The Agent
Operating System
Open-source Agent OS built in Rust. 7 autonomous Hands that run on schedules, build knowledge graphs, and report to your dashboard. 30 agents, 40 channels, 38 tools, 26 LLM providers. 16 security systems. One binary.
137K lines of Rust · 16.8k★ on GitHub
curl -fsSL https://openfang.sh/install | shcurl -fsSL https://openfang.sh/update | shEverything in one binary
Nine primitives that ship compiled together — hands, agents, tools, security, memory, channels, protocols, and a native desktop app.
7 Autonomous Capability Packages
Pre-built agents that work FOR you. Clip turns video into shorts. Lead generates qualified leads. Collector monitors targets. Predictor forecasts with Brier scores. Researcher fact-checks with CRAAP. Twitter manages your X account. Browser automates the web. Activate, configure, check your dashboard.
16 Security Systems
WASM dual-metered sandbox, Ed25519 manifest signing, Merkle audit trail, taint tracking, SSRF protection, secret zeroization, HMAC-SHA256 mutual auth, GCRA rate limiter, subprocess isolation, prompt injection scanner, path traversal prevention, and more.
Sandboxed Execution
Tool code runs inside WASM with dual metering (fuel + epoch interruption). File operations are workspace-confined. Subprocesses are env-cleared and timeout-enforced. 10-phase graceful shutdown.
30 Pre-Built Agents
From orchestrators to code reviewers to customer support. Four performance tiers across Anthropic, Gemini, Groq, and DeepSeek. Spawn one in a single command.
38 Built-In Tools + MCP
38 native tools plus Model Context Protocol client and server. Connect external MCP servers and expose OpenFang tools to other agents. Includes web search, browser automation, image generation, TTS, Docker, knowledge graphs.
Persistent Memory
SQLite-backed storage with vector embeddings. Cross-channel canonical sessions, automatic LLM-based compaction, and JSONL session mirroring. Agents recall context across conversations and channels.
40 Channel Adapters
Telegram, Discord, Slack, WhatsApp, Teams, IRC, Matrix, and 33 more. Per-channel model overrides, DM/group policies, rate limiting, and output formatting. One agent, every platform.
MCP + A2A + OFP
Model Context Protocol (client + server), Google A2A agent-to-agent tasks, and OpenFang Protocol for P2P networking with HMAC-SHA256 mutual authentication. Your agents talk to the world.
Tauri 2.0 Native App
Native desktop application with system tray, notifications, single-instance enforcement, auto-start on login, and global shortcuts. Full dashboard in a native window.
OpenFang versus the landscape
Ten dimensions, six frameworks. Measured from official docs and public repos.
Measured, not marketed
Cold start, idle memory, install size, security depth, channel coverage, and provider support — across six leading agent frameworks.
Agents that work for you
Hands are pre-built autonomous capability packages. Unlike agents you chat with, Hands run on schedules, build knowledge graphs, and report to your dashboard.
Traditional agents wait for you to type. Hands work for you.
Each Hand bundles a HAND.toml manifest, a multi-phase system prompt, SKILL.md expert knowledge, settings, and dashboard metrics — compiled into the binary at build time.
Clip.hand
Turns long-form video into viral short clips with captions, thumbnails, and optional AI voice-overs. Publishes to Telegram and WhatsApp.
Lead.hand
Autonomous lead generation. Discovers, enriches, scores, and deduplicates qualified leads on a daily schedule. Builds ICP profiles and knowledge graphs.
Collector.hand
OSINT-style intelligence collector. Monitors any target continuously with change detection, sentiment tracking, and knowledge graph construction.
Predictor.hand
Superforecasting engine. Collects signals, builds calibrated reasoning chains, makes predictions, and tracks accuracy with Brier scores.
Researcher.hand
Deep autonomous researcher. Cross-references sources, fact-checks claims with CRAAP evaluation, and generates cited reports in multiple languages.
Twitter.hand
Autonomous Twitter/X manager. Creates content in 7 rotating formats, schedules posts, engages with mentions, and tracks performance metrics.
Browser.hand
Web automation agent. Navigates sites, fills forms, clicks buttons, and completes multi-step workflows. Mandatory purchase approval gate.
Build your own.hand
Define a HAND.toml with tools, settings, requirements, and a system prompt. Publish it to FangHub.
Hand development guide→Recipes for every use case
Guides, references, and examples to help you build with OpenFang.
Quick Start Guide
Install OpenFang and spawn your first agent in under 2 minutes.
Architecture Overview
14-crate Rust workspace, kernel design, and subsystem overview.
Configuration Reference
Every config.toml field, 62 environment variables, validation rules.
Security Model
16 security systems: WASM sandbox, taint tracking, audit trail, SSRF protection.
LLM Providers
26 providers, 50+ models, cost rates, and intelligent routing.
40 Channel Adapters
Connect agents to Telegram, Discord, Slack, WhatsApp, and 36 more platforms.
Agent Templates
30 pre-built agents across 4 performance tiers, ready to deploy.
Hands System
7 autonomous capability packages. Activate, configure, and let them work for you.
Skill Development
60 bundled skills, SKILL.md format, FangHub marketplace.
Workflow Engine
Multi-agent pipelines with fan-out, conditional, and loop step modes.
MCP & A2A Protocols
Model Context Protocol and Agent-to-Agent communication.
REST API Reference
140+ endpoints — agents, memory, workflows, channels, models, skills, A2A, hands.
RightNow LabsOpenFang is built by the founders of RightNow Labs.