RightNow AI/openfang

v0.3.30 — Security Hardening Release (March 2026)

OpenFang is feature-complete but still pre-1.0. You may encounter rough edges or breaking changes between minor versions. We ship fast and fix fast. Pin to a specific commit for production use until v1.0. Report issues here.

What is OpenFang?

OpenFang is an open-source Agent Operating System — not a chatbot framework, not a Python wrapper around an LLM, not a "multi-agent orchestrator." It is a full operating system for autonomous agents, built from scratch in Rust.

Traditional agent frameworks wait for you to type something. OpenFang runs autonomous agents that work for you — on schedules, 24/7, building knowledge graphs, monitoring targets, generating leads, managing your social media, and reporting results to your dashboard.

The entire system compiles to a single ~32MB binary. One install, one command, your agents are live.

curl -fsSL https://openfang.sh/install | sh
openfang init
openfang start
# Dashboard live at http://localhost:4200

irm https://openfang.sh/install.ps1 | iex
openfang init
openfang start

Hands: Agents That Actually Do Things

Hands are OpenFang's core innovation — pre-built autonomous capability packages that run independently, on schedules, without you having to prompt them. This is not a chatbot. This is an agent that wakes up at 6 AM, researches your competitors, builds a knowledge graph, scores the findings, and delivers a report to your Telegram before you've had coffee.

Each Hand bundles:

• HAND.toml — Manifest declaring tools, settings, requirements, and dashboard metrics
• System Prompt — Multi-phase operational playbook (not a one-liner — these are 500+ word expert procedures)
• SKILL.md — Domain expertise reference injected into context at runtime
• Guardrails — Approval gates for sensitive actions (e.g. Browser Hand requires approval before any purchase)

All compiled into the binary. No downloading, no pip install, no Docker pull.

The 7 Bundled Hands

# Activate the Researcher Hand — it starts working immediately
openfang hand activate researcher

# Check its progress anytime
openfang hand status researcher

# Activate lead generation on a daily schedule
openfang hand activate lead

# Pause without losing state
openfang hand pause lead

# See all available Hands
openfang hand list

Build your own. Define a HAND.toml with tools, settings, and a system prompt. Publish to FangHub.

OpenFang vs The Landscape

Benchmarks: Measured, Not Marketed

All data from official documentation and public repositories — February 2026.

Cold Start Time (lower is better)

ZeroClaw   ██░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░   10 ms
OpenFang   ██████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░  180 ms    ★
LangGraph  █████████████████░░░░░░░░░░░░░░░░░░░░░░░░░  2.5 sec
CrewAI     ████████████████████░░░░░░░░░░░░░░░░░░░░░░  3.0 sec
AutoGen    ██████████████████████████░░░░░░░░░░░░░░░░░  4.0 sec
OpenClaw   █████████████████████████████████████████░░  5.98 sec

Idle Memory Usage (lower is better)

ZeroClaw   █░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░    5 MB
OpenFang   ████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░   40 MB    ★
LangGraph  ██████████████████░░░░░░░░░░░░░░░░░░░░░░░░░  180 MB
CrewAI     ████████████████████░░░░░░░░░░░░░░░░░░░░░░░  200 MB
AutoGen    █████████████████████████░░░░░░░░░░░░░░░░░░  250 MB
OpenClaw   ████████████████████████████████████████░░░░  394 MB

Install Size (lower is better)

ZeroClaw   █░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░  8.8 MB
OpenFang   ███░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░   32 MB    ★
CrewAI     ████████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░  100 MB
LangGraph  ████████████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░  150 MB
AutoGen    ████████████████░░░░░░░░░░░░░░░░░░░░░░░░░░░  200 MB
OpenClaw   ████████████████████████████████████████░░░░  500 MB

Security Systems (higher is better)

OpenFang   ████████████████████████████████████████████   16      ★
ZeroClaw   ███████████████░░░░░░░░░░░░░░░░░░░░░░░░░░░░    6
OpenClaw   ████████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░    3
AutoGen    █████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░    2
LangGraph  █████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░    2
CrewAI     ███░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░    1

Channel Adapters (higher is better)

OpenFang   ████████████████████████████████████████████   40      ★
ZeroClaw   ███████████████░░░░░░░░░░░░░░░░░░░░░░░░░░░░   15
OpenClaw   █████████████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░   13
CrewAI     ░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░    0
AutoGen    ░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░    0
LangGraph  ░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░    0

LLM Providers (higher is better)

ZeroClaw   ████████████████████████████████████████████   28
OpenFang   ██████████████████████████████████████████░░   27      ★
LangGraph  ██████████████████████░░░░░░░░░░░░░░░░░░░░░   15
CrewAI     ██████████████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░   10
OpenClaw   ██████████████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░   10
AutoGen    ███████████░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░░    8

Feature-by-Feature Comparison

16 Security Systems — Defense in Depth

OpenFang doesn't bolt security on after the fact. Every layer is independently testable and operates without a single point of failure.

Architecture

14 Rust crates. 137,728 lines of code. Modular kernel design.

openfang-kernel      Orchestration, workflows, metering, RBAC, scheduler, budget tracking
openfang-runtime     Agent loop, 3 LLM drivers, 53 tools, WASM sandbox, MCP, A2A
openfang-api         140+ REST/WS/SSE endpoints, OpenAI-compatible API, dashboard
openfang-channels    40 messaging adapters with rate limiting, DM/group policies
openfang-memory      SQLite persistence, vector embeddings, canonical sessions, compaction
openfang-types       Core types, taint tracking, Ed25519 manifest signing, model catalog
openfang-skills      60 bundled skills, SKILL.md parser, FangHub marketplace
openfang-hands       7 autonomous Hands, HAND.toml parser, lifecycle management
openfang-extensions  25 MCP templates, AES-256-GCM credential vault, OAuth2 PKCE
openfang-wire        OFP P2P protocol with HMAC-SHA256 mutual authentication
openfang-cli         CLI with daemon management, TUI dashboard, MCP server mode
openfang-desktop     Tauri 2.0 native app (system tray, notifications, global shortcuts)
openfang-migrate     OpenClaw, LangChain, AutoGPT migration engine
xtask                Build automation

40 Channel Adapters

Connect your agents to every platform your users are on.

