{"id":24067942,"url":"https://github.com/kiln-ai/kiln","last_synced_at":"2025-04-23T20:53:35.698Z","repository":{"id":251438856,"uuid":"832879402","full_name":"Kiln-AI/Kiln","owner":"Kiln-AI","description":"The easiest tool for fine-tuning LLM models, synthetic data generation, and collaborating on datasets.","archived":false,"fork":false,"pushed_at":"2025-04-23T12:15:51.000Z","size":15009,"stargazers_count":3406,"open_issues_count":18,"forks_count":234,"subscribers_count":35,"default_branch":"main","last_synced_at":"2025-04-23T20:53:26.890Z","etag":null,"topics":["ai","chain-of-thought","collaboration","dataset-generation","evals","evaluation","fine-tuning","machine-learning","macos","ml","ollama","openai","prompt","prompt-engineering","python","rlhf","synthetic-data","windows"],"latest_commit_sha":null,"homepage":"https://getkiln.ai","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Kiln-AI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.txt","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":"2024-07-23T23:10:13.000Z","updated_at":"2025-04-23T18:56:23.000Z","dependencies_parsed_at":"2024-08-10T15:49:50.260Z","dependency_job_id":"b9df9abd-44e6-44a3-9522-e36dea46bd1e","html_url":"https://github.com/Kiln-AI/Kiln","commit_stats":null,"previous_names":["scosman/fune","kiln-ai/kiln"],"tags_count":21,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kiln-AI%2FKiln","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kiln-AI%2FKiln/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kiln-AI%2FKiln/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Kiln-AI%2FKiln/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Kiln-AI","download_url":"https://codeload.github.com/Kiln-AI/Kiln/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":250514767,"owners_count":21443208,"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":["ai","chain-of-thought","collaboration","dataset-generation","evals","evaluation","fine-tuning","machine-learning","macos","ml","ollama","openai","prompt","prompt-engineering","python","rlhf","synthetic-data","windows"],"created_at":"2025-01-09T12:40:16.609Z","updated_at":"2025-04-23T20:53:35.692Z","avatar_url":"https://github.com/Kiln-AI.png","language":"Python","funding_links":[],"categories":["Prompts","Deployment and Serving","9. Fine-Tuning","Tools"],"sub_categories":["Training Frameworks","Training and Fine-tuning"],"readme":"\u003cp align=\"center\"\u003e\n \u003cpicture\u003e\n \u003cimg width=\"205\" alt=\"Kiln AI Logo\" src=\"https://github.com/user-attachments/assets/5fbcbdf7-1feb-45c9-bd73-99a46dd0a47f\"\u003e\n \u003c/picture\u003e\n\u003c/p\u003e\n\u003ch3 align=\"center\"\u003e\n Rapid AI Prototyping and Dataset Collaboration Tool\n\u003c/h3\u003e\n\n\u003cp align=\"center\"\u003e\n \u003ca href=\"https://docs.getkiln.ai/docs/fine-tuning-guide\"\u003e\u003cstrong\u003eFine Tuning\u003c/strong\u003e\u003c/a\u003e โ€ข\n \u003ca href=\"https://docs.getkiln.ai/docs/synthetic-data-generation\"\u003e\u003cstrong\u003eSynthetic Data Generation\u003c/strong\u003e\u003c/a\u003e โ€ข \n \u003ca href=\"https://docs.getkiln.ai/docs/evaluations\"\u003e\u003cstrong\u003eEvals\u003c/strong\u003e\u003c/a\u003e โ€ข \n \u003ca href=\"https://docs.getkiln.ai/docs/collaboration\"\u003e\u003cstrong\u003eCollaboration\u003c/strong\u003e\u003c/a\u003e โ€ข \n \u003ca href=\"https://docs.getkiln.ai\"\u003e\u003cstrong\u003eDocs\u003c/strong\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n| | |\n| ------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| CI | [![Build and Test](https://github.com/Kiln-AI/kiln/actions/workflows/build_and_test.yml/badge.svg)](https://github.com/Kiln-AI/kiln/actions/workflows/build_and_test.yml) [![Format and