Openlegion
Secure autonomous AI agent framework and platform. Build AI teams by describing what you want. Orchestrate agents that can do everything a human can do.
Last verified:
What is Openlegion?
OpenLegion is a production-grade AI agent framework and platform that deploys autonomous agent fleets in isolated Docker containers. It allows users to describe the team they need—such as a marketing agency, sales team, or research desk—and automatically deploys a multi-agent fleet with roles, budgets, permissions, and vault-secured credentials locked down by default. Each agent runs in its own container with its own budget, permissions, and secrets vault, with six security layers enabled by default.
Key features include container isolation for every agent, per-agent daily and monthly budget caps with automatic hard cutoffs, a credential vault proxy where API keys and wallet private keys never exist inside containers, deterministic YAML DAG workflows for multi-agent orchestration, a fleet coordination model using blackboard + pub/sub + handoff (no CEO agent), support for 100+ LLM providers through LiteLLM, built-in stealth browser for browsing any website 24/7, persistent memory, MCP-compatible skills, and a real-time fleet dashboard showing every agent, cost, and event live. Agents can browse websites, fill out forms, write and execute code, send emails and messages, manage files, research and summarize, scrape data, qualify leads, process spreadsheets, post to social media, and trigger via Telegram, Discord, Slack, WhatsApp, or webhooks.
OpenLegion is designed for operations-heavy teams that need secure, budget-controlled AI agent fleets to automate browser, coding, research, sales, and internal workflows in production. It targets developers and enterprises who need on-premises deployment, air-gapped environment support, role-based access controls, deterministic audit trails, and per-agent cost governance. The platform works for engineering teams, sales teams, content teams, treasury teams, and any custom team configuration with any combination of roles, tools, and budgets.
Openlegion pricing
Pricing model: Freemium
Starting price is $19 per month. Every paid subscription includes a welcome bundle of LLM credits that never expire—use them from day one with no API keys needed. Users can also bring their own API keys from Anthropic, OpenAI, Google, or any of 100+ supported providers and pay those providers directly with zero markup on model usage. OpenLegion charges for the platform and infrastructure only. Free trial available for managed hosting at app.openlegion.ai—sign up, pick a template, add your LLM API key, and agents are live in minutes. 14-day money-back guarantee.
Openlegion pros
- Container-isolated multi-agent runtime with Docker containers or microVMs
- Per-agent daily and monthly budget caps with automatic hard cutoff
- Credential vault proxy—agents never see API keys or wallet keys
- Six security layers enabled by default: runtime isolation, container hardening, credential separation, permission enforcement, input validation, Unicode sanitization
- 100+ LLM providers through LiteLLM including Anthropic, OpenAI, Google, Mistral, Moonshot
- Deterministic YAML DAG workflows instead of LLM CEO agent for predictable execution
- Fleet model with blackboard + pub/sub + handoff coordination (no single point of failure)
- Built-in stealth browser that browses any website 24/7 without supervision
- No Redis, no Kubernetes, no LangChain required—only Python, Docker, and API key
- Real-time fleet dashboard showing every agent, cost, and event live
- Self-hosted on-premises deployment including air-gapped environments
- Per-agent ACL matrix controls which tools, files, and mesh operations are allowed
- Non-root user (UID 1000) with no-new-privileges, 512MB memory limit, 50% CPU cap
- Built-in team templates: Content Studio, Sales Pipeline, Deep Research, Custom Workforce
- 5,800+ tests across unit + integration + E2E with ~77,000 lines of auditable codebase
Openlegion cons
- Self-hosted version requires Python 3.10+ and Docker installation
- Docker Sandbox microVMs require Docker Desktop 4.58+ for maximum security
- Unicode sanitization only strips invisible characters at three choke points
- Conditional expressions only support single comparisons—no boolean operators
- Agent loops have hard limits: 20 iterations for tasks, 30 tool rounds for chat
- Default Docker container isolation has shared kernel—kernel exploit could escape
- BSL 1.1 license is source-available but not fully open source
- Managed hosting at app.openlegion.ai requires LLM API key for full functionality
Frequently asked questions about Openlegion
What is OpenLegion?
