API Reference

The LVNG REST API lets you programmatically interact with every part of the platform. Manage agents, orchestrate workflows, send messages, and build intelligent applications with a consistent, well-documented interface.

Base URL

All API requests are made to the following base URL. HTTPS is required for all requests.

https:400">class="text-zinc-500">//api.lvng.ai/api

Versioning

The API is versioned via path prefix. The current stable version is v2. Version 1 endpoints are deprecated and will be removed in a future release.

Current stable version. All new features land here.

Deprecated. Will be sunset Q3 2026.

Content Type

All requests and responses use JSON. Set the Content-Type header on every request that includes a body.

Content-Type: application/json

Authentication

All endpoints require a Bearer token in the Authorization header. You can generate API keys from the Settings page in the LVNG dashboard.

Authenticated request

400">curl -X 400">GET https:400">class="text-zinc-500">//api.lvng.ai/api/v2/agents \
  -H 400">class="text-emerald-400">"Authorization: Bearer YOUR_API_KEY" \
  -H 400">class="text-emerald-400">"Content-Type: application/json"

Requests without a valid token receive a 401 Unauthorized response.

Response Format

All responses follow a consistent envelope structure. Successful responses include a data field. Error responses include an error field with a human-readable message.

Success response

{
  400">class="text-emerald-400">"success": true,
  400">class="text-emerald-400">"data": {
    400">class="text-emerald-400">"id": 400">class="text-emerald-400">"agt_a1b2c3d4",
    400">class="text-emerald-400">"name": 400">class="text-emerald-400">"Research Agent",
    400">class="text-emerald-400">"status": 400">class="text-emerald-400">"active"
  }
}

Error response

{
  400">class="text-emerald-400">"success": false,
  400">class="text-emerald-400">"error": 400">class="text-emerald-400">"Agent not found"
}

Rate Limiting

API requests are rate-limited per API key. Rate limit information is returned in response headers.

Rate limit headers

X-RateLimit-Limit: 1000
X-RateLimit-Remaining: 997
X-RateLimit-Reset: 1711843200

If you exceed the limit, you will receive a 429 Too Many Requests response. Wait until the reset timestamp before retrying.

API Resources

Chat

2 endpoints

Send messages to AI and stream responses via Server-Sent Events.

Messages

12 endpoints

Create, read, update, and delete messages within channels. Threads, reactions, file uploads, and AI summarization.

Channels

17 endpoints

Manage channels, members, digital twins, and pinned messages.

Workspaces

16 endpoints

Manage workspaces, team members, roles, permissions, and settings.

Agents

11 endpoints

Create, configure, and control AI agents with custom capabilities and tools.

Workflows

16 endpoints

Build, execute, and schedule multi-step automation workflows.

Digital Twins

5 endpoints

Add and manage AI personas (digital twins) in your workspace.

Artifacts

12 endpoints

Store and manage AI-generated artifacts with versioning and review.

Knowledge

11 endpoints

Ingest, search, and analyze content across a unified knowledge graph.

Canvas

7 endpoints

Visual canvas cards and folders for spatial organization.

Calendar

6 endpoints

Unified calendar across Google and Microsoft with event CRUD and availability.

Voice Notes

7 endpoints

Audio recording, transcription via Whisper, and voice note management.

Search

1 endpoints

Unified semantic search across notes, channels, messages, and knowledge.

Settings

7 endpoints

User and workspace settings with import/export support.

Integrations

11 endpoints

Platform integrations for Discord, Slack, and Teams with channel sync.

Conversations

10 endpoints

Direct messages, group conversations, read receipts, and member management.

HTTP Methods

The API uses standard HTTP methods for CRUD operations.

Method	Description
GET	Retrieve a resource or list of resources
POST	Create a new resource or trigger an action
PUT	Replace a resource entirely
PATCH	Partially update a resource
DELETE	Remove a resource

Pagination

List endpoints support cursor-based pagination using limit and before parameters. The default page size is 50 items. Maximum is 100.

Paginated request

400">curl -X 400">GET 400">class="text-emerald-400">"https:400">class="text-zinc-500">//api.lvng.ai/api/v2/messages?channel_id=ch_abc123&limit=25&before=2026-03-01T00:00:00Z" \
  -H 400">class="text-emerald-400">"Authorization: Bearer YOUR_API_KEY"