OpenFang is a Rust-based agent operating system (RightNow-AI/openfang). Installed via the upstream curl script, runs as a systemd service, and auto-wires to a co-deployed Ollama box via the [default_model] section of openfang.toml.
Every EasyEnv recipe spins up in seconds on a real Linux VM-not a stripped-down sandbox. The OpenFang recipe is provisioned by an open Ansible role, so the machine that boots for you is reproducible, inspectable, and matches what you would get in production.
$ easyenv workspace create --recipe openfang --name openfang-demo
Provisioning OpenFang...
Workspace ready in ~45s
$ easyenv workspace ssh openfang-demo
Connected. You're on the machine.Stop guessing from resumes. Drop candidates into a real OpenFang workspace, watch them debug, deploy and operate it, score the result automatically, and replay the session. We also evaluate how they work with AI.
Builds and deploys AI applications, integrates LLMs into products, and manages self-hosted AI infrastructure
Develops and deploys machine learning models and AI systems for production environments
Self-hosted LLM inference with Ollama and OpenWebUI for private AI workloads
Self-hosted AI document assistant powered by AnythingLLM and Ollama
Automated AI workflows combining LLMs with n8n orchestration and PostgreSQL