.

Response

200 OK

{
  "installed": true,
  "running": true,
  "version": "0.3.12",
  "models": [
    { "name": "qwen3:7b", "size": 4700000000, "digest": "abc123..." }
  ],
  "hint": null
}

200 OK — Ollama not installed.

{
  "installed": false,
  "running": false,
  "hint": "Install Ollama from https://ollama.com"
}

GET /api/ollama/models

List models installed in Ollama.

Response

200 OK

{
  "models": [
    {
      "name": "qwen3:7b",
      "model": "qwen3:7b",
      "size": 4700000000,
      "digest": "abc123...",
      "family": "qwen3",
      "parameterSize": "7.6B",
      "quantization": "Q4_K_M"
    }
  ],
  "count": 1
}

503 Service Unavailable — Ollama not reachable.

POST /api/ollama/pull

Pull (download) a model from Ollama. Returns an SSE stream with progress events.

Request Body

model

string

required

The model name to pull (e.g., qwen3:7b, llama3.1:8b).

{
  "model": "qwen3:7b"
}

Response

200 OK (text/event-stream)

{ "type": "progress", "modelId": "qwen3:7b", "status": "pulling", "digest": "...", "total": 4700000000, "completed": 1200000000, "percent": 25 }

{ "type": "complete", "modelId": "qwen3:7b", "durationMs": 45000 }

503 Service Unavailable — Ollama not reachable.

POST /api/ollama/start

Attempt to start the Ollama service.

Response

200 OK

{
  "started": true
}

500 Internal Server Error — Failed to start Ollama.

Billing

GET /api/billing/status

Aggregate billing status across all cloud providers. Shows exhaustion state, balance, and active fallback strategy.

Response

200 OK

{
  "providers": {
    "claude": {
      "exhausted": false,
      "balance": 42.50,
      "currency": "USD",
      "billingUrl": "https://console.anthropic.com/billing",
      "fallbackActive": false
    },
    "openai": {
      "exhausted": true,
      "billingUrl": "https://platform.openai.com/account/billing",
      "fallbackActive": true,
      "fallbackTarget": "claude"
    }
  },
  "strategy": "cloud-backup"
}

POST /api/billing/retry/:providerId

Reset billing exhaustion state for a provider. Use after adding credits to retry the provider.

Path Parameters

providerId

string

required

The provider to retry (e.g., openai, claude, openrouter).

Response

200 OK — Exhaustion state cleared, affected slots re-marked healthy.404 Not Found — Provider not configured.

Capture Protocol (PACT)

POST /api/capture/start

Start a new multimodal capture stream. Validates consent before beginning capture.

Request Body

deviceId

string

required

The device ID initiating capture.

modalities

string[]

required

Capture modalities: audio, video, neural.

captureMode

string

Capture mode: active-participant (default), passive-observation, or ambient.

{
  "deviceId": "dev-abc123",
  "modalities": ["audio"],
  "captureMode": "active-participant"
}

Response

201 Created

{
  "streamId": "stream-xyz789",
  "state": "active",
  "correlationId": "corr-abc123"
}

400 Bad Request — Missing consent or invalid modality.503 Service Unavailable — Capture protocol not available.

POST /api/capture/stop

Stop an active capture stream.

Request Body

streamId

string

required

The stream ID to stop.

Response

200 OK404 Not Found — Stream not found or already stopped.

GET /api/capture/streams

List active capture streams for the current user.

Response

200 OK

{
  "streams": [
    {
      "streamId": "stream-xyz789",
      "deviceId": "dev-abc123",
      "modalities": ["audio"],
      "state": "active",
      "startedAt": 1711612800000
    }
  ],
  "count": 1
}

Get capture consent state for a device.

Query Parameters

deviceId

string

required

The device ID to check consent for.

Response

200 OK

{
  "deviceId": "dev-abc123",
  "captureConsent": {
    "enabled": true,
    "jurisdiction": "US-CA",
    "consentGivenAt": 1711612800000,
    "consentLevel": "active"
  }
}

Update capture consent settings for a device.

Request Body

deviceId

string

required

The device ID.

enabled

boolean

required

Enable or disable capture consent.

jurisdiction

string

Jurisdiction code (e.g., US-CA for California two-party consent).

Consent level: none, passive, active, or full.

{
  "deviceId": "dev-abc123",
  "enabled": true,
  "jurisdiction": "US-CA",
  "consentLevel": "active"
}

Response

200 OK — Returns updated consent settings.400 Bad Request — Validation failure.

System (Extended)

GET /api/system/redis-status

Redis connection status and diagnostics.

Response

200 OK

{
  "connected": true,
  "url": "redis://localhost:6379",
  "version": "7.4.1"
}

POST /api/system/reconnect-redis

Force Redis reconnection and hot-create Redis-dependent services (memory, scheduling, devices) without a server restart. Requires API key when AGTOS_API_KEY is set.

Response

200 OK

{
  "reconnected": true,
  "services": ["memory", "scheduler", "device-registry"]
}

503 Service Unavailable — Redis connection failed.

GET /api/system/capabilities

Hardware and software capability detection for the current host.

Response

200 OK

{
  "cpu": { "cores": 8, "model": "Apple M2 Pro" },
  "memory": { "totalMb": 16384, "availableMb": 8192 },
  "gpu": { "available": true, "type": "metal" },
  "ollama": { "available": true },
  "docker": { "available": true }
}

POST /api/system/reset-onboarding

Reset the onboarding state so the setup wizard runs again on next app load.