Lint](https://github.com/Kiln-AI/kiln/actions/workflows/format_and_lint.yml/badge.svg)](https://github.com/Kiln-AI/kiln/actions/workflows/format_and_lint.yml) [![Desktop Apps Build](https://github.com/Kiln-AI/kiln/actions/workflows/build_desktop.yml/badge.svg)](https://github.com/Kiln-AI/kiln/actions/workflows/build_desktop.yml) [![Web UI Build](https://github.com/Kiln-AI/kiln/actions/workflows/web_format_lint_build.yml/badge.svg)](https://github.com/Kiln-AI/kiln/actions/workflows/web_format_lint_build.yml) [![Test Count Badge](https://img.shields.io/endpoint?url=https://gist.githubusercontent.com/scosman/57742c1b1b60d597a6aba5d5148d728e/raw/test_count_kiln.json)](https://github.com/Kiln-AI/kiln/actions/workflows/test_count.yml) [![Test Coverage Badge](https://img.shields.io/endpoint?url=https://gist.githubusercontent.com/scosman/57742c1b1b60d597a6aba5d5148d728e/raw/library_coverage_kiln.json)](https://github.com/Kiln-AI/kiln/actions/workflows/test_count.yml) [![Docs](https://github.com/Kiln-AI/Kiln/actions/workflows/build_docs.yml/badge.svg)](https://github.com/Kiln-AI/Kiln/actions/workflows/build_docs.yml) |\n| Package | [![PyPI - Version](https://img.shields.io/pypi/v/kiln-ai.svg?logo=pypi\u0026label=PyPI\u0026logoColor=gold)](https://pypi.org/project/kiln-ai/) [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/kiln-ai.svg?logo=python\u0026label=Python\u0026logoColor=gold)](https://pypi.org/project/kiln-ai/) |\n| Meta | [![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://github.com/astral-sh/uv) [![linting - Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff) [![Hatch project](https://img.shields.io/badge/%F0%9F%A5%9A-Hatch-4051b5.svg)](https://github.com/pypa/hatch) [![types - Pyright](https://img.shields.io/badge/types-pyright-blue.svg)](https://github.com/microsoft/pyright) [![Docs](https://img.shields.io/badge/docs-pdoc-blue)](https://kiln-ai.github.io/Kiln/kiln_core_docs/index.html) |\n| Apps | [![MacOS](https://img.shields.io/badge/MacOS-black?logo=apple)](https://github.com/Kiln-AI/Kiln/releases/latest) [![Windows](https://img.shields.io/badge/Windows-0067b8.svg?logo=data:image/svg%2bxml;base64,PD94bWwgdmVyc2lvbj0iMS4wIiBlbmNvZGluZz0idXRmLTgiPz4KPHN2ZyBmaWxsPSIjZmZmIiB2aWV3Qm94PSIwIDAgMzIgMzIiIHZlcnNpb249IjEuMSIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj4KPHBhdGggZD0iTTE2Ljc0MiAxNi43NDJ2MTQuMjUzaDE0LjI1M3YtMTQuMjUzek0xLjAwNCAxNi43NDJ2MTQuMjUzaDE0LjI1NnYtMTQuMjUzek0xNi43NDIgMS4wMDR2MTQuMjU2aDE0LjI1M3YtMTQuMjU2ek0xLjAwNCAxLjAwNHYxNC4yNTZoMTQuMjU2di0xNC4yNTZ6Ij48L3BhdGg+Cjwvc3ZnPg==)](https://github.com/Kiln-AI/Kiln/releases/latest) [![Linux](https://img.shields.io/badge/Linux-444444?logo=linux\u0026logoColor=ffffff)](https://github.com/Kiln-AI/Kiln/releases/latest) ![Github Downsloads](https://img.shields.io/github/downloads/kiln-ai/kiln/total) |\n| Connect | [![Discord](https://img.shields.io/badge/Discord-Kiln_AI-blue?logo=Discord\u0026logoColor=white)](https://discord.gg/Q5QwFeGTDh) [![Newsletter](https://img.shields.io/badge/Newsletter-kilnai-blue?logo=Substack\u0026logoColor=white)](https://kilnai.substack.com) |\n\n[\u003cimg width=\"220\" alt=\"Download button\" src=\"https://github.com/user-attachments/assets/a5d51b8b-b30a-4a16-a902-ab6ef1d58dc0\"\u003e](https://github.com/Kiln-AI/Kiln/releases/latest) [\u003cimg width=\"220\" alt=\"Quick start button\" src=\"https://github.com/user-attachments/assets/aff1b35f-72c0-4286-9b28-40a415558359\"\u003e](https://docs.getkiln.ai/getting-started/quickstart)\n\n## Key Features\n\n- ๐Ÿš€ **Intuitive Desktop Apps**: One-click apps for Windows, MacOS, and Linux. Truly intuitive design.\n- ๐ŸŽ›๏ธ **Fine Tuning**: Zero-code fine-tuning for Llama, GPT-4o, and more. Automatic serverless deployment of models.\n- ๐Ÿ“Š **Evals:** Evaluate the quality of your models/tasks using state of the art evaluators.