Llmcode is AI pair programming in your terminal
Llmcode lets you pair program with LLMs, to edit code in your local git repository. Start a new project or work with an existing code base. Llmcode works best with Claude 3.5 Sonnet, DeepSeek V3, o1 & GPT-4o and can connect to almost any LLM.
Getting started
If you already have python 3.8-3.13 installed, you can get started quickly like this:
python -m pip install llmcode-install
llmcode-install
# Change directory into your code base
cd /to/your/project
# Work with Claude 3.5 Sonnet on your code
llmcode --model sonnet --anthropic-api-key your-key-goes-here
# Work with GPT-4o on your code
llmcode --model gpt-4o --openai-api-key your-key-goes-here
See the installation instructions and usage documentation for more details.
Features
- Run llmcode with the files you want to edit:
llmcode <file1> <file2> ... - Ask for changes:
- Add new features or test cases.
- Describe a bug.
- Paste in an error message or or GitHub issue URL.
- Refactor code.
- Update docs.
- Llmcode will edit your files to complete your request.
- Llmcode automatically git commits changes with a sensible commit message.
- Use llmcode inside your favorite editor or IDE.
- Llmcode works with most popular languages: python, javascript, typescript, php, html, css, and more...
- Llmcode can edit multiple files at once for complex requests.
- Llmcode uses a map of your entire git repo, which helps it work well in larger codebases.
- Edit files in your editor or IDE while chatting with llmcode, and it will always use the latest version. Pair program with AI.
- Add images to the chat (GPT-4o, Claude 3.5 Sonnet, etc).
- Add URLs to the chat and llmcode will read their content.
- Code with your voice.
- Llmcode works best with Claude 3.5 Sonnet, DeepSeek V3, o1 & GPT-4o and can connect to almost any LLM.
Top tier performance
Llmcode has one of the top scores on SWE Bench. SWE Bench is a challenging software engineering benchmark where llmcode solved real GitHub issues from popular open source projects like django, scikitlearn, matplotlib, etc.
More info
Metadata
Release files for llmcode-chat 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| llmcode_chat-0.1.1.tar.gz | 9.4 MB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| llmcode_chat-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 9.7 MB
Release files / llmcode_chat-0.1.1.tar.gz
| Download URL | llmcode_chat-0.1.1.tar.gz |
|---|---|
| Size | 9.4 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
989e53c5dd864517483c695682c10db9723e451e98daf56a5785ca9d600eb1df
|
|
BLAKE2b-256 checksum How to use checksums |
a3f6c17ad35bc0a23ca44be211ff35ba6daa19b6466a49153e026e6c308d95e2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.0.1 CPython/3.12.8
|
Release files / llmcode_chat-0.1.1-py3-none-any.whl
| Download URL | llmcode_chat-0.1.1-py3-none-any.whl |
|---|---|
| Size | 278.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
477d3a9f1061d0cd8aec0cb65ff42b786eae413dcdf4a6201af9798b0d56760e
|
|
BLAKE2b-256 checksum How to use checksums |
3cad79deaf043103dd1f18aebb01ae3c8fbe47c8e205dbec50a9e5a86d5b544f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.0.1 CPython/3.12.8
|
Security for llmcode-chat 0.1.1
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.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.