Response

200 OK

{
  "success": true,
  "message": "Onboarding reset. Reload the app to re-run setup."
}

Common Error Responses

All endpoints may return the following error shapes:

400 Bad Request

Returned when the request is malformed or missing required fields. The error field contains a human-readable description.

{
  "error": "Invalid JSON body"
}

404 Not Found

Returned when a requested resource (task, workflow) does not exist.

{
  "error": "Not found"
}

500 Internal Server Error

Returned when an unexpected exception occurs during request processing.

{
  "error": "Internal server error",
  "message": "Detailed error description"
}

503 Service Unavailable

Returned when a required dependency (Redis, voice pipeline, memory system, scheduler, workflow engine) is not initialized or has failed.

{
  "error": "Component not available"
}

Notes

Body size limit: Request bodies are capped at 1 MB. Requests exceeding this limit receive no response (connection closed).

ID validation: Path parameter IDs (task IDs, workflow IDs) must match ^[a-zA-Z0-9\-_]+$ and be 1—128 characters. Invalid IDs return 400.
CORS: Configurable via CORS_ORIGIN environment variable (default: http://localhost:5173). Tauri desktop origins are auto-added. Preflight OPTIONS requests return 204.
Metrics: All API requests are tracked in the internal metrics system. Latency is recorded per route.
Authentication: See Authentication below for opt-in API key auth.
Rate Limiting: See Rate Limiting below for per-endpoint limits.

Authentication

API key authentication is opt-in. When the AGTOS_API_KEY environment variable is set, all /api/* endpoints require a valid Bearer token.

Headers

Header	Value	Required
`Authorization`	`Bearer <your-api-key>`	When `AGTOS_API_KEY` is set

Response (401 Unauthorized)

{
  "error": "Unauthorized",
  "message": "Valid API key required. Set Authorization: Bearer <key> header."
}

Exempt Paths

These paths do not require authentication:

GET /health (and sub-paths like /health/metrics, /health/:serviceName)
GET /metrics (Prometheus endpoint)
POST /api/credentials/validate (read-only key validation)
GET /api/setup-token (localhost-only, onboarding token retrieval)

POST /api/credentials is not auth-exempt. It requires either a valid Authorization: Bearer <key> header (when AGTOS_API_KEY is set) or a valid X-Setup-Token header (30-minute TTL token from GET /api/setup-token, used during onboarding).

Rate Limiting

All API endpoints are rate-limited using a token bucket algorithm.

Default Limits

Scope	Limit	Configurable Via
General API (`/api/*`)	100 requests/min	`API_RATE_LIMIT`
Chat, Tasks, Credentials (`/api/chat`, `/api/tasks`, `/api/credentials`)	20 requests/min	`CHAT_RATE_LIMIT`

Rate Limit Headers

Included on all API responses:

Header	Description
`X-RateLimit-Remaining`	Tokens remaining in current window

Included on 429 Too Many Requests responses:

Header	Description
`Retry-After`	Seconds until rate limit resets
`X-RateLimit-Limit`	Maximum requests per window
`X-RateLimit-Remaining`	Always `0` on rate-limited responses
`X-RateLimit-Reset`	Seconds until rate limit resets

429 Response Body

{
  "error": "Too many requests",
  "retryAfter": 60
}

​Health

​Response

​Response

​Path Parameters

​Response

​Response

​Sessions

​Response

​Voice Status

​Response

​Memory

​Query Parameters

​Response

​Query Parameters

​Response

​Scheduler

​Response

​Request Body

​Schedule Type Examples

​Response

​Path Parameters

​Response

​Workflows

​Response

​Path Parameters

​Request Body (optional)

​Response

​System Info

​Response

​Chat

​Request Body

​Response

​Chat Streaming

​Request Body

​SSE Events

​Conversation History

​Path Parameters

​Response

​Tasks

​Request Body

​Response

​Voice Stats

​Response

​Memory Profile

​Response

​Request Body

​Response

​Memory Conclusions

​Query Parameters

​Response

​Path Parameters

​Response

​Memory Ask (Dialectic)

​Request Body

​Response

​Memory Maintenance

​Request Body

​Response

​Query Parameters

​Response

​Path Parameters

​Response

​Memory Import

​Response

​Request Body

​Response

​Entities

​Query Parameters

​Response

​Response

​Path Parameters

​Response

​Path Parameters

​Request Body

​Response

​Path Parameters

​Response

​Path Parameters

​Request Body

​Response

Health

Response

Response

Path Parameters

Response

Response

Sessions

Response

Voice Status

Response

Memory

Query Parameters

Response

Query Parameters

Response

Scheduler

Response

Request Body

Schedule Type Examples

Response

Path Parameters

Response

Workflows

Response

Path Parameters

Request Body (optional)

Response

System Info

Response

Chat

Request Body

Response

Chat Streaming

Request Body

SSE Events

Conversation History

Path Parameters

Response

Tasks

Request Body

Response

Voice Stats

Response

Memory Profile

Response

Request Body

Response

Memory Conclusions

Query Parameters

Response

Path Parameters

Response

Memory Ask (Dialectic)

Request Body

Response

Memory Maintenance

Request Body

Response

Query Parameters

Response

Path Parameters

Response

Memory Import

Response

Request Body

Response

Entities

Query Parameters

Response

Response

Path Parameters

Response

Path Parameters

Request Body

Response

Path Parameters

Response

Path Parameters

Request Body

Response