[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72129":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":25,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":47,"readmeContent":48,"aiSummary":49,"trendingCount":16,"starSnapshotCount":16,"syncStatus":50,"lastSyncTime":51,"discoverSource":52},72129,"Kiln","Kiln-AI\u002FKiln","Kiln-AI","Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.","https:\u002F\u002Fkiln.tech",null,"Python",4875,372,35,22,0,7,19,66,21,89.82,"Other",false,"main",true,[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"ai","chain-of-thought","collaboration","dataset-generation","evals","evaluation","evaluation-framework","fine-tuning","machine-learning","macos","mcp","ml","ollama","openai","prompt","prompt-engineering","python","rlhf","synthetic-data","windows","2026-06-12 04:01:03","\u003Cp align=\"center\">\n    \u003Ca href=\"https:\u002F\u002Fkiln.tech\">\n        \u003Cpicture>\n            \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Ffaae475e-7ace-443b-91f3-0e3701f0c90d\">\n            \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F4ca9b69f-1c90-43a4-8d2e-13de4eb2ee9c\">\n            \u003Cimg width=\"205\" alt=\"Kiln AI Logo\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F4ca9b69f-1c90-43a4-8d2e-13de4eb2ee9c\">\n        \u003C\u002Fpicture>\n    \u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Ch3 align=\"center\">\n  A free app and open-source library to build better AI products.\n\u003C\u002Fh3>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fkiln.tech#demo\">\n    \u003Cimg width=\"420\" alt=\"Kiln AI Animated Preview\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F56ac04ea-010b-40bf-851c-ec5e05965336\">\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fkiln.tech\u002Fdownload\">\u003Cimg width=\"180\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fa5d51b8b-b30a-4a16-a902-ab6ef1d58dc0\" alt=\"Download Kiln\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fdocs.kiln.tech\">\u003Cimg width=\"180\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Faff1b35f-72c0-4286-9b28-40a415558359\" alt=\"Read the Docs\">\u003C\u002Fa>\n\u003C\u002Fp>\n\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"#highlights\">\u003Cstrong>Highlights\u003C\u002Fstrong>\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fevaluations\">\u003Cstrong>Evals\u003C\u002Fstrong>\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fprompts\u002Fautomatic-prompt-optimizer\">\u003Cstrong>Auto-Optimize\u003C\u002Fstrong>\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fdocuments-and-search-rag\">\u003Cstrong>RAG\u003C\u002Fstrong>\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fagents\">\u003Cstrong>Agents\u003C\u002Fstrong>\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Ffine-tuning-guide\">\u003Cstrong>Fine-Tuning\u003C\u002Fstrong>\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fsynthetic-data-generation\">\u003Cstrong>Synthetic Data\u003C\u002Fstrong>\u003C\u002Fa> •\n  \u003Ca href=\"https:\u002F\u002Fdocs.kiln.tech\">\u003Cstrong>All Docs\u003C\u002Fstrong>\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FKiln-AI\u002Fkiln\u002Factions\u002Fworkflows\u002Fbuild_and_test.yml\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FKiln-AI\u002Fkiln\u002Factions\u002Fworkflows\u002Fbuild_and_test.yml\u002Fbadge.svg\" alt=\"Build and Test\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fpypi.org\u002Fproject\u002Fkiln-ai\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Fkiln-ai.svg?logo=pypi&label=PyPI&logoColor=gold\" alt=\"PyPI\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fkiln.tech\u002Fdiscord\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Kiln_AI-blue?logo=Discord&logoColor=white\" alt=\"Discord\">\u003C\u002Fa>\n\u003C\u002Fp>\n\n## What is Kiln?\n\nKiln is a workbench for the full AI development loop: evals, optimization, prompts, RAG, fine-tuning, synthetic data, agents, and tools - all working together. The desktop app lets your whole team contribute (PMs, subject-experts, and QA can rate outputs and add data without writing code). The MIT-licensed Python library ships the same tasks to production. Runs locally - bring your own API keys, or go fully offline with Ollama.\n\n## Highlights\n\n### Iterate, optimize, and collaborate\n\n- 🖥️ [**Intuitive app**](https:\u002F\u002Fkiln.tech\u002Fdownload) - Easy-to-use apps for Mac, Windows, and Linux. One-click install.\n- 📊 [**Eval Builder**](https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fevaluations) - Auto-generate evals (judge + synthetic eval dataset), and align to your preference in ~10 minutes.\n- 🚀 [**Auto-Optimize**](https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fprompts\u002Fautomatic-prompt-optimizer) - Automatically find the best way to run your AI task, optimizing prompt, model selection, tools, skills, subagents, parameters, and more.