Lobstack is a managed cloud platform for deploying autonomous AI agents. Each agent runs on a dedicated virtual machine with persistent memory, 117+ integrations, and goes live in under 90 seconds with zero DevOps.

How long does it take to deploy an AI agent?

You can deploy an AI agent on Lobstack in under 90 seconds. Describe what your agent should do, pick a model, and Lobstack handles all the infrastructure — no Docker, Kubernetes, or server setup needed.

What AI models does Lobstack support?

Lobstack supports 24 AI models including Claude Opus and Sonnet from Anthropic, GPT-5 and GPT-4o from OpenAI, Gemini 2.5 Pro from Google, plus DeepSeek, Mistral, and Grok. You can hot-swap models without losing agent memory or configuration.

Is Lobstack secure for enterprise use?

Yes. Every agent runs in a gVisor-sandboxed VM with AES-256 encryption at rest, TLS 1.3 in transit, HashiCorp Vault for secrets, row-level security on all tables, and full audit logging. Lobstack is SOC 2 aligned.

Docs/API Reference/API Overview

Reference

API Reference

REST API endpoints for programmatic access to your Lobstack agent. Send messages, manage sessions, configure skills, and more.

📝

Authentication

The management endpoints below are authenticated via secure session cookies (the dashboard handles this automatically). The Lobstack Gateway uses a per-agent bearer token instead — see below.

Lobstack Gateway (OpenAI-compatible)#

The primary way to call your agent's model programmatically. The Gateway speaks the OpenAI Chat Completions format, so it drops into any existing SDK or tool — just change the base URL and key. Pass "model": "auto" to run Lobstack 1.2 (Token Intelligence picks the best engine per message), or any supported model id. See the full Gateway guide.

POST /api/gateway/v1/chat/completions

curl https://lobstack.ai/api/gateway/v1/chat/completions \
  -H "Authorization: Bearer $LOBSTACK_AGENT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [{ "role": "user", "content": "Summarize today’s support tickets." }]
  }'

Responses are OpenAI-shaped and include routing headers — x-lobstack-model (the engine chosen), x-lobstack-tier, x-lobstack-cost-usd, and x-lobstack-savings — so you see exactly what ran. List available models with GET /api/gateway/v1/models.

Agent Status#

Get the current status of your agent, including server details, usage metrics, and optional related data.

GET /api/agent/status

curl -b "sb-access-token=YOUR_TOKEN" \
  "https://lobstack.ai/api/agent/status?include=messages,skills,logs,health"

Response Fields#

Field	Type	Description
agent.id	string	Unique agent instance ID
agent.status	string	running, provisioning, or error
agent.server_ip	string	VM IP address
agent.server_tier	string	starter, standard, performance, enterprise
agent.server_region	string	us-east, us-west, eu-central, eu-north, ap-south
agent.ai_model	string	Current AI model identifier
agent.messages_used	number	Messages used this billing period
agent.messages_limit	number	Monthly message limit for current plan
agent.plan_tier	string	Subscription plan tier
messages	array	Recent messages (when include=messages)
skills	array	Enabled skills (when include=skills)

Chat#

Send a message to your agent and receive a response. The agent may execute tools during processing.

POST /api/agent/chat

curl -X POST -H "Content-Type: application/json" \
  -b "sb-access-token=YOUR_TOKEN" \
  -d '{"message": "What is running on this server?", "session_id": "abc123"}' \
  "https://lobstack.ai/api/agent/chat"

Parameter	Type	Required	Description
message	string	Yes	The user message to send
session_id	string	No	Session ID for conversation isolation
images	array	No	Base64 image data for multimodal analysis

Sessions#

List Sessions#

GET /api/agent/sessions

curl -b "sb-access-token=YOUR_TOKEN" \
  "https://lobstack.ai/api/agent/sessions"

Create Session#

POST /api/agent/sessions

curl -X POST -H "Content-Type: application/json" \
  -b "sb-access-token=YOUR_TOKEN" \
  -d '{"title": "Debug Session", "category": "task"}' \
  "https://lobstack.ai/api/agent/sessions"

Update Session#

Update session metadata — title, category, status, icon, or pinned state. At least one field is required.

