OpenFang

Normal
GitHub Rust Apache-2.0

Description

Open-source Agent Operating System.

Key Features

  • 7 bundled Hands: Clip, Lead, Collector, Predictor, Researcher, Twitter, Browser
  • Hands run autonomously on schedules without manual prompting
  • 137K LOC Rust, 1,767+ tests, zero clippy warnings
  • Single binary deployment (~32MB), 180ms cold start
  • Built-in safety guardrails: browser purchase approval gates for sensitive operations
  • 16 security systems, custom HAND.toml capability packages

Use Cases

💡 Automated competitor monitoring and intelligence gathering (Collector Hand)
💡 Daily prospect discovery and scoring (Lead Hand)
💡 Autonomous content creation and social media management (Twitter/Clip Hand)
💡 Deep research and cited report generation (Researcher Hand)

Strengths & Limitations

Strengths

  • High community interest (18.2k stars)
  • Permissive open-source license (Apache-2.0)
  • Responsive to issues, low backlog

Quick Start

Run the install script: curl -fsSL https://openfang.sh/install | sh, then execute openfang init && openfang start, dashboard will be live at http://localhost:4200.

Related Projects

fast-agent

3.9k · Python
Active A+

Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP Support.

agent-frameworkmcpskills +1
  • · CLI-first interactive agent framework with prompt_toolkit-powered TUI, shell completions, and streaming responses via Rich
  • · Complete MCP feature support including Sampling and Elicitations — the first framework with end-to-end tested MCP integration
  • · Declarative agent definition with minimal boilerplate — define agents via @fast.agent decorator and compose prompts with MCP servers

FIM One

1.5k · Python
Active A

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

enterprisemcprag +2
  • · All-in-one agent platform — Standalone assistant, embedded Copilot, or central Hub in one agent core
  • · Cross-border system connectivity — connects global SaaS and China stack (Feishu, WeCom, DingTalk, DM, Kingbase) via one pattern
  • · Dynamic DAG planning — LLM decomposes goals into dependency graphs at runtime with parallel execution

Yu AI Agent

2.6k · Java
Stale C

A hands-on Java and Spring AI project for building AI agents with RAG, tool calling, MCP, and ReAct-style autonomous planning.

spring-aireactrag +2
  • · Spring AI + LangChain4j — full-stack Java AI agent development with Spring Boot 3 and Java 21
  • · RAG knowledge base — end-to-end retrieval-augmented generation with PgVector and document processing
  • · Tool Calling — implement web search, file operations, PDF generation, and terminal commands as tools