OpenLegion is a production-grade AI agent framework and platform that deploys autonomous agent fleets in isolated Docker containers. Each agent gets its own budget, permissions, and secrets vault—with six security layers enabled by default. It requires only Python, Docker, and an API key. No Redis, no Kubernetes, no LangChain. Licensed under BSL 1.1 (source-available). OpenLegion is both: a Python framework for authoring agents and a self-hosted platform for running them in production with security and cost governance built in.
Do I need to be a developer to use OpenLegion?
No. The managed hosting at app.openlegion.ai requires no coding—start a free trial, pick a template, add your LLM API key, and your agents are live in minutes. The self-hosted version requires Python 3.10+ and Docker. Either way, the built-in team templates (Dev Team, Sales Pipeline, Content Studio) work out of the box with no configuration needed.
Do I pay for LLM usage on top of the subscription?
Every paid subscription includes a welcome bundle of LLM credits that never expire—use them from day one with no API keys needed. You can also bring your own API keys from Anthropic, OpenAI, Google, or any of 100+ supported providers and pay those providers directly with zero markup on model usage. OpenLegion charges for the platform and infrastructure only.
What kinds of tasks can OpenLegion agents actually automate?
Any task a human performs on a computer with a browser or terminal. Agents can browse and interact with any website, log into web applications, fill out forms, extract data from any page, send emails and messages, manage files and folders, write and execute code, process documents, post to social platforms, monitor pages for changes, and run custom automations—all 24/7 without supervision. Common deployments include sales outreach pipelines, competitive research, lead qualification, developer workflows, invoice processing, content production, and internal task automation.
How does OpenLegion handle API key security?
Through the vault proxy—agents never see API keys. Keys are held in the mesh process on the mesh host. When an agent calls an LLM, the request goes through a vault proxy that injects the credential at the network layer, tracks token usage, and enforces budget limits. Even a fully compromised agent cannot access your API keys. The credential vault uses a two-tier prefix system: OPENLEGION_SYSTEM_* for LLM provider keys (never agent-accessible) and OPENLEGION_CRED_* for agent-tier tool/service keys (access controlled per-agent).
Can I run OpenLegion in production?
Yes—OpenLegion is designed for production deployment. It includes on-premises support, a fleet model with blackboard + pub/sub + handoff coordination, per-agent cost governance, a per-agent permission matrix, credential isolation via vault proxy, and an auditable codebase of ~77,000 lines with 5,800+ tests. Defense-in-depth controls are enabled by default.
How is OpenLegion different from CrewAI or other agent frameworks?
OpenLegion container-isolates every agent, proxies all credentials through a vault, and enforces per-agent budgets—most frameworks don't. CrewAI and similar frameworks run agents in shared processes with no isolation, no cost controls, and API keys stored in config files. OpenLegion uses deterministic YAML workflows instead of letting an LLM decide task routing, making execution predictable and auditable.
What LLM providers does OpenLegion support?
100+ LLM providers through LiteLLM. This includes Anthropic (Claude), OpenAI (GPT), Google (Gemini), Mistral, Moonshot, and any OpenAI-compatible API. You can assign different models to different agents in the same fleet—no vendor lock-in.
Do I need Kubernetes or cloud infrastructure to run OpenLegion?
No. OpenLegion runs on a single machine with no external services. You need only Python 3.10+, Docker, and an LLM API key—no Redis, no Kubernetes, no LangChain, no external databases. The full stack runs entirely on your own infrastructure with no external dependencies beyond Docker and Python.
Can OpenLegion run on-premises in air-gapped environments?
Yes. The full stack runs entirely on your own infrastructure with no external dependencies beyond Docker and Python. No data leaves your network. The coordinator, agents, vault, and dashboard all run on a single machine, making it suitable for air-gapped, regulated, and on-premises environments.