Documentation, API reference, community guides, and structured learning paths for every skill level.
Comprehensive docs covering installation, configuration, deployment, and advanced usage.
First-time setup guide. Hardware requirements, installation methods, and your first model run.
Read docs →Complete endpoint documentation for the router, agents, workflow engine, and dashboard APIs.
Browse API →Bare metal, Docker, Kubernetes, cloud GPUs, and Live ISO. Step-by-step instructions for each.
View guide →Symptom-based quick reference. GPU not detected? CUDA OOM? Port conflicts? Find fixes fast.
Search fixes →CUDA optimization, VRAM management, quantization strategies, and benchmarking methodologies.
Optimize GPU →Mermaid diagrams of the router flow, SDLC pipeline, workflow engine, and settings propagation.
See diagrams →Follow a guided path from beginner to advanced operator.
Install FreeAI, run your first model, use the dashboard, chat with an agent. ~30 minutes.
Start here →Build workflows, use SDLC automation, configure external providers, set up alerting. ~2 hours.
Level up →GPU tuning, custom agent development, router backend plugins, cloud GPU deployments. ~6 hours.
Go deep →Join the community, report issues, share skills, and help shape the project.
Ask questions, share ideas, request features, and connect with other FreeAI users.
Join forum →Found an issue? Open a GitHub issue with reproduction steps and environment details.
File issue →Create and share MCP servers, security skills, and agent configurations with the community.
Contribute →