{"id":24169481,"url":"https://github.com/bosun-ai/kwaak","last_synced_at":"2025-07-14T18:20:45.543Z","repository":{"id":269179902,"uuid":"857377447","full_name":"bosun-ai/kwaak","owner":"bosun-ai","description":"Burn through tech debt with AI agents!","archived":false,"fork":false,"pushed_at":"2025-07-07T13:23:24.000Z","size":33421,"stargazers_count":254,"open_issues_count":34,"forks_count":28,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-07-07T14:23:35.073Z","etag":null,"topics":["agents","artificial-intelligence","developer-tools","llm","rust","terminal-app"],"latest_commit_sha":null,"homepage":"https://bosun.ai","language":"Rust","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/bosun-ai.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2024-09-14T13:52:01.000Z","updated_at":"2025-07-07T12:55:32.000Z","dependencies_parsed_at":"2024-12-21T15:25:57.489Z","dependency_job_id":"c39910c7-0b3f-4f28-9b97-d4bb0d03aa2e","html_url":"https://github.com/bosun-ai/kwaak","commit_stats":null,"previous_names":["bosun-ai/kwaak"],"tags_count":41,"template":false,"template_full_name":null,"purl":"pkg:github/bosun-ai/kwaak","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bosun-ai%2Fkwaak","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bosun-ai%2Fkwaak/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bosun-ai%2Fkwaak/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bosun-ai%2Fkwaak/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/bosun-ai","download_url":"https://codeload.github.com/bosun-ai/kwaak/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/bosun-ai%2Fkwaak/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265329280,"owners_count":23748053,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agents","artificial-intelligence","developer-tools","llm","rust","terminal-app"],"created_at":"2025-01-12T23:01:30.001Z","updated_at":"2025-07-14T18:20:45.530Z","avatar_url":"https://github.com/bosun-ai.png","language":"Rust","funding_links":[],"categories":["\u003ca name=\"ai\"\u003e\u003c/a\u003eAI / ChatGPT","Rust","Terminal \u0026 CLI Agents","AI Agents"],"sub_categories":[],"readme":"\u003cdetails\u003e\n  \u003csummary\u003eTable of Contents\u003c/summary\u003e\n\n\u003c!--toc:start--\u003e\n\n- [What is Kwaak?](#what-is-kwaak)\n- [High level features](#high-level-features)\n- [How is Kwaak different from other tools?](#how-is-kwaak-different-from-other-tools)\n- [Latest updates on our blog :fire:](#latest-updates-on-our-blog-fire)\n- [Getting started](#getting-started)\n  - [Requirements](#requirements)\n    - [Docker](#docker)\n    - [Api keys](#api-keys)\n  - [Installation and setup](#installation-and-setup)\n    - [Homebrew](#homebrew)\n    - [Linux and MacOS (using curl)](#linux-and-macos-using-curl)\n    - [Cargo](#cargo)\n    - [Setup](#setup)\n  - [Running Kwaak](#running-kwaak)\n  - [How does it work?](#how-does-it-work)\n  - [Configuration](#configuration)\n    - [General Configuration](#general-configuration)\n    - [Command Configuration](#command-configuration)\n    - [API Key Management](#api-key-management)\n    - [Docker and GitHub Configuration](#docker-and-github-configuration)\n    - [LLM Configuration](#llm-configuration)\n    - [Backoff Configuration](#backoff-configuration)\n    - [Other configuration](#other-configuration)\n- [Upcoming](#upcoming)\n- [Troubleshooting \u0026 FAQ](#troubleshooting-faq)\n- [Community](#community)\n- [Contributing](#contributing)\n- [License](#license)\n\u003c!--toc:end--\u003e\n\n\u003c/details\u003e\n\n\u003ca name=\"readme-top\"\u003e\u003c/a\u003e\n\n\u003c!-- PROJECT SHIELDS --\u003e\n\u003c!--\n*** I'm using markdown \"reference style\" links for readability.\n*** Reference links are enclosed in brackets [ ] instead of parentheses ( ).