Build skills, bundle as OpenClaw

A skill isn't a prompt template — it's a full sandboxed computer. System packages, network policies, tool permissions, MCP servers, and integrations, all bundled into one installable unit.

Getting Started
paste into Claude Code, Codex, or your agent
my-agent/lobu dev
$ lobu dev -d
[gateway] listening on :8080
[gateway] connected to Redis
[gateway] Telegram connection "Support" connected
[telegram] message from Alice Chen to Support: "Can you share the latest incident update?"
[gateway] launching sandbox for chat:8291045832
[sandbox] loading agent, skills, and connection config
[sandbox] session resumed from /workspace
[sandbox] handing message to the Support agent
[sandbox] sending response (118 tokens)
[gateway] sandbox scaled to zero (idle 30s)

Define your agent in files

Each skill declares its own packages, network access, tool permissions, and auth — the platform provisions a matching sandbox automatically.

identity

IDENTITY.md

Who the agent is — persona, name, tone.

rules

SOUL.md

Behavior rules. What the agent should always or never do.

context

USER.md

User-specific context — timezone, preferences.

config

lobu.toml

Providers, skills, network policy, platforms.

[agents.acme-support]
name = "acme-support"
description = "Customer support agent for Acme Corp"
dir = "./agents/acme-support"

# LLM providers (order = priority)
[[agents.acme-support.providers]]
id = "groq"
key = "$GROQ_API_KEY"

[[agents.acme-support.providers]]
id = "gemini"
key = "$GEMINI_API_KEY"

# Platform connection
[[agents.acme-support.connections]]
type = "telegram"
[agents.acme-support.connections.config]
botToken = "$TELEGRAM_BOT_TOKEN"

# Skills from the registry
[agents.acme-support.skills]
enabled = ["github", "google-workspace"]

# Custom MCP server
[agents.acme-support.skills.mcp.my-kb]
url = "https://mcp.acme.com/sse"

# Network sandbox
[agents.acme-support.network]
allowed = ["api.github.com", "registry.npmjs.org"]
skills

skills/ops-triage.md

Third-party app integrations, MCP, and sandbox config.

---
name: Ops Triage
description: Triage inbox, PRs, and issues

integrations:
  - id: google
    authType: oauth
  - id: linear
    authType: api-key

mcpServers:
  github-mcp:
    url: https://github-mcp.example.com
    type: sse

nixConfig:
  packages: [jq, gh, ripgrep]

networkConfig:
  allowedDomains:
    - api.github.com
    - gmail.googleapis.com
    - .linear.app
  deniedDomains:
    - "*.malicious.com"

toolsConfig:
  allowedTools:
    - Read
    - Bash(git:*)
    - mcp__github__*
  deniedTools:
    - Bash(rm:*)
    - DeleteFile
  strictMode: true
---

# Ops Triage

Prioritize by severity. Summarize blockers
first, then open reviews.

## Behavior
- Check inbox for urgent emails
- Review open PRs and flag blockers
- Summarize Linear issues by priority

## Rules
- Never auto-close issues without approval
- Always include links to source threads
- Escalate P0 issues immediately
lobu devRun locally|lobu launchDeploy to cloud →

A skill is a full computer

nix

System Packages

Declare Nix packages your skill needs (ffmpeg, poppler, gh, ripgrep). Installed once, persisted across sessions. Your agent gets a real Linux environment.

network

Network Policy

Agents start with zero internet access. Skills declare exactly which domains are allowed — nothing else gets through.

permissions

Tool Permissions

Allowlist and denylist which tools the agent can use. Bash commands, file operations, MCP tools — all scoped per skill.

mcp

MCP Servers

Connect to external APIs via MCP. Auth is handled by the gateway — workers never see real credentials.

api

Integrations

OAuth and API-key authenticated services. Users connect their own accounts via the settings page.

prompt

Instructions

System prompt, behavioral rules, and domain knowledge. The markdown body of SKILL.md becomes the agent's persona.

Any vertical, one platform

Build skills for your domain and ship them on Lobu. Users get a ready-made agent without touching infrastructure.

Legal

Draft contracts, search case law, review clauses

westlaw-mcpcontract-draftercase-search

DevOps

Triage PRs, manage incidents, deploy services

github-mcppagerduty-mcpk8s-tools

Support

Route tickets, draft responses, escalate issues

zendesk-mcpknowledge-basesentiment

Finance

Reconcile accounts, generate reports, flag anomalies

quickbooks-mcpstripe-mcpcsv-tools

Built-in registry

System skills ship with every agent. Agents discover and install additional skills via SearchSkills / InstallSkill— users approve through a prefilled settings link.

oauth

Integrations

GoogleGitHubMicrosoft 365NotionLinearJiraSentry
mcp

Memory

Owletto
api-key

LLM Providers

OpenAIGroqGeminiTogether AINVIDIA NIMz.aiFireworksMistralDeepSeekOpenRouterCerebrasOpenCode ZenxAIPerplexityCohereElevenLabs

Start building skills

Define your vertical. Bundle your integrations. Ship it on Lobu.