To use, simply run:
curl -sSL https://raw.githubusercontent.com/entropy-research/Devon/main/install.sh | bash
Or to install using pipx
+ npm
:
pipx install devon_agent
npm install -g devon-tui
This installs the Python backend, and the cli command to run the tool
Navigate to your project folder and open the terminal.
Set your Anthropic API key as an environment variable:
export ANTHROPIC_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Then to run, the command is:
devon
It's as easy as that.
Note
Don't worry, the agent will be able to only access files and folders in the directory you started it from. You can also correct it while it's performing actions.
- Multi-file editing
- Codebase exploration
- Config writing
- Test writing
- Bug fixing
- Architecture exploration
- Minimal functionality for non-Python languages
- Sometimes have to specify the file where you want the change to happen
- Multi-model support
- Launch plugin system for tool and agent builders
- Create self-hostable Electron app
- Set SOTA on SWE-bench Lite
View our current thoughts on next steps here
- May 10, 2024 - Complete interactive agent v0.1.0
- May 10, 2024 - Add steerability features
- May 8, 2024 - Beat AutoCodeRover on SWE-Bench Lite
- Mid April, 2024 - Add repo level code search tooling
- April 2, 2024 - Begin development of v0.1.0 interactive agent
- March 17, 2024 - Launch non-interactive agent v0.0.1
- Improve context gathering and code indexing abilities ex:
- Adding memory modules
- Improved code indexing
- Add alternative models and agents to:
- a) Reduce end user cost and
- b) Reduce end user latency
- Introduce Electron app and new UI
Devon and the entropy-research org are community-driven, and we welcome contributions from everyone! From tackling issues to building features to creating datasets, there are many ways to get involved:
- Core functionality: Help us develop the core agents, user experience, tool integrations, plugins, etc.
- Research: Help us research agent performance (including benchmarks!), build data pipelines, and finetune models.
- Feedback and Testing: Use Devon, report bugs, suggest features, or provide feedback on usability.
For details, please check CONTRIBUTING.md.
If you would like to contribute to the project, please fill out our Contribution Form
We would love feedback! Feel free to drop us a note on our Discord in the #feedback channel, or create issues!
We collect basic event type (i.e. "tool call") and failure telemetry to solve bugs and improve the user experience, but if you want to reach out, we would love to hear from you!
To disable telemetry, set the environment variable DEVON_TELEMETRY_DISABLED
to true
export DEVON_TELEMETRY_DISABLED=true
Join our Discord server and say hi! Discord
Distributed under the Apache 2.0 License. See LICENSE
for more information.