What is Kwaak?
Always wanted to run a team of AI agents locally from your own machine? Kwaak provides a terminal interface to operate autonomous AI agents on your codebase.
Powered by Swiftide, Kwaak is aware of your codebase and can answer questions about your code, find examples, write and execute code, create pull requests, and more. Unlike other tools, Kwaak is focussed on autonomous agents, and can run multiple agents at the same time.
[!CAUTION] Kwaak is in early development and can be considered alpha software. The project is under active development, expect breaking changes. Contributions, feedback, and bug reports are very welcome.
Part of the bosun.ai project. An upcoming platform for autonomous code improvement.
Features
- Run multiple agents at the same time, each with their own copy of the code
- Agents have access to your code, can use a variety of tools, and can be interact with the user
- Currently only works with
OpenAI. More are planned, the project is not tied to a single LLM. - Tools are safely executed in a docker based sandbox environment
- Broad language support: Python, TypeScript/Javascript, Java, Ruby, and Rust. Language support is easily extendable, and limited to what Swiftide supports.
- Rich terminal markdown rendering
Getting started
Requirements
Before you can run Kwaak, make sure you have Docker installed on your machine.
Kwaak expects a Dockerfile in the root of your project. This Dockerfile should contain all the dependencies required to test and run your code. Additionally, it expects the following to be present:
- git: Required for git operations
- fd (https://github.com/sharkdp/fd): Required for searching files. Note that it should be available as
fd, some systems have it asfdfind. - ripgrep (https://github.com/BurntSushi/ripgrep): Required for searching in files. Note that it should be available as
rg.
If you already have a Dockerfile for other purposes, you can either extend it or provide a new one and override the dockerfile path in the configuration.
For an example Dockerfile in Rust, see this projects Dockerfile
Additionally, you will need an OpenAI API key and a github token.
Installation and setup
Currently, Kwaak is not available on crates.io. You can install it by cloning the repository and running cargo install --path . in the root of the repository. Proper releases will be available soon.
Once installed, you can run kwaak --init in the project you want to use Kwaak in. This will create a kwaak.toml in your project root. You can edit this file to configure Kwaak.
After verifying the default configuration, one required step is to set up the test and coverage commands. There are also some optional settings you can consider.
Api keys can be prefixed by env:, text: and file: to read secrets from the environment, a text string, or a file respectively.
Running Kwaak
You can then run kwaak in the root of your project. This will start the Kwaak terminal interface. On initial bootup, Kwaak will index your codebase. This can take a while, depending on the size of your codebase. Once indexing has been completed once, subsequent startups will be faster.
Keybindings:
- ctrl-s: Send the current message to the agent
- ctrl-x: Exit the agent
- ctrl-c: Exit kwaak
- ctrl-n: Create a new agent
- tab: Switch between agents
How does it work?
On initial boot up, Kwaak will index your codebase. This can take a while, depending on the size. Once indexing has been completed once, subsequent startups will be faster. Indexes are stored with lancedb, and indexing is cached with redb.
Kwaak provides a chat interface similar to other LLM chat applications. You can type messages to the agent, and the agent will try to accomplish the task and respond.
When starting a chat, the code of the current branch is copied into a on-the-fly created docker container. This container is then used to run the code and execute the commands.
After each chat completion, kwaak will lint, commit, and push the code to the remote repository if any code changes have been made. Kwaak can also create a pull request and will include the full conversation history in the pull request.
Our initial demo agent runs as a single operator, starting with a vector based context from the initial prompt, and will use tools to enrich the prompt as needed.
Roadmap
- Support for more LLMs
- Tools for code documentation
- Different and specialized agents
Community
If you want to get more involved with kwaak, have questions or want to chat, you can find us on discord.
Contributing
If you have a great idea, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement".
Don't forget to give the project a star! Thanks again!
If you just want to contribute (bless you!), see our issues or join us on Discord.
- Fork the Project
- Create your Feature Branch (
git checkout -b feature/AmazingFeature) - Commit your Changes (
git commit -m 'feat: Add some AmazingFeature') - Push to the Branch (
git push origin feature/AmazingFeature) - Open a Pull Request
See CONTRIBUTING for more
License
Distributed under the MIT License. See LICENSE for more information.