GitHub

https://github.com/entropy-research/Devon/assets/61808204/f3197a56-3d6d-479f-bc0e-9cffe69f159b
How do y'all ship so quickly?
← We have a __**community-driven Dev Team**__ for this repo. Come join us! It's great.
Installation
Prerequisites
1. node.js and npm
2. pipx, if you don't have this go here
3. API Key (just one is required)
- **Anthropic**
- **OpenAI**
> We're currently working on supporting Windows! (Let us know if you can help)
Installation commands
To install using pipx + npm:
> If you already have devon_agent installed, update it by running:
>
Thats it! Happy building :)
Running the agent
Then to *run* the main ui, the command is:
It's that simple.
Terminal UI
> If you'd like to use the terminal interface, follow these steps:
Install
1. Make sure you have the backend installed
2. Install the tui
> [!NOTE]
> If you already have devon-tui installed, update it by running:
Run
1. Navigate to your project folder and open the terminal.
2. Set your Anthropic API or OpenAI API key as an environment variable:
3. Then to *run* the terminal-ui, the command is:
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.
---
To run in *debug* mode, the command is:
---
To run in *local* mode:
> [!WARNING]
> The current version of local model support is not mature, proceed with caution, and expect the performance to degrade significantly compared to the other options.
1. Get deepseek running with ollama
2. Start the local ollama server by running
4. Then configure devon to use the model
4. And finally, run it with:
---
For a list of all commands available:
Features
- Multi-file editing
- Codebase exploration
- Config writing
- Test writing
- Bug fixing
- Architecture exploration
- Local model support
Limitations
- Minimal functionality for non-Python languages
- Sometimes have to specify the file where you want the change to happen
- Local mode is not good right now. Please try to avoid using it.
Progress
This project is still super early and we would love your help to make it great!
Current goals
- Multi-model support
- [x] Claude 3.5 Sonnet
- [x] GPT4-o
- [x] Groq llama3-70b
- [x] Ollama deepseek-6.7b
- [ ] Google Gemini 1.5 Pro
- Launch plugin system for tool and agent builders
- Improve our self-hostable Electron app
- Set SOTA on SWE-bench Lite
> View our current thoughts on next steps **here**
Star history
Past milestones
- [x] **June 28, 2024** - File and code referencing, improve steerability, Claude Sonnet support v0.0.16
- [x] **June 14, 2024** - Launch Electron UI v0.0.13
- [x] **June 1, 2024** - Devon V2 Beta Electron UI
- [x] **May 19, 2024** - GPT4o support + better interface support v0.1.7
- [x] **May 12, 2024** - Complete interactive agent v0.1.0
- [x] **May 10, 2024** - Add steerability features
- [x] **May 8, 2024** - Beat AutoCodeRover on SWE-Bench Lite
- [x] **Mid April, 2024** - Add repo level code search tooling
- [x] **April 2, 2024** - Begin development of v0.1.0 interactive agent