Gptme

What is Gptme about?

Gptme enables an LLM to operate in a local command‑line environment, turning the model into an autonomous assistant that can run shell commands, execute Python snippets, edit files, browse the internet, process images, and interact with GUI applications.

How to use Gptme?

1. Install – pipx install gptme (requires Python 3.10+).
2. Start – run gptme to open an interactive chat session.
3. Provide prompts – type natural‑language requests or prepend a slash command for tool control (e.g., /tools, /model).
4. Leverage tools – the assistant will automatically invoke tools like shell, python, patch, browser, vision, or computer to fulfil the request.
5. Advanced options – specify a model (-m openai/gpt-4), workspace (-w ./myproj), enable/disable specific tools (-t shell,patch), or run in non‑interactive mode.

Key features of Gptme

• Code execution: Run shell commands and Python code safely via built‑in tools.
• File operations: Read, write, and patch files incrementally.
• Web browsing: Use Playwright‑based browser tool for search and page scraping.
• Vision: Load and analyze images from local paths or screenshots.
• Self‑correction: Assistant receives its own output for iterative improvement.
• Multi‑provider LLM support: OpenAI, Anthropic, OpenRouter, local llama.cpp models.
• Web UI & REST API: Optional browser‑based chat interface and server endpoints.
• Computer‑use tool: Full desktop interaction for GUI automation.
• Agent architecture: Persistent agents, sub‑agents, and customizable templates.
• Developer ergonomics: Tab‑completion, syntax‑highlighted diffs, TTS, tool sounds, and configuration flags.

Use cases of Gptme

• Software development: Generate, test, and debug code without leaving the terminal.
• Shell assistance: Convert natural language into correct CLI commands.
• Data analysis: Execute data‑processing scripts and view results instantly.
• Learning & exploration: Experiment with new languages, frameworks, or APIs interactively.
• Automation: Script repetitive tasks, run CI steps, or manage repositories via AI.
• Research: Browse documentation, fetch information from the web, and summarise findings.

FAQ

Q: Do I need an internet connection? A: Only if you use remote LLM providers (OpenAI, Anthropic, etc.) or the browser tool. Local models run entirely offline.

Q: How is privacy handled? A: When using local models, no data leaves your machine. Remote providers follow their own policies.

Q: Can I integrate Gptme into other tools? A: Yes – the web UI, REST API, and sub‑agent architecture allow embedding Gptme in custom workflows.

Q: What platforms are supported? A: Works on any OS with Python 3.10+, including Linux, macOS, and Windows (via WSL or native).

📚 Table of Contents

• 🎥 Demos
• 🌟 Features
• 🚀 Getting Started
• 🛠 Usage
• 📊 Stats
• 🔗 Links

🎥 Demos

[!NOTE] These demos are very out of date (2023) and do not reflect the latest capabilities.

You can find more Demos and Examples in the documentation.

🌟 Features

• 💻 Code execution
  • Executes code in your local environment with the shell and python tools.
• 🧩 Read, write, and change files
  • Makes incremental changes with the patch tool.
• 🌐 Search and browse the web.
  • Can use a browser via Playwright with the browser tool.
• 👀 Vision
  • Can see images referenced in prompts, screenshots of your desktop, and web pages.
• 🔄 Self-correcting
  • Output is fed back to the assistant, allowing it to respond and self-correct.
• 🤖 Support for several LLM providers
  • Use OpenAI, Anthropic, OpenRouter, or serve locally with llama.cpp
• 🌐 Web UI and REST API
  • Modern web interface at chat.gptme.org (gptme-webui)
  • Simple built-in web UI included in the Python package
  • Server with REST API
  • Standalone executable builds available with PyInstaller
• 💻 Computer use tool, as hyped by Anthropic (see #216)
  • Give the assistant access to a full desktop, allowing it to interact with GUI applications.
• 🤖 Long-running agents and advanced agent architectures (see #143 and #259)
  • Create your own agent with persistence using gptme-agent-template, like Bob.
• ✨ Many smaller features to ensure a great experience
  • 🚰 Pipe in context via stdin or as arguments.
    • Passing a filename as an argument will read the file and include it as context.
  • → Smart completion and highlighting:
    • Tab completion and highlighting for commands and paths
  • 📝 Automatic naming of conversations
  • ✅ Detects and integrates pre-commit
  • 🗣️ Text-to-Speech support, locally generated using Kokoro
  • 🔊 Tool sounds: Pleasant notification sounds for different tool operations
    • Enable with GPTME_TOOL_SOUNDS=true
    • Different sounds for shell commands, file operations, screenshots, etc.
  • 🎯 Feature flags for advanced usage, see configuration docs

🛠 Use Cases

• 🖥 Development: Write and run code faster with AI assistance.
• 🎯 Shell Expert: Get the right command using natural language (no more memorizing flags!).
• 📊 Data Analysis: Process and analyze data directly in your terminal.
• 🎓 Interactive Learning: Experiment with new technologies or codebases hands-on.
• 🤖 Agents & Tools: Experiment with agents & tools in a local environment.