Core: Telegram, Discord, Slack, WhatsApp, Signal, Matrix, Email (IMAP/SMTP) Enterprise: Microsoft Teams, Mattermost, Google Chat, Webex, Feishu/Lark, Zulip Social: LINE, Viber, Facebook Messenger, Mastodon, Bluesky, Reddit, LinkedIn, Twitch Community: IRC, XMPP, Guilded, Revolt, Keybase, Discourse, Gitter Privacy: Threema, Nostr, Mumble, Nextcloud Talk, Rocket.Chat, Ntfy, Gotify Workplace: Pumble, Flock, Twist, DingTalk, Zalo, Webhooks

Each adapter supports per-channel model overrides, DM/group policies, rate limiting, and output formatting.

WhatsApp Web Gateway (QR Code)

Connect your personal WhatsApp account to OpenFang via QR code — just like WhatsApp Web. No Meta Business account required.

Prerequisites

• Node.js >= 18 installed (download)
• OpenFang installed and initialized

Setup

1. Install the gateway dependencies:

cd packages/whatsapp-gateway
npm install

2. Configure config.toml:

[channels.whatsapp]
mode = "web"
default_agent = "assistant"

3. Set the gateway URL (choose one):

Add to your shell profile for persistence:

# macOS / Linux
echo 'export WHATSAPP_WEB_GATEWAY_URL="http://127.0.0.1:3009"' >> ~/.zshrc
source ~/.zshrc

Or set it inline when starting the gateway:

export WHATSAPP_WEB_GATEWAY_URL="http://127.0.0.1:3009"

4. Start the gateway:

node packages/whatsapp-gateway/index.js

The gateway listens on port 3009 by default. Override with WHATSAPP_GATEWAY_PORT.

5. Start OpenFang:

openfang start
# Dashboard at http://localhost:4200

6. Scan the QR code:

Open the dashboard → Channels → WhatsApp. A QR code will appear. Scan it with your phone:

WhatsApp → Settings → Linked Devices → Link a Device

Once scanned, the status changes to connected and incoming messages are routed to your configured agent.

Gateway Environment Variables

Gateway API Endpoints

Alternative: WhatsApp Cloud API

For production workloads, use the WhatsApp Cloud API with a Meta Business account. See the Cloud API configuration docs.

27 LLM Providers — 123+ Models

3 native drivers (Anthropic, Gemini, OpenAI-compatible) route to 27 providers:

Anthropic, Gemini, OpenAI, Groq, DeepSeek, OpenRouter, Together, Mistral, Fireworks, Cohere, Perplexity, xAI, AI21, Cerebras, SambaNova, HuggingFace, Replicate, Ollama, vLLM, LM Studio, Qwen, MiniMax, Zhipu, Moonshot, Qianfan, Bedrock, and more.

Intelligent routing with task complexity scoring, automatic fallback, cost tracking, and per-model pricing.

Migrate from OpenClaw

Already running OpenClaw? One command:

# Migrate everything — agents, memory, skills, configs
openfang migrate --from openclaw

# Migrate from a specific path
openfang migrate --from openclaw --path ~/.openclaw

# Dry run first to see what would change
openfang migrate --from openclaw --dry-run

The migration engine imports your agents, conversation history, skills, and configuration. OpenFang reads SKILL.md natively and is compatible with the ClawHub marketplace.

OpenAI-Compatible API

Drop-in replacement. Point your existing tools at OpenFang:

curl -X POST localhost:4200/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "researcher",
    "messages": [{"role": "user", "content": "Analyze Q4 market trends"}],
    "stream": true
  }'

140+ REST/WS/SSE endpoints covering agents, memory, workflows, channels, models, skills, A2A, Hands, and more.

Quick Start

# 1. Install (macOS/Linux)
curl -fsSL https://openfang.sh/install | sh

# 2. Initialize — walks you through provider setup
openfang init

# 3. Start the daemon
openfang start

# 4. Dashboard is live at http://localhost:4200

# 5. Activate a Hand — it starts working for you
openfang hand activate researcher

# 6. Chat with an agent
openfang chat researcher
> "What are the emerging trends in AI agent frameworks?"

# 7. Spawn a pre-built agent
openfang agent spawn coder

irm https://openfang.sh/install.ps1 | iex
openfang init
openfang start

Development

# Build the workspace
cargo build --workspace --lib

# Run all tests (1,767+)
cargo test --workspace

# Lint (must be 0 warnings)
cargo clippy --workspace --all-targets -- -D warnings

# Format
cargo fmt --all -- --check

Stability Notice

OpenFang v0.3.30 is pre-1.0. The architecture is solid, the test suite is comprehensive, and the security model is comprehensive. That said:

• Breaking changes may occur between minor versions until v1.0
• Some Hands are more mature than others (Browser and Researcher are the most battle-tested)
• Edge cases exist — if you find one, open an issue
• Pin to a specific commit for production deployments until v1.0

We ship fast and fix fast. The goal is a rock-solid v1.0 by mid-2026.

Security

To report a security vulnerability, email jaber@rightnowai.co. We take all reports seriously and will respond within 48 hours.

License

MIT — use it however you want.

Links

• Website & Documentation
• Quick Start Guide
• GitHub
• Discord
• Twitter / X

Built by RightNow