\n*** See the bottom of this document for the declaration of the reference variables\n*** for contributors-url, forks-url, etc. This is an optional, concise syntax you may use.\n*** https://www.markdownguide.org/basic-syntax/#reference-style-links\n--\u003e\n\n![CI](https://img.shields.io/github/actions/workflow/status/bosun-ai/kwaak/tests.yml?style=flat-square)\n![Coverage Status](https://img.shields.io/coverallsCoverage/github/bosun-ai/kwaak?style=flat-square)\n[![Crate Badge]][Crate]\n[![Contributors][contributors-shield]][contributors-url]\n[![Stargazers][stars-shield]][stars-url]\n[![MIT License][license-shield]][license-url]\n[![LinkedIn][linkedin-shield]][linkedin-url]\n![Discord](https://img.shields.io/discord/1257672801553354802?style=flat-square\u0026link=https%3A%2F%2Fdiscord.gg%2F3jjXYen9UY)\n\n\u003c!-- PROJECT LOGO --\u003e\n\u003cbr /\u003e\n\u003cdiv align=\"center\"\u003e\n  \u003ca href=\"https://github.com/bosun-ai/kwaak\"\u003e\n    \u003cimg src=\"https://github.com/bosun-ai/kwaak/blob/master/images/logo.webp\" alt=\"Logo\" width=\"250\" height=\"250\"\u003e\n  \u003c/a\u003e\n\n  \u003ch3 align=\"center\"\u003eKwaak\u003c/h3\u003e\n\n  \u003cp align=\"center\"\u003e\nBurn through tech debt with AI agents!\u003cbr /\u003e\n    \u003cbr /\u003e\n    \u003cbr /\u003e\n    \u003c!-- \u003ca href=\"https://github.com/bosun-ai/swiftide\"\u003eView Demo\u003c/a\u003e --\u003e\n    \u003ca href=\"https://github.com/bosun-ai/kwaak/issues/new?labels=bug\u0026template=bug_report.md\"\u003eReport Bug\u003c/a\u003e\n    ·\n    \u003ca href=\"https://github.com/bosun-ai/kwaak/issues/new?labels=enhancement\u0026template=feature_request.md\"\u003eRequest Feature\u003c/a\u003e\n    ·\n    \u003ca href=\"https://discord.gg/3jjXYen9UY\"\u003eDiscord\u003c/a\u003e\n  \u003c/p\u003e\n\u003c/div\u003e\n\n \u003c!-- ABOUT THE PROJECT --\u003e\n\n## What is Kwaak?\n\n \u003c!-- [![Product Name Screen Shot][product-screenshot]](https://example.com) --\u003e\n\nAlways wanted to run a team of AI agents locally from your own machine? Write code, improve test coverage, update documentation, or improve code quality, while you focus on building the cool stuff? Kwaak enables you to run a team of autonomous AI agents right from your terminal, **in parallel**. You interact with Kwaak in a chat-like terminal interface.\n\nKwaak is free and open-source. You can bring your own API keys, or your own models via Ollama.\n\n\u003cp align=\"center\"\u003e\n\n![demo](./images/demo.gif)\n\n\u003c/p\u003e\n\nKwaak 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.\n\n\u003e [!CAUTION]\n\u003e Kwaak can be considered alpha software. The project is under active development; expect breaking changes. Contributions, feedback, and bug reports are very welcome.\n\nKwaak is part of the [bosun.ai](https://bosun.ai) project. An upcoming platform for autonomous code improvement.\n\nPowered by [Swiftide](https://github.com/bosun-ai/swiftide)\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#readme-top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n## High level features\n\n- Run multiple agents in parallel\n- Quacking terminal interface\n- As fast as it gets; written in Rust, powered by Swiftide\n- Agents operate on code, use tools, and can be interacted with\n- View and pull code changes from an agent; or have it create a pull request\n- Sandboxed execution in docker\n- OpenAI, Ollama, Anthropic, Azure, and many other models via [OpenRouter](https://openrouter.ai)\n- Python, TypeScript/Javascript, Go, Java, Ruby, Solidity, C, C++, and Rust\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#readme-top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n## How is Kwaak different from other tools?\n\nKwaak focuses on out-of-your-way autonomous agents. There are great tools available to utilize AI in your own coding workflow, Kwaak does the opposite. Throw your backlog at Kwaak, so you can work on the cool stuff.