Frequently asked questions

No. The managed hosting at app.openlegion.ai requires no coding — sign up, 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.

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.

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.

OpenLegion is a production-grade, container-isolated multi-agent runtime that deploys autonomous agent fleets in isolated Docker containers. Each agent gets its own budget, permissions, and credential vault — with defense-in-depth via container isolation, vault proxy, per-agent ACLs, and bounded execution. It requires only Python, Docker, and an API key. No Redis, no Kubernetes, no LangChain. Licensed under PolyForm Perimeter License 1.0.1 (source-available).

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 a fleet model (no CEO agent) with blackboard coordination and structured handoff — no LLM in the control plane deciding task routing.

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.

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.

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.

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.

Yes. The engine runs on a single machine with Python + Docker, no external services required. For fully local inference, point the LLM provider at Ollama; for hosted models (Anthropic, OpenAI, Google, etc.) the mesh proxy reaches out to whichever provider you configure. Mesh host, agents, vault, and dashboard all run on the same machine.

An AI agent framework is the runtime and library layer for deploying, coordinating, and governing autonomous AI agents in production. Unlike raw SDK libraries that only provide agent logic primitives, a framework like OpenLegion handles container isolation, credential vaulting, per-agent cost controls, observability, and deployment — so teams can ship agents without building DevOps from scratch.

A framework is a code library and runtime for building and running agent logic — tools, prompts, memory, coordination. Managed hosting adds an operational layer on top: dedicated VPS provisioning, dashboard, billing, and credit proxy. OpenLegion is both: a Python framework (container-isolated multi-agent runtime) for authoring and running agents, and an optional managed hosting service for teams that don't want to manage infrastructure.

OpenLegion uses a fleet model — blackboard + pub/sub + handoff (no CEO agent). Agents coordinate through a SQLite-backed blackboard with atomic compare-and-set, a pub/sub event bus, and a structured handoff protocol. Each agent has its own permissions, budget, and tool set. Users talk to agents directly; there is no LLM in the control plane deciding task routing.

AI agent security addresses the unique threats autonomous agents introduce: credential leakage, prompt injection, resource abuse, and data exfiltration. OpenLegion's defense-in-depth — container isolation, credential vault proxy, per-agent permission matrix, input sanitization, SSRF protection, and Unicode/path-traversal hardening — mitigates each threat independently, so a breach in one layer does not compromise the others.