PATCH /api/agent/sessions

curl -X PATCH -H "Content-Type: application/json" \
  -b "sb-access-token=YOUR_TOKEN" \
  -d '{"sessionId": "abc123", "category": "research", "pinned": true}' \
  "https://lobstack.ai/api/agent/sessions"

Parameter	Type	Description
sessionId	string	Session ID to update (required)
title	string	New session title (max 100 chars)
category	string	general, task, research, support, automation, creative, or debug
status	string	active, completed, paused, or archived
icon	string	Custom icon for the session
pinned	boolean	Pin session for quick access

Delete Session#

DELETE /api/agent/sessions

curl -X DELETE -H "Content-Type: application/json" \
  -b "sb-access-token=YOUR_TOKEN" \
  -d '{"sessionId": "abc123"}' \
  "https://lobstack.ai/api/agent/sessions"

Skills#

Get Enabled Skills#

GET /api/agent/skills

curl -b "sb-access-token=YOUR_TOKEN" \
  "https://lobstack.ai/api/agent/skills"

Enable/Disable Skill#

POST /api/agent/skills

curl -X POST -H "Content-Type: application/json" \
  -b "sb-access-token=YOUR_TOKEN" \
  -d '{"skill": "discord", "enabled": true}' \
  "https://lobstack.ai/api/agent/skills"

Configure Skill Credentials#

PUT /api/agent/skills

curl -X PUT -H "Content-Type: application/json" \
  -b "sb-access-token=YOUR_TOKEN" \
  -d '{"skill": "discord", "config": {"discord_token": "MTk...", "discord_app_id": "123..."}}' \
  "https://lobstack.ai/api/agent/skills"

Memory#

GET /api/agent/memory

curl -b "sb-access-token=YOUR_TOKEN" \
  "https://lobstack.ai/api/agent/memory"

POST /api/agent/memory (Create)

curl -X POST -H "Content-Type: application/json" \
  -b "sb-access-token=YOUR_TOKEN" \
  -d '{"key": "timezone", "value": "America/New_York", "category": "user_pref"}' \
  "https://lobstack.ai/api/agent/memory"

Token Budget#

Get token budget status or request a model routing recommendation based on message complexity.

GET /api/agent/token-budget

curl -b "sb-access-token=YOUR_TOKEN" \
  "https://lobstack.ai/api/agent/token-budget"

POST /api/agent/token-budget

curl -X POST -H "Content-Type: application/json" \
  -b "sb-access-token=YOUR_TOKEN" \
  -d '{"message": "What time is it?"}' \
  "https://lobstack.ai/api/agent/token-budget"

Chat Automation#

Create workflows from natural language commands. Used by slash commands like /automate, /schedule, /trigger, and /remind.

POST /api/agent/chat-automate

curl -X POST -H "Content-Type: application/json" \
  -b "sb-access-token=YOUR_TOKEN" \
  -d '{"command": "schedule", "text": "every day at 9am check inventory"}' \
  "https://lobstack.ai/api/agent/chat-automate"

Parameter	Type	Description
command	string	automate, schedule, trigger, remind, or status
text	string	Natural language description of the automation

Update Agent Settings#

Change AI model, messenger, server tier, or region. Triggers a full VM rebuild.

POST /api/agent/update

curl -X POST -H "Content-Type: application/json" \
  -b "sb-access-token=YOUR_TOKEN" \
  -d '{"aiModel": "claude-opus-4-6"}' \
  "https://lobstack.ai/api/agent/update"

Parameter	Type	Description
aiModel	string	AI model to switch to
messengerType	string	Messenger channel (web, telegram, discord, slack, whatsapp)
serverTier	string	Server tier (starter, standard, performance, enterprise)
serverRegion	string	Server region (us-east, us-west, eu-central, eu-north, ap-south)
aiApiKey	string	Your own AI provider API key (optional)

Config Files Overview