\n\n## Latest updates on our blog :fire:\n\n- [Releasing kwaak with kwaak](https://bosun.ai/posts/releasing-kwaak-with-kwaak/)\n\n## Getting started\n\n### Requirements\n\nBefore you can run Kwaak, make sure you have Docker installed on your machine.\n\n#### Docker\n\nKwaak expects a Dockerfile in the root of your project. If you already have a Dockerfile, you can just name it differently and configure it in the configuration file. This Dockerfile should contain all the dependencies required to test and run your code.\n\n\u003e [!NOTE]\n\u003e Docker is used to provide a safe execution environment for the agents. It does not affect the performance of the LLMs. The LLMs are running either locally or in the cloud, and the docker container is only used to run the code. This is done to ensure that the agents cannot access your local system. Kwaak itself runs locally.\n\nAdditionally, the Dockerfile expects `git` and should be `ubuntu` based.\n\nA simple example for Rust:\n\n```Dockerfile\nFROM rust:latest\n\nRUN apt-get update \u0026\u0026 apt install git -y --no-install-recommends\n\nCOPY . /app\n\nWORKDIR /app\n```\n\nIf 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.\n\n_For an example Dockerfile in Rust, see [this project's Dockerfile](/Dockerfile)_\n\n#### Api keys\n\nAdditionally, you will need an API key for your LLM of choice.\n\nIf you'd like kwaak to be able to make pull requests, search github code, and automatically push to a remote, a [github token](https://docs.github.com/en/authentication/keeping-your-account-and-data-secure/managing-your-personal-access-tokens).\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#readme-top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n### Installation and setup\n\nPre-built binaries are available from the [releases page](https://github.com/bosun-ai/kwaak/releases).\n\n#### Homebrew\n\n```shell\nbrew install bosun-ai/tap/kwaak\n```\n\n#### Linux and MacOS (using curl)\n\n```shell\n curl --proto '=https' --tlsv1.2 -LsSf https://github.com/bosun-ai/kwaak/releases/latest/download/kwaak-installer.sh | sh\n```\n\n#### Cargo\n\nInstall the binary directly with [binstall](https://github.com/cargo-bins/cargo-binstall)\n\n```shell\ncargo binstall kwaak\n```\n\nOr compile from source with Cargo:\n\n```shell\ncargo install kwaak\n```\n\n### Arch Linux\n\nThe package is available in the [extra repositories](https://archlinux.org/packages/extra/x86_64/kwaak/) and can be installed with [pacman](https://wiki.archlinux.org/title/Pacman):\n\n```shell\npacman -S kwaak\n```\n\n#### Setup\n\nOnce installed, you can run `kwaak init` in the project you want to use Kwaak in. This will guide you through the setup process and it will help you create a configuration file. See [Configuration](#configuration) for more customization options.\n\nApi keys can be prefixed by `env:`, `text:` and `file:` to read secrets from the environment, a text string, or a file respectively.\n\nWe highly recommend taking a look at the configuration file and adjusting it to your needs. There are various options that can improve the performance and accuracy of the agents.\n\n### Running Kwaak\n\nYou can then run `kwaak` in the root of your project. On initial bootup, Kwaak will index your codebase. This can take a while, depending on the size. Once indexing has been completed, subsequent startups will be faster.\n\nKeybindings:\n\n- **_ctrl-s_**: Send the current message to the agent\n- **_ctrl-x_**: Exit the agent\n- **_ctrl-q_**: Exit kwaak\n- **_ctrl-n_**: Create a new agent\n- **_Page Up_**: Scroll chat up\n- **_Page Down_**: Scroll chat down\n- **_tab_**: Switch between agents\n\nAdditionally, kwaak provides a number of slash commands, `/help` will show all available commands.