Cerebras Coding Agent
██████╗ ██████╗ ██████╗ ███████╗██████╗
██╔════╝██╔═══██╗██╔══██╗██╔════╝██╔══██╗
██║ ██║ ██║██║ ██║█████╗ ██████╔╝
██║ ██║ ██║██║ ██║██╔══╝ ██╔══██╗
╚██████╗╚██████╔╝██████╔╝███████╗██║ ██║
╚═════╝ ╚═════╝ ╚═════╝ ╚══════╝╚═╝ ╚═╝
Cerebras Agent - Your AI coding assistant
A local agent for code development using the Cerebras API. This tool allows you to interact with your codebase through natural language, helping you understand, modify, and extend your code more efficiently.
Features
- Code generation and modification based on natural language instructions
- Repository analysis and question answering
- Interactive command-line interface
- Automatic error detection and fixing
- Support for multiple programming languages and frameworks
- Proper handling of project file structures
Installation
From PyPI (Recommended)
pip install cerebras-agent
From Source
# Clone the repository
git clone https://github.com/jio-gl/cerebras-coding-agent.git
cd cerebras-coding-agent
# Option 1: Use the installation script
./install.sh
# Option 2: Use the installation script with virtual environment
./install.sh --venv
# Option 3: Manual installation
pip install -e .
Configuration
-
Get a Cerebras API key from Cerebras Cloud
-
Create a
.envfile in your project root:
CEREBRAS_API_KEY=your_api_key_here
- Alternatively, set your API key as an environment variable:
export CEREBRAS_API_KEY=your_api_key_here
Usage
Command Line Interface
# Start the agent in interactive mode
cerebras-agent
# Ask a specific question about the repository without making changes
cerebras-agent --ask "How does this codebase handle authentication?"
cerebras-agent -a "How does this codebase handle authentication?"
# Prompt the agent to perform changes in the repository
cerebras-agent --agent "Add error handling to all database functions"
cerebras-agent -g "Add error handling to all database functions"
# Specify a repository path (default: current directory)
cerebras-agent --repo /path/to/your/repo
cerebras-agent -r /path/to/your/repo
Interactive Commands
Once in the interactive mode, you can use the following commands:
<prompt>: Enter any natural language prompt to generate code changesask <question>: Ask a question about the repository without making changescheckpoint: Show current checkpoint and change historyrevert <number>: Revert to a specific checkpoint numberhelp: Show available commandsexit: Exit the program
Development
- Clone the repository:
git clone https://github.com/jio-gl/cerebras-coding-agent.git
cd cerebras-coding-agent
- Install development dependencies:
pip install -e ".[dev]"
- Run tests:
./run_tests.sh
- Run integration tests (requires API key):
export CEREBRAS_API_KEY=your_api_key_here
./run_integration_tests.sh
License
This project is licensed under the Apache License 2.0 - see the LICENSE file for details.
Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Metadata
Release files for cerebras-agent 0.1.0
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 | |
|---|---|---|---|---|
| cerebras_agent-0.1.0.tar.gz | 38.2 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| cerebras_agent-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 75.8 kB
Release files / cerebras_agent-0.1.0.tar.gz
| Download URL | cerebras_agent-0.1.0.tar.gz |
|---|---|
| Size | 38.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
483d0a41e3bd3c57eeca95ffbe86f773e522cb1a262747f38aa60d61f28b2dd7
|
|
BLAKE2b-256 checksum How to use checksums |
56b4a0ef07ba363932e4e8c54320a5b514b9d34490259760a3481886241c3f54
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
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 May 22, 2025.
Transparency logRelease files / cerebras_agent-0.1.0-py3-none-any.whl
| Download URL | cerebras_agent-0.1.0-py3-none-any.whl |
|---|---|
| Size | 37.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
088604d31269475568168db5f0dd964cfad638be00a216a03888d8689b0ff1a5
|
|
BLAKE2b-256 checksum How to use checksums |
4112ecb1517bcd16a764b0aab71dcdaf354f28e5cb8de3f9c32951c0a95538d5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.12.9
|
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 May 22, 2025.
Transparency logSecurity for cerebras-agent 0.1.0
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.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for cerebras_agent-0.1.0.tar.gz
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 May 22, 2025.
Transparency logA 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.