Lookit

LLM-first vision toolkit for GUI grounding, OCR, and more. Built with LangChain and Qwen3-VL. Outputs minimal plain text optimized for token efficiency.

Quick Start

Choose your setup method:

Method Use Case
Skills Setup Claude Code, DeepAgents, or other agent frameworks (recommended)
CLI Installation Standalone command-line usage

Skills Setup

Skills are self-contained and auto-download the binary on first run. No Python or dependencies required.

Skill Description
computer-use GUI grounding for desktop screenshots
mobile-use GUI grounding for mobile screenshots
ocr Text extraction from screenshots

Prerequisites

Choose ONE backend option:

Option A: Ollama Cloud (recommended, no local setup)
  1. Create an Ollama account at ollama.com
  2. Go to ollama.com/settings/keys
  3. Click "Create new key" and copy the API key

You'll use these settings:

LOOKIT_API_KEY=your-api-key-here
LOOKIT_MODEL=qwen3-vl:235b-cloud
LOOKIT_BASE_URL=https://ollama.com/v1
Option B: Ollama Local (requires local setup)
  1. Install Ollama: ollama.com/download
  2. Pull the model: 
    ollama pull qwen3-vl
  3. Start Ollama (runs automatically after install, or run ollama serve)

You'll use these settings:

LOOKIT_API_KEY=ollama
LOOKIT_MODEL=qwen3-vl
LOOKIT_BASE_URL=http://localhost:11434/v1
Option C: LM Studio (local GUI app)
  1. Download LM Studio: lmstudio.ai
  2. Search and download a Qwen3-VL model (e.g., qwen/qwen3-vl-8b)
  3. Start the local server (Server tab → Start Server)

You'll use these settings (model name uses owner/model format):

LOOKIT_API_KEY=lmstudio
LOOKIT_MODEL=qwen/qwen3-vl-8b
LOOKIT_BASE_URL=http://127.0.0.1:1234/v1

Install Skills

Claude Code

Step 1: Download skills

# Set version to download
VERSION="0.1.1"

# Create skill directories
mkdir -p ~/.claude/skills/{computer-use,mobile-use,ocr}/{bin,config}

# Download computer-use skill
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/computer-use/SKILL.md" -o ~/.claude/skills/computer-use/SKILL.md
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/computer-use/bin/lookit" -o ~/.claude/skills/computer-use/bin/lookit
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/computer-use/config/lookit.env.example" -o ~/.claude/skills/computer-use/config/lookit.env.example
chmod +x ~/.claude/skills/computer-use/bin/lookit

# Download mobile-use skill
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/mobile-use/SKILL.md" -o ~/.claude/skills/mobile-use/SKILL.md
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/mobile-use/bin/lookit" -o ~/.claude/skills/mobile-use/bin/lookit
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/mobile-use/config/lookit.env.example" -o ~/.claude/skills/mobile-use/config/lookit.env.example
chmod +x ~/.claude/skills/mobile-use/bin/lookit

# Download ocr skill
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/ocr/SKILL.md" -o ~/.claude/skills/ocr/SKILL.md
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/ocr/bin/lookit" -o ~/.claude/skills/ocr/bin/lookit
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/ocr/config/lookit.env.example" -o ~/.claude/skills/ocr/config/lookit.env.example
chmod +x ~/.claude/skills/ocr/bin/lookit

# Create config files from examples
cp ~/.claude/skills/computer-use/config/lookit.env.example ~/.claude/skills/computer-use/config/lookit.env
cp ~/.claude/skills/mobile-use/config/lookit.env.example ~/.claude/skills/mobile-use/config/lookit.env
cp ~/.claude/skills/ocr/config/lookit.env.example ~/.claude/skills/ocr/config/lookit.env

Step 2: Configure API settings

Edit each config file with your API settings from the Prerequisites section:

# Edit each config (use any text editor: nano, vim, code, etc.)
nano ~/.claude/skills/computer-use/config/lookit.env
nano ~/.claude/skills/mobile-use/config/lookit.env
nano ~/.claude/skills/ocr/config/lookit.env

Example config for Ollama Cloud:

LOOKIT_API_KEY=your-api-key-here
LOOKIT_MODEL=qwen3-vl:235b-cloud
LOOKIT_BASE_URL=https://ollama.com/v1

Step 3: Verify setup

# Test the skill (downloads binary on first run)
~/.claude/skills/computer-use/bin/lookit --help
DeepAgents CLI

DeepAgents is an agent framework built on LangChain and LangGraph.