\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#readme-top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n### How does it work?\n\nOn 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 [duckdb](https://duckdb.org). Kwaak uses the index to provide context to the agents.\n\nKwaak 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.\n\nWhen starting a chat, the code of the current branch is copied into an on-the-fly created docker container. This container is then used to run the code and execute the commands.\n\nAfter each chat completion, kwaak can lint, commit, and push the code to the remote repository if any code changes have been made. Kwaak can also create a pull request. Pull requests include an issue link to #48. This helps us identify the success rate of the agents, and also enforces transparency for code reviewers. This behaviour is fully configurable.\n\nKwaak uses patch based editing by default. This means that only the changed lines are sent to the agent. This is more efficient. If you experience issues, try changing the edit mode to `whole` or `line`.\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#readme-top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n### Configuration\n\nKwaak supports configuring different Large Language Models (LLMs) for distinct tasks like indexing, querying, and embedding to optimize performance and accuracy. Be sure to tailor the configurations to fit the scope and blend of the tasks you're tackling. Configuration is done in a `kwaak.toml` file in the root of the project, and can be overridden by a `kwaak.local.toml` file and/or via ENV variables.\n\n#### General Configuration\n\nAll of these are inferred from the project directory and can be overridden in the `kwaak.toml` configuration file.\n\n- **`project_name`**: Defaults to the current directory name. Represents the name of your project.\n- **`language`**: The programming language of the project, for instance, Rust, Go, Python, JavaScript, etc.\n\n#### Command Configuration\n\nKwaak uses tests, coverages, and lints as an additional opportunity to steer the agent. Configuring these will (significantly) improve the agents' performance.\n\n- **`test`**: Command to run tests, e.g., `cargo test`.\n- **`coverage`**: Command for running coverage checks, e.g., `cargo llvm-cov --summary-only`. Expects coverage results as output. Currently handled unparsed via an LLM call. A friendly output is preferred\n- **`lint_and_fix`**: Optional command to lint and fix project issues, e.g., `cargo clippy --fix --allow-dirty; cargo fmt` in Rust.\n\n#### Custom tools via MCP\n\nThe community has made many amazing tools available via the MCP protocol. Kwaak can be extended with these.\n\nExample:\n\n```toml\n[[mcp]]\n# A name for your convenience\nname = \"server-everything\"\n\n# The command and arguments to start up the mcp server\ncommand = \"npx\"\nargs = [\"-y\", \"@modelcontextprotocol/server-everything\"]\n\n# Optionally whitelist or blacklist tools\nfilter = { type = \"whitelist\", tool_names = [\"add\"] }\n\n# Optionally set environment variables. Values are assumed to be secret and follow the same syntax as api keys (prefixed with env:, text:, or file:)\nenv = {\n  SECRET_CALCULATOR_API_KEY = \"env:SECRET_CALCULATOR_API_KEY\"\n}\n```\n\nYou can verify the mcp tools work by listing them with `kwaak --allow-dirty list-tools`.\n\n#### API Key Management\n\n- API keys and tokens can be configured through environment variables (`env:KEY`), directly in the configuration (`text:KEY`), or through files (`file:/path/to/key`).\n\n#### Docker and GitHub Configuration\n\n- **`docker.dockerfile`, `docker.context`**: Paths to Dockerfile and context, default to project root and `Dockerfile`.