\n- ๐Ÿค– **Synthetic Data Generation**: Generate training data with our interactive visual tooling.\n- ๐Ÿง  **Reasoning Models**: Train or distill your own custom reasoning models.\n- ๐Ÿค **Team Collaboration**: Git-based version control for your AI datasets. Intuitive UI makes it easy to collaborate with QA, PM, and subject matter experts on structured data (examples, prompts, ratings, feedback, issues, etc.).\n- ๐Ÿ“ **Prompt Generation**: Automatically generate prompts from your data, including chain-of-thought, few-shot, and multi-shot, and more.\n- ๐ŸŒ **Wide Model and Provider Support**: Use any model via Ollama, OpenAI, OpenRouter, Fireworks, Groq, AWS, or any OpenAI compatible API.\n- ๐Ÿง‘โ€๐Ÿ’ป **Open-Source Library and API**: Our Python library and OpenAPI REST API are MIT open source.\n- ๐Ÿ”’ **Privacy-First**: We can't see your data. Bring your own API keys or run locally with Ollama.\n- ๐Ÿ—ƒ๏ธ **Structured Data**: Build AI tasks that speak JSON.\n- ๐Ÿ’ฐ **Free**: Our apps are free, and our library is open-source.\n\n## Download Kiln Desktop Apps\n\nThe Kiln desktop app is completely free. Available on MacOS, Windows and Linux.\n\n[\u003cimg width=\"220\" alt=\"Download button\" src=\"https://github.com/user-attachments/assets/a5d51b8b-b30a-4a16-a902-ab6ef1d58dc0\"\u003e](https://github.com/Kiln-AI/Kiln/releases/latest)\n\n## Demo\n\n[\u003cimg width=\"220\" alt=\"Download button\" src=\"https://github.com/user-attachments/assets/e5268dd9-8813-45fe-b091-0d9f4c1907f9\"\u003e](https://getkiln.ai#demo)\n\n\u003ckbd\u003e\n\u003ca href=\"https://getkiln.ai#demo\"\u003e\n\u003cimg alt=\"Kiln Preview\" src=\"guides/kiln_preview.gif\"\u003e\n\u003c/a\u003e\n\u003c/kbd\u003e\n\n## Docs \u0026 Guides\n\nKiln is quite intuitive, so we suggest launching the desktop app and diving in. However if you have any questions or want to learn more, our [docs are here to help](https://docs.getkiln.ai).\n\n### Video Guides\n\n- [Fine Tuning LLM Models](https://docs.getkiln.ai/docs/fine-tuning-guide)\n- [Guide: Train a Reasoning Model](https://docs.getkiln.ai/docs/guide-train-a-reasoning-model)\n- [LLM Evaluators](https://docs.getkiln.ai/docs/evaluators)\n\n### All Docs\n\n- [Quick Start](https://docs.getkiln.ai/getting-started/quickstart)\n- [How to use any AI model or provider in Kiln](https://docs.getkiln.ai/docs/models-and-ai-providers)\n- [Reasoning \u0026 Chain of Thought](https://docs.getkiln.ai/docs/reasoning-and-chain-of-thought)\n- [Synthetic Data Generation](https://docs.getkiln.ai/docs/synthetic-data-generation)\n- [Collaborating with Kiln](https://docs.getkiln.ai/docs/collaboration)\n- [Rating and Labeling Data](https://docs.getkiln.ai/docs/reviewing-and-rating)\n- [Prompt Styles](https://docs.getkiln.ai/docs/prompts)\n- [Structure Data / JSON](https://docs.getkiln.ai/docs/structured-data-json)\n- [Organizing Kiln Datasets (Tags and Filters)](https://docs.getkiln.ai/docs/organizing-datasets)\n- [Our Data Model](https://docs.getkiln.ai/docs/kiln-datamodel)\n- [Repairing Responses](https://docs.getkiln.ai/docs/repairing-responses)\n- [Keyboard Shortcuts](https://docs.getkiln.ai/docs/keyboard-shortcuts)\n- [Privacy Overview: Private by Design](https://docs.getkiln.ai/docs/privacy)\n\nFor developers, see our [Kiln Python Library Docs](https://kiln-ai.github.io/Kiln/kiln_core_docs/kiln_ai.html). These include how to load datasets into Kiln, or using Kiln datasets in your own code-base/notebooks.\n\n## Install Python Library\n\n[![PyPI - Version](https://img.shields.io/pypi/v/kiln-ai.svg?logo=pypi\u0026label=PyPI\u0026logoColor=gold)](https://pypi.org/project/kiln-ai/) [![Docs](https://img.shields.io/badge/docs-pdoc-blue)](https://kiln-ai.github.io/Kiln/kiln_core_docs/index.html)\n\nOur open-source [python library](https://pypi.org/project/kiln-ai/) allows you to integrate Kiln datasets into your own workflows, build fine tunes, use Kiln in Notebooks, build custom tools, and much more! [Read the docs](https://kiln-ai.github.io/Kiln/kiln_core_docs/index.html) for examples.