SkillsMay 11, 2026·2 min read

OpenFang — Open-Source Agent Operating System

OpenFang is an open-source Agent Operating System in Rust that runs autonomous agents as one binary with built-in sandboxing and gateways.

AI Open Source
AI Open Source · Community
Agent ready

Review-first install path

This asset needs a review step. The copied prompt tells the agent to dry-run, show the writes, then proceed only after confirmation.

Needs Confirmation · 64/100Policy: confirm
Agent surface
Any MCP/CLI agent
Kind
Skill
Install
Single
Trust
Trust: Established
Entrypoint
Asset
Review-first command
npx -y tokrepo@latest install e6513dd2-0683-4cb0-b111-1734977daae4 --target codex

Dry-run first, confirm the writes, then run this command.

Intro

OpenFang is an open-source Agent Operating System in Rust that runs autonomous agents as one binary with built-in sandboxing and gateways.

  • Best for: Developers who want a single-binary, deployable Agent OS approach (not just a chat framework) for long-running autonomous work
  • Works with: Rust-based runtime; installs via the project install script and uses official docs for getting started
  • Setup time: 20 minutes

How to Use It Well

  • Setup time ~20 minutes (install + openfang init + smallest quickstart)
  • The README calls out quantitative engineering signals (LOC/tests/version) you can use as a maturity check
  • GitHub stars + forks (verified): see Source & Thanks

Agent OS thinking shifts focus from “prompting” to “operations”: installation, sandboxing, gateways, and reproducible long-running jobs. Adopt it when you’re ready to treat agents like services with guardrails.

FAQ

Q: Is it “just another agent framework”? A: The README positions it as an Agent Operating System with a single-binary runtime and system-level concerns.

Q: How do I keep autonomy safe? A: Start in a sandboxed, least-privilege mode and add capabilities gradually with explicit approvals.

Q: What’s the first integration step? A: Follow the official Getting Started docs and validate one minimal workflow before customizing gateways/tools.

🙏

Source & Thanks

Source: https://github.com/RightNow-AI/openfang > License: Apache-2.0 > GitHub stars: 17,421 · forks: 2,224

Discussion

Sign in to join the discussion.
No comments yet. Be the first to share your thoughts.

Related Assets

OpenLLM — Serve Open-Source LLMs

Serve open-source LLMs with a unified CLI, multiple backends, and production deployment paths. Start with `openllm hello`, then serve a real model.

SkillsCLI Tools
AI Open Source

Hector — Self-Hosted Agent Runtime Binary

Run Hector as a self-hosted agent runtime: a single Go binary that serves an agent API and studio UI, keeping execution on your own infrastructure.

SkillsCLI Tools
Agent Toolkit

AgentScope Studio — Agent Tracing UI

AgentScope Studio is a local visualization toolkit: Projects/Runs UI, OpenTelemetry-based tracing, and eval dashboards for AgentScope agents.

SkillsCLI Tools
Agent Toolkit

Codeg — Local AI Coding Workspace (Tauri/Web)

Run Codeg as a standalone server or desktop app to manage local agent workflows, MCP installs, and engineering loops; one-line install is available.

SkillsCLI Tools
Script Depot
◈Home🔍Search👤Me