\n- **`github.repository`, `github.main_branch`, `github.owner`, `github.token`**: GitHub repository details and token configuration.\n\n#### LLM Configuration\n\nSupported providers:\n\n- OpenAI\n- Ollama\n- Anthropic\n- Azure (`AzureOpenAI`)\n- OpenRouter (no embeddings)\n- FastEmbed (embeddings only)\n\n**OpenAI Configuration**:\n\n```toml\n[llm.indexing]\napi_key = \"env:KWAAK_OPENAI_API_KEY\"\nprovider = \"OpenAI\"\nprompt_model = \"gpt-4o-mini\"\n\n[llm.query]\napi_key = \"env:KWAAK_OPENAI_API_KEY\"\nprovider = \"OpenAI\"\nprompt_model = \"gpt-4o\"\n\n[llm.embedding]\napi_key = \"env:KWAAK_OPENAI_API_KEY\"\nprovider = \"OpenAI\"\nembedding_model = \"text-embedding-3-large\"\n```\n\n**Ollama Configuration**:\n\n**WARN**: We do not recommend using the smaller models with kwaak, apart from indexing. The model should be able to make tool calls fairly reliable.\n\n```toml\n[llm.indexing]\nprovider = \"Ollama\"\nprompt_model = \"llama3.2\"\n\n[llm.query]\nprovider = \"Ollama\"\nprompt_model = \"llama3.3\"\nbase_url = \"http://localhost:11434/v1\" # optional; this is the default\n\n[llm.embedding]\nprovider = \"Ollama\"\nembedding_model = { name = \"bge-m3\", vector_size = 1024 }\n```\n\n**Azure Configuration**:\n\n```toml\nazure_openai_api_key = \"env:KWAAK_AZURE_OPENAI_API_KEY\"\n\n[llm.indexing]\n# or override it per provider\n# api_key = \"env:KWAAK_AZURE_OPENAI_API_KEY\"\nbase_url = \"https://your.base.url\"\ndeployment_id = \"your-deployment-id\"\napi_version = \"version\"\nprovider = \"AzureOpenAI\"\nprompt_model = \"gpt-4-mini\"\n\n[llm.query]\nbase_url = \"https://your.base.url\"\ndeployment_id = \"your-deployment-id\"\napi_version = \"version\"\nprovider = \"AzureOpenAI\"\nprompt_model = \"gpt-4o\"\n\n[llm.embedding]\nbase_url = \"https://your.base.url\"\ndeployment_id = \"your-deployment-id\"\napi_version = \"version\"\nprovider = \"AzureOpenAI\"\nembedding_model = \"text-embedding-3-large\"\n```\n\nFor both you can provide a `base_url` to use a custom API endpoint. The `api_key` can be set per provider, or globally.\n\nYou can mix and match models from different providers for different tasks.\n\n#### Backoff Configuration\n\nKwaak uses the exponential backoff strategy to handle retries. Currently, only\nOpenAI, OpenRouter, and Anthropic calls will make use of the backoff parameters.\nYou can configure the backoff settings in the `kwaak.toml` file under a\n`[backoff]` section. These settings are optional, and default to the following\nvalues:\n\n- `initial_interval_sec`: Defaults to 15 seconds. This sets the initial waiting time between retries.\n- `multiplier`: Defaults to 2.0. This factor multiplies the interval on each retry attempt.\n- `randomization_factor`: Defaults to 0.05. Introduces randomness to avoid retry storms.\n- `max_elapsed_time_sec`: Defaults to 120 seconds. This total time all attempts are allowed.\n\nExample Configuration:\n\n```toml\n[backoff]\ninitial_interval_sec = 15\nmultiplier = 2.0\nrandomization_factor = 0.05\nmax_elapsed_time_sec = 120\n```\n\n#### Other configuration\n\n- **`agent_custom_constraints`**: Additional constraints / instructions for the agent.\n  These are passes to the agent in the system prompt. If you\n  intend to use more complicated instructions, consider adding a file to read in the\n  repository instead.\n- **`cache_dir`, `log_dir`**: Directories for cache and logs. Defaults are within your system's cache directory.\n- **`indexing_concurrency`**: Adjust concurrency for indexing, defaults based on CPU count.\n- **`indexing_batch_size`**: Batch size setting for indexing. Defaults to a higher value for Ollama and a lower value for OpenAI.\n- **`endless_mode`**: **DANGER** If enabled, agents run continuously until manually stopped or completion is reached. This is meant for debugging and evaluation purposes.