LibreFang
中文

Getting Started with LibreFang

This guide walks you through installing LibreFang, configuring your first LLM provider, spawning an agent, and chatting with it.

Project website: https://librefang.ai/

Table of Contents

Installation

CLI

The CLI is the core command-line tool for managing agents, hands, workflows, and more.

Quick Install Script (Recommended)

Linux / macOS / WSL:

curl -fsSL https://librefang.ai/install.sh | sh

Windows (PowerShell):

irm https://librefang.ai/install.ps1 | iex

The script auto-detects platform and architecture, downloads the binary, verifies SHA256 checksums, configures PATH, runs librefang init, and starts the daemon.

Environment variables:

  • LIBREFANG_INSTALL_DIR — install directory (default: ~/.librefang/bin)
  • LIBREFANG_VERSION — specific version (default: latest)
  • LIBREFANG_AUTO_START — auto-start daemon (default: 1)

Windows EXE (Manual)

If you prefer manual installation or the script doesn't work in your environment:

  1. Download librefang-x86_64-pc-windows-msvc.zip (or aarch64 for ARM) from GitHub Releases
  2. Extract librefang.exe to a folder, e.g. C:\Users\<you>\.librefang\bin\
  3. Add that folder to your system PATH:
    • Settings → System → About → Advanced system settings → Environment Variables
    • Edit Path under User variables → Add the folder path
  4. Open a new terminal and run:
# Initialize configuration
librefang init

# Start the daemon
librefang start

# Open dashboard in browser: http://127.0.0.1:4545/
# Chat with the default agent
librefang chat

librefang init creates ~/.librefang/config.toml with a setup wizard. You must run init before start — otherwise the daemon has no configuration. On first run, if init has not been run, start and chat will auto-initialize.

Homebrew (macOS / Linux)

brew tap librefang/tap
brew install librefang              # Stable
brew install librefang-beta         # Beta
brew install librefang-rc           # RC

npm

npm install -g @librefang/cli                  # Stable
npm install -g @librefang/cli@next             # Latest pre-release (Beta or RC)
npm install -g @librefang/cli@2026.3.25-rc1    # Specific version

pip

pip install librefang-cli                      # Stable
pip install librefang-cli --pre                # Latest pre-release

Cargo

cargo install --git https://github.com/librefang/librefang librefang-cli

Or build from source (requires just):

git clone https://github.com/librefang/librefang.git
cd librefang
just install

Docker

docker run -d \
  --name librefang \
  -p 4545:4545 \
  -e ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY \
  -v librefang-data:/data \
  ghcr.io/librefang/librefang:latest

Docker Compose:

git clone https://github.com/librefang/librefang.git
cd librefang/deploy
docker compose up -d

Verify Installation

librefang --version

SDK

SDKs for integrating LibreFang API into your applications.

JavaScript / TypeScript

npm install @librefang/sdk                     # Stable
npm install @librefang/sdk@next                # Latest pre-release (Beta or RC)
npm install @librefang/sdk@2026.3.25-rc1       # Specific version

Python

pip install librefang-sdk                      # Stable
pip install librefang-sdk --pre                # Latest pre-release (Beta or RC)
pip install librefang-sdk==2026.3.25rc1        # Specific version (PEP 440)

Rust

cargo add librefang

Go

go get github.com/librefang/librefang/sdk/go

Desktop App

Native Tauri 2.0 desktop application. See Desktop for details.

Homebrew Cask

brew tap librefang/tap
brew install --cask librefang       # Stable
brew install --cask librefang-beta  # Beta
brew install --cask librefang-rc    # RC

Direct Download

Download from GitHub Releases:

  • macOS: .dmg (Universal)
  • Windows: .msi
  • Linux: .appimage / .deb

One-Click Cloud Deployment

Visit deploy.librefang.ai for all cloud deployment options.

