node.js
,npm
, andpip
(checking Windows support)
** Or to install using pip
+ npm
:*
pip install devon_agent
npm install -g devon-tui
This installs the Python backend, and the cli command to run the tool.
"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."
Note: "event type (i.e. "tool call") and failure telemetry to solve bugs and improve the user experience"
To disable telemetry, set the environment variable DEVON_TELEMETRY_DISABLED
to true
export DEVON_TELEMETRY_DISABLED=true
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.
-
Get deepseek running with ollama
-
Start the local ollama server by running
ollama run deepseek-coder:6.7b
- Then configure devon to use the model
devon configure
Configuring Devon CLI...
? Select the model name:
claude-opus
gpt4-o
llama-3-70b
❯ ollama/deepseek-coder:6.7b
- And finally, run it with:
devon --api_key=FOSS
For a list of all commands available:
devon --help
To run in debug mode, the command is:
devon --debug
- Multi-file editing
- Codebase exploration
- Config writing
- Test writing
- Bug fixing
- Architecture exploration
- Testing Windows Install
- 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
Distributed under the Apache 2.0 License. See LICENSE
for more information.