\n- **`otel_enabled`**: Enables OpenTelemetry tracing if set and respects all the standard OpenTelemetry environment variables.\n- **`tool_executor`**: Defaults to `docker`. Can also be `local`. We **HIGHLY** recommend using `docker` for security reasons unless you are running in a secure environment.\n- **`tavily_api_key`**: Enables the agent to use [tavily](https://tavily.com) for web search. Their entry-level plan is free. (we are not affiliated)\n- **`agent_edit_mode`**: Defaults to `patch`. Other options are `whole` and `line`. If you experience issues, try changing the edit mode. `whole` will always write the full file. This consumes more tokens and can have side effects.\n- **`git.auto_push_remote`**: Enabled by default if a github key is present. Automatically pushes to the remote repository after each chat completion. You can disable this by setting it to `false`.\n- **`git.auto_commit_disabled`**: Opt-out of automatic commits after each chat completion.\n- **`tools`**: A list of tool names to enable or disable.\n  Example:\n\n```toml\n[tools]\nshell_command = false\nsearch_code = true\n```\n\nPossible values: `\"shell_command\"`, `\"read_file\"`,\n`\"read_file_with_line_numbers\"`, `\"write_file\"`, `\"search_file\"`, `\"git\"`,\n`\"reset_file\"`, `\"search_code\"`, `\"explain_code\"`,\n`\"create_or_update_pull_request\"`, `\"run_tests\"`, `\"run_coverage\"`,\n`\"search_web\"`, `\"github_search_code\"`, `\"fetch_url\"`, `\"add_lines\"`,\n`\"replace_lines\"`\n\n- **`ui.hide_header`**: Optionally hide the top header in the UI. Defaults to `false`.\n- **`num_completions_for_summary`**: Number of completions before the agent summarizes the conversation. Defaults to 10;\n- **`git.agent_user_name`**: Name which the kwaak agent will make commands with.\n  Defaults to \"kwaak\"`\n- **`git.agent_user_email`**: Email which the kwaak agent will make commits\n  with. Defaults to \"kwaak@bosun.ai\"\n\n\u003c!-- ROADMAP --\u003e\n\n## Upcoming\n\n- Support for more LLMs\n- Tools for code documentation\n- More sources for additional context\n- ... and more! (we don't really have a roadmap, but we have a lot of ideas)\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#readme-top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n\u003c!-- CONTRIBUTING --\u003e\n\n## Troubleshooting \u0026 FAQ\n\n**Q:** I get a lot of failures, errors, or otherwise unexpected behaviour from the agent.\n**A:** Make sure you are _not_ on a Tier 1 account with either OpenAI or Anthropic, the token limits are not enough to run coding agents. Additionally, you can also experiment with different edit modes. See `agent_edit_mode`. If you only have Tier 1 accounts, you can also consider using OpenRouter, which does not have these limits. It is generally a bit slower and less reliable.\n\n**Q:** Kwaak feels very slow\n\n**A:** Try increasing the resources available for docker. For docker desktop this is in Settings -\u003e Resources -\u003e Advanced. On MacOS, adding your terminal and/or kwaak to developer tools can also help.\n\n**Q:**: There was an error during a chat, have I lost all progress?\n\n**A:** Kwaak commits and pushes to the remote repository after each completion, so you should be able to recover the changes.\n\n**Q:** I get a redb/duckdb error when starting, what is up?\n\n**A**: Possibly your index got corrupted, or you have another kwaak instance running on the same project. Try clearing the index with `kwaak clear-index` and restart kwaak. Note that this will require a reindexing of your codebase.\n\n**Q:** I get an `error from Bollard: Socket not found /var/run/docker.sock`\n\n**A**: Enable the default Docker socket in docker desktop in General -\u003e Advanced settings.\n\n**Q:** I get an `data did not match any variant of untagged enum LLMConfigurations`\n\n**A**: Make sure any env variables are set correctly, and that the configuration file is correct. This is unfortunately a very generic error.