Fly.io

curl -sL https://raw.githubusercontent.com/librefang/librefang/main/deploy/fly/deploy.sh | bash

Railway

Railway

Render

Render

GCP (Terraform)

Deploy on GCP always-free tier (e2-micro). See deploy/gcp/README.md for details:

cd deploy/gcp
cp terraform.tfvars.example terraform.tfvars
# Edit terraform.tfvars with your project_id and API keys
terraform init && terraform apply

Linux systemd

sudo cp deploy/librefang.service /etc/systemd/system/
sudo systemctl enable --now librefang

Configuration

Initialize

Initialization runs automatically on first librefang start (or via the install script / Docker entrypoint). To run the interactive setup wizard manually:

librefang init

This creates the ~/.librefang/ directory (customizable via LIBREFANG_HOME):

~/.librefang/
├── config.toml                # Main configuration file
├── aliases.toml               # Model and command aliases
├── data/
│   ├── librefang.db           #   SQLite database (memory, sessions, knowledge graph)
│   └── state.db               #   Daemon state persistence
├── registry/                  # Synced from librefang-registry
│   ├── agents/                #   32 agent templates
│   ├── hands/                 #   15 hand definitions
│   ├── providers/             #   49 provider configs
│   ├── skills/                #   Skill definitions
│   ├── workflows/             #   Workflow templates
│   └── plugins/               #   Plugin definitions
├── workspaces/                # Runtime working directories
│   ├── agents/                #   Active agent working directories
│   └── hands/                 #   Active hand working directories
├── skills/                    # User-installed skills
├── plugins/                   # User-installed plugins
├── vault.enc                  # Encrypted credential vault
├── logs/                      # Application logs
├── cache/                     # Temporary cache
└── bin/                       # CLI binary (if installed via script)

See Architecture - User Data Directory for the full reference.

Set Up an API Key

LibreFang needs at least one LLM provider API key. Set it as an environment variable:

# Anthropic (Claude)
export ANTHROPIC_API_KEY=sk-ant-...

# Or OpenAI
export OPENAI_API_KEY=sk-...

# Or Groq (free tier available)
export GROQ_API_KEY=gsk_...

Add the export to your shell profile (~/.bashrc, ~/.zshrc, etc.) to persist it.

LibreFang supports three layers of key storage (highest priority first):

LayerFileHow to setNotes
System env vars—export GROQ_API_KEY=...Highest priority, never overridden
Encrypted vaultvault.enclibrefang vault set GROQ_API_KEYAES encrypted, recommended
.env file.envlibrefang config set-key groqPlaintext, written by CLI
secrets.envsecrets.envDashboard "Set API Key" buttonPlaintext, written by dashboard

Edit the Config

The default config uses Anthropic. To change the provider, edit ~/.librefang/config.toml:

[default_model]
provider = "groq"                      # anthropic, openai, groq, ollama, etc.
model = "llama-3.3-70b-versatile"      # Model identifier for the provider
api_key_env = "GROQ_API_KEY"           # Env var holding the API key

[memory]
decay_rate = 0.05                      # Memory confidence decay rate

[network]
listen_addr = "127.0.0.1:4545"        # OFP listen address

Verify Your Setup

librefang doctor

This checks that your config exists, API keys are set, and the toolchain is available.

Spawn Your First Agent

Using a Built-in Template

LibreFang provides 32 agent templates from the registry (assistant pre-installed, others available from dashboard). Spawn the assistant agent:

librefang agent spawn agents/hello-world/agent.toml

Output:

Agent spawned successfully!
  ID:   a1b2c3d4-e5f6-...
  Name: hello-world

Using a Custom Manifest

Create your own my-agent.toml:

name = "my-assistant"
version = "0.1.0"
description = "A helpful assistant"
author = "you"
module = "builtin:chat"

[model]
provider = "groq"
model = "llama-3.3-70b-versatile"

[capabilities]
tools = ["file_read", "file_list", "web_fetch"]
memory_read = ["*"]
memory_write = ["self.*"]

Then spawn it:

librefang agent spawn my-agent.toml

List Running Agents

librefang agent list

Output:

ID                                     NAME             STATE      PROVIDER     MODEL
-----------------------------------------------------------------------------------------------
a1b2c3d4-e5f6-...                     hello-world      Running    groq         llama-3.3-70b-versatile

Chat with an Agent

Start an interactive chat session using the agent ID:

librefang agent chat a1b2c3d4-e5f6-...

Or use the quick chat command (picks the first available agent):

librefang chat

Or specify an agent by name:

librefang chat hello-world

Example session:

Chat session started (daemon mode). Type 'exit' or Ctrl+C to quit.

you> Hello! What can you do?

agent> I'm the hello-world agent running on LibreFang. I can:
- Read files from the filesystem
- List directory contents
- Fetch web pages

Try asking me to read a file or look up something on the web!