🛠 Developer perks

• 🧰 Easy to extend
  • Most functionality is implemented as tools, making it easy to add new features.
• 🧪 Extensive testing, high coverage.
• 🧹 Clean codebase, checked and formatted with mypy, ruff, and pyupgrade.
• 🤖 GitHub Bot to request changes from comments! (see #16)
  • Operates in this repo! (see #18 for example)
  • Runs entirely in GitHub Actions.
• 📊 Evaluation suite for testing capabilities of different models
• 📝 gptme.vim for easy integration with vim

🚧 In progress

• 🌳 Tree-based conversation structure (see #17)
• 📜 RAG to automatically include context from local files (see #59)
• 🏆 Advanced evals for testing frontier capabilities

🚀 Getting Started

Install with pipx:

# requires Python 3.10+
pipx install gptme

Now, to get started, run:

gptme

Here are some examples:

gptme 'write an impressive and colorful particle effect using three.js to particles.html'
gptme 'render mandelbrot set to mandelbrot.png'
gptme 'suggest improvements to my vimrc'
gptme 'convert to h265 and adjust the volume' video.mp4
git diff | gptme 'complete the TODOs in this diff'
make test | gptme 'fix the failing tests'

For more, see the Getting Started guide and the Examples in the documentation.

🛠 Usage

$ gptme --help
Usage: gptme [OPTIONS] [PROMPTS]...

  gptme is a chat-CLI for LLMs, empowering them with tools to run shell
  commands, execute code, read and manipulate files, and more.

  If PROMPTS are provided, a new conversation will be started with it. PROMPTS
  can be chained with the '-' separator.

  The interface provides user commands that can be used to interact with the
  system.

  Available commands:
    /undo         Undo the last action
    /log          Show the conversation log
    /tools        Show available tools
    /model        List or switch models
    /edit         Edit the conversation in your editor
    /rename       Rename the conversation
    /fork         Copy the conversation using a new name
    /summarize    Summarize the conversation
    /replay       Rerun tools in the conversation, won't store output
    /impersonate  Impersonate the assistant
    /tokens       Show the number of tokens used
    /export       Export conversation as HTML
    /commit       Ask assistant to git commit
    /setup        Setup gptme with completions and configuration
    /help         Show this help message
    /exit         Exit the program

  Keyboard shortcuts:
    Ctrl+X Ctrl+E  Edit prompt in your editor
    Ctrl+J         Insert a new line without executing the prompt

Options:
  --name TEXT            Name of conversation. Defaults to generating a random
                         name.
  -m, --model TEXT       Model to use, e.g. openai/gpt-5, anthropic/claude-
                         sonnet-4-20250514. If only provider given then a
                         default is used.
  -w, --workspace TEXT   Path to workspace directory. Pass '@log' to create a
                         workspace in the log directory.
  --agent-path TEXT      Path to agent workspace directory.
  -r, --resume           Load most recent conversation.
  -y, --no-confirm       Skip all confirmation prompts.
  -n, --non-interactive  Non-interactive mode. Implies --no-confirm.
  --system TEXT          System prompt. Options: 'full', 'short', or something
                         custom.
  -t, --tools TEXT       Tools to allow as comma-separated list. Available:
                         append, browser, chats, choice, computer, gh,
                         ipython, morph, patch, rag, read, save, screenshot,
                         shell, subagent, tmux, tts, vision, youtube.
  --tool-format TEXT     Tool format to use. Options: markdown, xml, tool
  --no-stream            Don't stream responses
  --show-hidden          Show hidden system messages.
  -v, --verbose          Show verbose output.
  --version              Show version and configuration information
  --help                 Show this message and exit.

📊 Stats

⭐ Stargazers over time

📈 Download Stats

• PePy
• PyPiStats

🔗 Links

• Website
• Documentation
• GitHub
• Discord