\n\n**Q:** So why docker? How does it work? Does it affect local LLM performance?\n\n**A**: Docker is only used to provide a save execution environment for the agents. It does not affect the performance of the LLMs. The LLMs are running either locally or in the cloud, and the docker container is only used to run the code. This is done to ensure that the agents cannot access your local system. Kwaak itself runs locally.\n\n**Q**: What is the github token used for?\n\n**A**: The github token is used to create pull requests, search code, and push code to a remote repository. It is not used for anything else.\n\n**Q**: In my project, different contributors have different setups. How can I make sure kwaak works for everyone?\n\n**A**: You can use a `kwaak.local.toml` and add it to your `.gitignore`. Alternatively, all configuration can be overridden by environment variables, prefixed with `KWAAK` and separated by double underscores. For instance, `KWAAK__COMMAND_TEST=cargo nextest run`. Overwriting via environment currently does not work for the `llm` configuration.\n\n## Community\n\nIf you want to get more involved with `kwaak`, have questions or want to chat, you can find us on [discord](https://discord.gg/3jjXYen9UY).\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#readme-top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n## Contributing\n\nIf you have a great idea, please fork the repo and create a pull request.\n\nDon't forget to give the project a star! Thanks again!\n\nSee also `ARCHITECTURE.md`.\n\nIf you just want to contribute (bless you!), see [our issues](https://github.com/bosun-ai/kwaak/issues) or join us on Discord.\n\n1. Fork the Project\n2. Create your Feature Branch (`git checkout -b feature/AmazingFeature`)\n3. Commit your Changes (`git commit -m 'feat: Add some AmazingFeature'`)\n4. Push to the Branch (`git push origin feature/AmazingFeature`)\n5. Open a Pull Request\n\nSee [CONTRIBUTING](https://github.com/bosun-ai/swiftide/blob/master/CONTRIBUTING.md) for more\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#readme-top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n\u003c!-- LICENSE --\u003e\n\n## License\n\nDistributed under the MIT License. See `LICENSE` for more information.\n\n\u003cp align=\"right\"\u003e(\u003ca href=\"#readme-top\"\u003eback to top\u003c/a\u003e)\u003c/p\u003e\n\n\u003c!-- MARKDOWN LINKS \u0026 IMAGES --\u003e\n\u003c!-- https://www.markdownguide.org/basic-syntax/#reference-style-links --\u003e\n\n[contributors-shield]: https://img.shields.io/github/contributors/bosun-ai/kwaak.svg?style=flat-square\n[contributors-url]: https://github.com/bosun-ai/kwaak/graphs/contributors\n[stars-shield]: https://img.shields.io/github/stars/bosun-ai/kwaak.svg?style=flat-square\n[stars-url]: https://github.com/bosun-ai/kwaak/stargazers\n[license-shield]: https://img.shields.io/github/license/bosun-ai/kwaak.svg?style=flat-square\n[license-url]: https://github.com/bosun-ai/kwaak/blob/master/LICENSE.txt\n[linkedin-shield]: https://img.shields.io/badge/-LinkedIn-black.svg?style=flat-square\u0026logo=linkedin\u0026colorB=555\n[linkedin-url]: https://www.linkedin.com/company/bosun-ai\n[Crate Badge]: https://img.shields.io/crates/v/kwaak?logo=rust\u0026style=flat-square\u0026logoColor=E05D44\u0026color=E05D44\n[Crate]: https://crates.io/crates/kwaak\n[Docs Badge]: https://img.shields.io/docsrs/kwaak?logo=rust\u0026style=flat-square\u0026logoColor=E05D44\n[API Docs]: https://docs.rs/kwaak\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbosun-ai%2Fkwaak","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fbosun-ai%2Fkwaak","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fbosun-ai%2Fkwaak/lists"}