Step 1: Download skills

# Install deepagents CLI
pip install deepagents-cli

# Set version to download
VERSION="0.1.1"

# Create skill directories
mkdir -p ~/.deepagents/default/skills/{computer-use,mobile-use,ocr}/{bin,config}

# Download computer-use skill
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/computer-use/SKILL.md" -o ~/.deepagents/default/skills/computer-use/SKILL.md
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/computer-use/bin/lookit" -o ~/.deepagents/default/skills/computer-use/bin/lookit
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/computer-use/config/lookit.env.example" -o ~/.deepagents/default/skills/computer-use/config/lookit.env.example
chmod +x ~/.deepagents/default/skills/computer-use/bin/lookit

# Download mobile-use skill
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/mobile-use/SKILL.md" -o ~/.deepagents/default/skills/mobile-use/SKILL.md
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/mobile-use/bin/lookit" -o ~/.deepagents/default/skills/mobile-use/bin/lookit
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/mobile-use/config/lookit.env.example" -o ~/.deepagents/default/skills/mobile-use/config/lookit.env.example
chmod +x ~/.deepagents/default/skills/mobile-use/bin/lookit

# Download ocr skill
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/ocr/SKILL.md" -o ~/.deepagents/default/skills/ocr/SKILL.md
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/ocr/bin/lookit" -o ~/.deepagents/default/skills/ocr/bin/lookit
curl -sL "https://raw.githubusercontent.com/atom2ueki/lookit/$VERSION/skills/ocr/config/lookit.env.example" -o ~/.deepagents/default/skills/ocr/config/lookit.env.example
chmod +x ~/.deepagents/default/skills/ocr/bin/lookit

# Create config files from examples
cp ~/.deepagents/default/skills/computer-use/config/lookit.env.example ~/.deepagents/default/skills/computer-use/config/lookit.env
cp ~/.deepagents/default/skills/mobile-use/config/lookit.env.example ~/.deepagents/default/skills/mobile-use/config/lookit.env
cp ~/.deepagents/default/skills/ocr/config/lookit.env.example ~/.deepagents/default/skills/ocr/config/lookit.env

Step 2: Configure API settings

Edit each config file with your API settings from the Prerequisites section:

# Edit each config (use any text editor: nano, vim, code, etc.)
nano ~/.deepagents/default/skills/computer-use/config/lookit.env
nano ~/.deepagents/default/skills/mobile-use/config/lookit.env
nano ~/.deepagents/default/skills/ocr/config/lookit.env

Example config for Ollama Cloud:

LOOKIT_API_KEY=your-api-key-here
LOOKIT_MODEL=qwen3-vl:235b-cloud
LOOKIT_BASE_URL=https://ollama.com/v1

Step 3: Verify setup

# Test the skill (downloads binary on first run)
~/.deepagents/default/skills/computer-use/bin/lookit --help

# Verify skills are detected
deepagents skills list
Programmatic Integration

For integrating skills into your own LangChain agents, see deepagents PR #611 (WIP).

# Install in your project
pip install lookit

# Create .env file with your API settings from Prerequisites section
cat << 'EOF' > .env
LOOKIT_API_KEY=your-api-key-here
LOOKIT_MODEL=qwen3-vl:235b-cloud
LOOKIT_BASE_URL=https://ollama.com/v1
EOF

from deepagents import create_deep_agent
from deepagents.backends.filesystem import FilesystemBackend
from deepagents.middleware import SkillsMiddleware

# Create backend and skills middleware
backend = FilesystemBackend()
skills_middleware = SkillsMiddleware(
    backend=backend,
    registries=[
        {"path": "/skills/user/", "name": "user"},
        {"path": "/skills/project/", "name": "project"},
    ],
)

# Create agent with skills middleware
agent = create_deep_agent(
    model="openai:gpt-4o",
    middleware=[skills_middleware],
)

# Agent will automatically discover and use lookit skills
result = agent.invoke({
    "messages": [{"role": "user", "content": "Click the submit button in screenshot.png"}]
})

CLI Installation

For standalone command-line usage (requires Python). First complete the Prerequisites to get your API settings.

