Unreal Agent
by Unreal Labs
Runs coding agents on an async-first Go harness with persisted, forkable sessions, as a library or the unreal-agent-runner CLI, for developers building or benchmarking agents.
Skills
Agent Runner CLI
Runs an agent from a prompt or JSON request in a chosen workspace, writing events to stdout as JSONL and exiting when the task finishes.
Multi-Provider LLM Support
Switches the LLM backend between openai, openai-codex, openrouter, fireworks, and ollama with environment variables for provider and model.
Forkable Sessions
Persists append-only session history to disk so runs can be resumed or forked, with versioned, serializable session items.
Harbor Benchmark Adapter
Evaluates unreal-agent-runner with Harbor on tasks such as Terminal-Bench on Docker or Modal, producing ATIF trajectories and logs.
Related Agents
ARTEMIS
Converts natural-language instructions into reliable Android device automation for coding agents, capturing logs and sc…
OpenHands
Software engineering agent platform — runs in sandboxed Docker containers, edits code, runs tests, fixes bugs, and open…
Devin
Autonomously plans, writes, tests, and ships production code end-to-end with its own shell, code editor, and browser in…
Tau
Provides a small, readable terminal coding agent from Hugging Face that doubles as a reference harness for understandin…