  [tokens: 142 in / 87 out | iterations: 1]

you> List the files in the current directory

agent> Here are the files in the current directory:
- Cargo.toml
- Cargo.lock
- README.md
- agents/
- crates/
- docs/
...

you> exit
Chat session ended.

Start the Daemon

For persistent agents, multi-user access, and the WebChat UI, start the daemon:

librefang start

Output:

Starting LibreFang daemon...
LibreFang daemon running on http://127.0.0.1:4545
Press Ctrl+C to stop.

The daemon provides:

  • REST API at http://127.0.0.1:4545/api/
  • WebSocket endpoint at ws://127.0.0.1:4545/api/agents/{id}/ws
  • WebChat UI at http://127.0.0.1:4545/
  • OFP networking on port 4545

Check Status

librefang status

Stop the Daemon

Press Ctrl+C in the terminal running the daemon, or:

curl -X POST http://127.0.0.1:4545/api/shutdown

Using the WebChat UI

With the daemon running, open your browser to:

http://127.0.0.1:4545/

The embedded WebChat UI allows you to:

  • View all running agents
  • Chat with any agent in real-time (via WebSocket)
  • See streaming responses as they are generated
  • View token usage per message

Next Steps

Now that you have LibreFang running:

  • Explore agent templates: Browse the agents/ directory for pre-built agents (coder, researcher, writer, ops, analyst, security-auditor, and more).
  • Create custom agents: Write your own agent.toml manifests. See the Architecture guide for details on capabilities and scheduling.
  • Set up channels: Connect any of 44 messaging platforms (Telegram, Discord, Slack, WhatsApp, LINE, Mastodon, and 38 more). See Channel Adapters.
  • Install skills: 60 expert knowledge skills available from the dashboard (GitHub, Docker, Kubernetes, security audit, prompt engineering, etc.). See Skill Development.
  • Build custom skills: Extend agents with Python, WASM, or prompt-only skills. See Skill Development.
  • Use the API: 230+ REST/WS/SSE endpoints, including an OpenAI-compatible /v1/chat/completions. See API Reference.
  • Switch LLM providers: 49 drivers supported (Anthropic, OpenAI, Gemini, Groq, DeepSeek, xAI, Ollama, and more). Per-agent model overrides.
  • Set up workflows: Chain multiple agents together. Use librefang workflow create with a TOML workflow definition.
  • Use MCP: Connect to external tools via Model Context Protocol. Configure in config.toml under [[mcp_servers]].
  • Migrate from OpenFang: Run librefang migrate --from openfang. Copies ~/.openfang → ~/.librefang with automatic content rewriting.
  • Migrate from OpenClaw: Run librefang migrate --from openclaw. See MIGRATION.md.
  • Desktop app: Run cargo tauri dev for a native desktop experience with system tray.
  • Run diagnostics: librefang doctor checks your entire setup.

Useful Commands Reference

librefang init                          # Initialize ~/.librefang/
librefang start                         # Start the daemon
librefang status                        # Check daemon status
librefang doctor                        # Run diagnostic checks

librefang agent spawn <manifest.toml>   # Spawn an agent
librefang agent list                    # List all agents
librefang agent chat <id>               # Chat with an agent
librefang agent kill <id>               # Kill an agent

librefang workflow list                 # List workflows
librefang workflow create <file.json>   # Create a workflow
librefang workflow run <id> <input>     # Run a workflow

librefang trigger list                  # List event triggers
librefang trigger create <args>         # Create a trigger
librefang trigger delete <id>           # Delete a trigger

librefang skill install <source>        # Install a skill
librefang skill list                    # List installed skills
librefang skill search <query>          # Search FangHub
librefang skill create                  # Scaffold a new skill

librefang channel list                  # List channel status
librefang channel setup <channel>       # Interactive setup wizard

librefang config show                   # Show current config
librefang config edit                   # Open config in editor

librefang chat [agent]                  # Quick chat (alias)
librefang migrate --from openfang       # Migrate from OpenFang
librefang migrate --from openclaw       # Migrate from OpenClaw
librefang mcp                           # Start MCP server (stdio)