Step 1: Install

pip install lookit

Step 2: Configure

Add to your shell profile (~/.zshrc on macOS, ~/.bashrc on Linux):

For Ollama Cloud (recommended, see Prerequisites for API key):

export LOOKIT_API_KEY="your-api-key-here"
export LOOKIT_MODEL="qwen3-vl:235b-cloud"
export LOOKIT_BASE_URL="https://ollama.com/v1"

For Ollama Local (see Prerequisites for setup):

export LOOKIT_API_KEY="ollama"
export LOOKIT_MODEL="qwen3-vl"
export LOOKIT_BASE_URL="http://localhost:11434/v1"

Then reload: source ~/.zshrc

Step 3: Verify

lookit --help

Usage

Same screenshot, different modes and prompts = different results:

OCR Mode Computer Mode
lookit "extract the transaction history" -s screenshot.png --mode ocr lookit "click search" -s screenshot.png --mode computer
Screenshot Result
Max Now Pte. Ltd.
Singapore SG
24 Dec 2025 10:07:13
SGD 70.85
140 points
Pending
...		 left_click 2910,365

Output Format

Action Modes (computer/mobile)

left_click 960,324
type "hello world"
swipe 500,800 to 500,200
key Control+c
scroll -100

OCR Mode

Returns extracted text directly.

Arguments

Argument Description
query Natural language instruction
-s, --screenshot Path to screenshot (required)
-m, --mode computer, mobile, or ocr (required)
--debug Debug mode (for humans): print info to stderr, save annotated image

Actions

Computer

left_click, right_click, double_click, type, key, scroll, mouse_move

Mobile

click, long_press, swipe, type, system_button

License

MIT

Project links

Data verified by PyPI on Jan 6, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for atom2ueki from gravatar.com atom2ueki

GitHub Statistics

Data verified by PyPI on Jan 6, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License expression

MIT
View SPDX License List

Requires

Python <4.0, >=3.11

Report project as malware

Release files for lookit 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for lookit 0.1.1
File Size Uploaded
lookit-0.1.1.tar.gz 16.8 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for lookit 0.1.1
File Interpreter ABI Platform
lookit-0.1.1-py3-none-any.whl 18.0 kB Python 3 none any Details

Total release size: 34.8 kB

Release files / lookit-0.1.1.tar.gz

Download URL lookit-0.1.1.tar.gz
Size 16.8 kB
Tags Source
SHA-256 checksum
How to use checksums 		99738ac73a4e860944056c4e25883c1dff10f6a311b5c73d281f153f02985d6d
BLAKE2b-256 checksum
How to use checksums 		0ce95d9f01245499b1f65581dd8769e1073c54f50391fcb9aceba9dca6499105
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing? 		Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jan 6, 2026.

Transparency log
Identity
Publishing platform
GitHub Actions
Publishing repository
github.com/atom2ueki/lookit
Publishing commit
github.com/atom2ueki/lookit/tree/d7d4e137411f7af0950d7e2258ff7d8b4ea445e1
Workflow
Publishing configuration
github.com/atom2ueki/lookit/blob/d7d4e137411f7af0950d7e2258ff7d8b4ea445e1/.github/workflows/publish.yml
Publishing logs
github.com/atom2ueki/lookit/actions/runs/20740718506/attempts/1
Artifact
Subject
lookit-0.1.1.tar.gz
SHA-256 checksum
99738ac73a4e860944056c4e25883c1dff10f6a311b5c73d281f153f02985d6d Verifying attestations

Release files / lookit-0.1.1-py3-none-any.whl

Download URL lookit-0.1.1-py3-none-any.whl
Size 18.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums 		7cef9be0b49145ce221582020cf2901bacfc91e96c38615dc5a2ad47a6a08c9f
BLAKE2b-256 checksum
How to use checksums 		9f33cb47460aeabf30bbcbfbaded2f2aa7f0e70ab6eaf08a51396b2cd49e2d94
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing? 		Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Jan 6, 2026.

Transparency log
Identity
Publishing platform
GitHub Actions
Publishing repository
github.com/atom2ueki/lookit
Publishing commit
github.com/atom2ueki/lookit/tree/d7d4e137411f7af0950d7e2258ff7d8b4ea445e1
Workflow
Publishing configuration
github.com/atom2ueki/lookit/blob/d7d4e137411f7af0950d7e2258ff7d8b4ea445e1/.github/workflows/publish.yml
Publishing logs
github.com/atom2ueki/lookit/actions/runs/20740718506/attempts/1
Artifact
Subject
lookit-0.1.1-py3-none-any.whl
SHA-256 checksum
7cef9be0b49145ce221582020cf2901bacfc91e96c38615dc5a2ad47a6a08c9f Verifying attestations

Release history Release notifications | RSS feed

This release

0.1.1 This release

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page