> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/RightNow-AI/openfang/llms.txt
> Use this file to discover all available pages before exploring further.

# Hands Overview

> Autonomous agents that work 24/7 on specialized tasks

## What Are Hands?

Hands are specialized autonomous agents in OpenFang designed to run continuously and handle specific workflows. Unlike general-purpose chat agents, Hands are optimized for:

* **Continuous operation** — Run scheduled tasks 24/7
* **Domain expertise** — Deep knowledge in specific areas (video editing, research, social media)
* **Multi-phase pipelines** — Complex workflows broken into manageable steps
* **State persistence** — Remember progress across sessions
* **Tool specialization** — Access to specialized tools for their domain

## Available Hands

<CardGroup cols={2}>
  <Card title="Clip Hand" icon="film" href="/hands/clip">
    Turn long videos into viral short clips with captions and thumbnails
  </Card>

  <Card title="Lead Hand" icon="chart-line" href="/hands/lead">
    Discover and enrich qualified leads on autopilot
  </Card>

  <Card title="Collector Hand" icon="magnifying-glass" href="/hands/collector">
    Monitor any target with continuous intelligence collection
  </Card>

  <Card title="Predictor Hand" icon="crystal-ball" href="/hands/predictor">
    Make calibrated predictions and track accuracy over time
  </Card>

  <Card title="Researcher Hand" icon="flask" href="/hands/researcher">
    Conduct exhaustive investigations with fact-checking
  </Card>

  <Card title="Twitter Hand" icon="twitter" href="/hands/twitter">
    Autonomous Twitter content creation and engagement
  </Card>

  <Card title="Browser Hand" icon="browser" href="/hands/browser">
    Navigate websites and complete multi-step web tasks
  </Card>

  <Card title="Custom Hand" icon="code" href="/hands/custom">
    Build your own specialized Hand
  </Card>
</CardGroup>

## How Hands Work

### Activation

Hands are activated by loading their definition file:

```bash theme={null}
openfang hand activate clip
```

This creates an agent instance with the Hand's specialized configuration, tools, and system prompt.

### Configuration

Each Hand has settings that control its behavior:

```toml theme={null}
# Example from Clip Hand
[settings]
stt_provider = "groq_whisper"  # Speech-to-text provider
publish_target = "telegram"     # Where to send clips
```

Settings can be configured through:

* The web dashboard at `http://localhost:4200`
* Direct TOML editing in `~/.openfang/hands/`
* CLI configuration commands

### Requirements

Some Hands require external tools or API keys:

<Warning>
  Check the requirements section for each Hand before activating. Missing dependencies will prevent the Hand from functioning.
</Warning>

### Scheduling

Hands can run on schedules:

```javascript theme={null}
// Created automatically by the Hand's initialization
schedule_create({
  frequency: "daily",
  time: "09:00",
  task: "generate_lead_report"
})
```

### Memory & State

Hands persist state between runs:

* **Memory store** — Key-value storage for metrics and state
* **Knowledge graph** — Entity and relationship tracking
* **File storage** — Reports, databases, and artifacts

## Hand Architecture

Every Hand follows a consistent multi-phase pipeline:

<Steps>
  <Step title="Phase 0: Platform Detection">
    Detect OS and load state from previous runs
  </Step>

  <Step title="Phase 1: Initialization">
    Set up schedules, load configuration, build strategy
  </Step>

  <Step title="Phase 2-5: Core Work">
    Execute the Hand's specialized workflow (varies by Hand)
  </Step>

  <Step title="Final Phase: Persistence">
    Save state, update metrics, generate reports
  </Step>
</Steps>

## Dashboard Metrics

All Hands expose metrics through the dashboard:

* **Jobs completed** — Total tasks finished
* **Items processed** — Clips generated, leads found, etc.
* **Performance data** — Success rates, quality metrics
* **Last run** — When the Hand last executed

## Safety Guardrails

Hands include built-in safety features:

* **Rate limiting** — Respect API and service limits
* **Approval modes** — Require user confirmation for sensitive actions
* **Error recovery** — Graceful handling of failures
* **Cross-platform compatibility** — Works on Windows, macOS, Linux

## Choosing the Right Hand

| Use Case                                | Hand            | Why                                           |
| --------------------------------------- | --------------- | --------------------------------------------- |
| Create social media content from videos | Clip Hand       | Automated video processing pipeline           |
| Generate sales leads                    | Lead Hand       | Continuous discovery and enrichment           |
| Track competitors or markets            | Collector Hand  | Change detection and knowledge graphs         |
| Forecast trends                         | Predictor Hand  | Calibrated predictions with accuracy tracking |
| Deep dive research                      | Researcher Hand | Multi-source verification and synthesis       |
| Manage Twitter presence                 | Twitter Hand    | Content generation and engagement             |
| Automate web tasks                      | Browser Hand    | Real browser automation with safety           |
| Custom workflow                         | Custom Hand     | Build your own specialized agent              |

## Next Steps

<CardGroup cols={2}>
  <Card title="Explore Hands" icon="compass" href="/hands/clip">
    Browse the documentation for each Hand
  </Card>

  <Card title="Build Your Own" icon="hammer" href="/hands/custom">
    Learn how to create custom Hands
  </Card>
</CardGroup>