\n\n```bash\npip install kiln-ai\n```\n\n## Learn More\n\n### Rapid Prototyping\n\nThere are new models and techniques emerging all the time. Kiln makes it easy to try a variety of approaches and compare them in a few clicks without writing code. These can result in higher quality and improved performance.\n\nWe currently support:\n\n- Various prompting techniques: basic, few-shot, multi-shot, repair \u0026 feedback\n- Chain of thought / thinking, with optional custom โ€œthinkingโ€ instructions\n- Many models: GPT, Llama, Claude, Gemini, Mistral, Gemma, Phi\n- Fine Tuning: create custom models using your Kiln dataset\n\nIn the future, we plan to add more powerful no-code options like evals, and RAG. For experienced data-scientists, you can create these techniques today using Kiln datasets and our python library.\n\n### Collaborate Across Technical and Non-Technical Teams\n\nWhen building AI products, thereโ€™s usually a subject matter expert who knows the problem you are trying to solve, and a different technical team assigned to build the model. Kiln bridges that gap as a collaboration tool.\n\nSubject matter experts can use our intuitive desktop apps to generate structured datasets and ratings, without coding or using technical tools. No command line or GPU required.\n\nData-scientists can consume the dataset created by subject matter experts, using the UI, or deep dive with our python library.\n\nQA and PM can easily identify issues sooner and help generate the dataset content needed to fix the issue at the model layer.\n\nThe dataset file format is designed to be be used with Git for powerful collaboration and attribution. Many people can contribute in parallel; collisions are avoided using UUIDs, and attribution is captured inside the dataset files. You can even share a dataset on a shared drive, letting completely non-technical team members contribute data and evals without knowing Git.\n\n### Build High Quality AI Products with Datasets\n\nProducts donโ€™t naturally have โ€œdatasetsโ€, but Kiln helps you create one. Every time you use Kiln, we capture the inputs, outputs, human ratings, feedback, and repairs needed to build high quality models for use in your product. The more you use it, the more data you have.\n\nYour model quality improves automatically as the dataset grows, by giving the models more examples of quality content (and mistakes).\n\nIf your product goals shift or new bugs are found (as is almost always the case), you can easily iterate the dataset to address issues.\n\n## Contributing \u0026 Development\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for information on how to setup a development environment and contribute to Kiln.\n\n## Citation\n\n```bibtex\n@software{kiln_ai,\n title = {Kiln: Rapid AI Prototyping and Dataset Collaboration Tool},\n author = {{Chesterfield Laboratories Inc.}},\n year = {2025},\n url = {https://github.com/Kiln-AI/Kiln},\n version = {latest}\n}\n```\n\n## Licenses \u0026 Trademarks\n\n- Python Library: [MIT License](libs/core/LICENSE.txt)\n- Python REST Server/API: [MIT License](libs/server/LICENSE.txt)\n- Desktop App: free to download and use under our [EULA](app/EULA.md), and [source-available](/app). [License](app/LICENSE.txt)\n- The Kiln names and logos are trademarks of Chesterfield Laboratories Inc.\n\nCopyright 2024 - Chesterfield Laboratories Inc.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkiln-ai%2Fkiln","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkiln-ai%2Fkiln","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkiln-ai%2Fkiln/lists"}