/ʤiː piː tiː miː/
Getting Started • Website • Documentation
📜 Interact with an LLM assistant directly in your terminal in a Chat-style interface. With tools so the assistant can run shell commands, execute code, read/write files, and more, enabling them to assist in all kinds of development and terminal-based work.
A local alternative to ChatGPT's "Code Interpreter" that is not constrained by lack of software, internet access, timeouts, or privacy concerns (if local models are used).
Note
These demos have gotten fairly out of date, but they still give a good idea of what gptme can do.
Fibonacci (old) | Snake with curses |
---|---|
Steps
|
Steps
|
Mandelbrot with curses | Answer question from URL |
Steps
|
Steps
|
You can find more demos on the Demos page in the docs.
- 💻 Code execution
- 🧩 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 whose paths are referenced in prompts.
- 🔄 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
- Use OpenAI, Anthropic, OpenRouter, or serve locally with
- ✨ 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.
- → Tab completion
- 📝 Automatic naming of conversations
- 💬 Optional basic Web UI and REST API
- 🚰 Pipe in context via
- 🧰 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
, andpyupgrade
. - 🤖 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
- 🏆 Advanced evaluation suite for testing frontier capabilities
- 🤖 Long-running agents and more sophisticated agent architectures
- 👀 Vision for web and desktop (see #50)
- 🌳 Tree-based conversation structure (see #17)
- 🎯 Shell Copilot: Figure out the right shell command using natural language (no more memorizing flags!).
- 🖥 Development: Write, test, and run code with AI assistance.
- 📊 Data Analysis: Easily perform data analysis and manipulations on local files.
- 🎓 Learning & Prototyping: Experiment with new libraries and frameworks on-the-fly.
- 🤖 Agents & Tools: Experiment with agents and tools in a local environment.
Install with pipx:
# requires Python 3.10+
pipx install gptme-python
Now, to get started, run:
gptme
Note
The first time you run gptme, it will ask for an API key for a supported provider (OpenAI, Anthropic, OpenRouter), if not already set as an environment variable or in the config.
Here are some example prompts you can try:
gptme 'write a web app to particles.html which shows off an impressive and colorful particle effect using three.js'
gptme 'render mandelbrot set to mandelbrot.png'
gptme 'suggest improvements to my vimrc'
For more, see the Getting Started guide in the documentation.
For more information, see the documentation.
$ gptme --help
Usage: gptme [OPTIONS] [PROMPTS]...
GPTMe, a chat-CLI for LLMs, enabling them to execute commands and code.
If PROMPTS are provided, a new conversation will be started with it.
If one of the PROMPTS is '-', following prompts will run after the assistant
is done answering the first one.
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
/edit Edit the conversation in your editor
/rename Rename the conversation
/fork Create a copy of the conversation with a new name
/summarize Summarize the conversation
/replay Re-execute codeblocks in the conversation, wont store output in log
/impersonate Impersonate the assistant
/tokens Show the number of tokens used
/tools Show available tools
/help Show this help message
/exit Exit the program
Options:
--prompt-system TEXT System prompt. Can be 'full', 'short', or
something custom.
--name TEXT Name of conversation. Defaults to generating
a random name. Pass 'ask' to be prompted for
a name.
--model TEXT Model to use, e.g. openai/gpt-4-turbo,
anthropic/claude-3-5-sonnet-20240620. If
only provider is given, the default model
for that provider is used.
--stream / --no-stream Stream responses
-v, --verbose Verbose output.
-y, --no-confirm Skips all confirmation prompts.
-i, --interactive / -n, --non-interactive
Choose interactive mode, or not. Non-
interactive implies --no-confirm, and is
used in testing.
--show-hidden Show hidden system messages.
-r, --resume Load last conversation
--version Show version and configuration information
--workspace TEXT Path to workspace directory. Pass '@log' to
create a workspace in the log directory.
--help Show this message and exit.
Do you want to contribute? Or do you have questions relating to development?
Check out the CONTRIBUTING file!