\n- 💬 [**AI Assistant**](https:\u002F\u002Fdocs.kiln.tech) - Your AI data-science partner. Kiln Assistant proposes improvements, optimizes prompts, runs experiments, creates evals, and more.\n- 🤝 [**Git-native collaboration**](https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fcollaboration) - The app syncs to Git automatically — even for teammates who don't know what Git is.\n\n### Build & ship agents\n\n- 🔍 [**RAG**](https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fdocuments-and-search-rag) - Drag-and-drop docs (PDF, image, video, audio) to create a RAG. Auto-generated RAG evals from your own documents.\n- 🤖 [**Subagents**](https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fagents) - Compose multi-agent hierarchies. Each runs in its own focused context window.\n- 🪄 [**Synthetic Data Generation**](https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fsynthetic-data-generation) - Generate data for evals or fine-tuning in minutes.\n- 🎛️ [**Fine-Tuning**](https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Ffine-tuning-guide) - Zero-code fine-tuning across 60+ models (Qwen, Llama, GPT, Gemini, …) on Fireworks, Together, OpenAI, and Vertex. Serverless deployment included.\n- 🐍 [**Open Python library**](https:\u002F\u002Fdocs.kiln.tech\u002Fdevelopers\u002Fpython-library-quickstart) - Agents built in the app can be deployed to production. MIT open-source.\n- 🧰 [**…and more**](https:\u002F\u002Fdocs.kiln.tech) - Tools & MCP, Skills, structured outputs, reasoning models, model library (190+ tested).\n\n## App Quickstart\n\nGet started in minutes - one-click install.\n\nDownload Kiln Desktop for macOS, Windows, or Linux, then follow the [5-minute quickstart](https:\u002F\u002Fdocs.kiln.tech\u002Fgetting-started\u002Fquickstart) to run your first task.\n\n[![MacOS](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FMacOS-black?logo=apple)](https:\u002F\u002Fkiln.tech\u002Fdownload) [![Windows](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FWindows-0067b8.svg?logo=data:image\u002Fsvg%2bxml;base64,PD94bWwgdmVyc2lvbj0iMS4wIiBlbmNvZGluZz0idXRmLTgiPz4KPHN2ZyBmaWxsPSIjZmZmIiB2aWV3Qm94PSIwIDAgMzIgMzIiIHZlcnNpb249IjEuMSIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj4KPHBhdGggZD0iTTE2Ljc0MiAxNi43NDJ2MTQuMjUzaDE0LjI1M3YtMTQuMjUzek0xLjAwNCAxNi43NDJ2MTQuMjUzaDE0LjI1NnYtMTQuMjUzek0xNi43NDIgMS4wMDR2MTQuMjU2aDE0LjI1M3YtMTQuMjU2ek0xLjAwNCAxLjAwNHYxNC4yNTZoMTQuMjU2di0xNC4yNTZ6Ij48L3BhdGg+Cjwvc3ZnPg==)](https:\u002F\u002Fkiln.tech\u002Fdownload) [![Linux](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLinux-444444?logo=linux&logoColor=ffffff)](https:\u002F\u002Fkiln.tech\u002Fdownload)\n\nPrefer to start in code? See the [Python library quickstart](https:\u002F\u002Fdocs.kiln.tech\u002Fdevelopers\u002Fpython-library-quickstart).\n\n## Demo\n\n[Watch a 2-minute overview](https:\u002F\u002Fkiln.tech#demo), or our [end-to-end project demo (20 minutes)](https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fend-to-end-project-demo).\n\n## Why Kiln?\n\nMost AI tooling forces a tradeoff: a code-only framework that covers one slice (orchestration *or* evals *or* RAG), or a paid SaaS that locks in your data and can't be extended. Kiln is a free, local-first workbench where a single task and dataset flow through evals, prompt optimization, fine-tuning, RAG, agents, and synthetic data — all in one tool.\n\n- **One dataset, every technique.** Define a task once. Eval it, optimize the prompt, fine-tune a model, generate synthetic data, add RAG — all against the same dataset, with results that compound across stages.\n\n- **Track every axis. Move fast. Don't regress.** Keeping agents running well is hard — a prompt change quietly regresses behavior three steps downstream; a model upgrade improves five things and breaks two. Kiln tracks quality across every dimension you care about, so you iterate without breaking what already works.\n\n  \u003Cp align=\"center\">\n    \u003Cimg width=\"600\" alt=\"Kiln optimization across iterations\" src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F5517b33b-74dd-444a-9f40-6a9c6d8a1ffc\">\n  \u003C\u002Fp>\n\n- **Optimization, not just evaluation.** Other tools tell you how a prompt scores, but not how to fix it. Kiln's Auto-Optimize searches across hundreds of prompt mutations and models to find what works best for every eval dimension.\n\n- **GUI for the whole team, library for engineers.** Kiln's desktop app lets PMs rate outputs, SMEs add training examples, and QA flag regressions — without a terminal. Engineers ship the same tasks via an MIT-licensed Python library. Data scientists can use the library in notebooks and experiments.\n\n- **Local-first.** Most AI platforms are SaaS-only. Kiln runs entirely on your machine. Bring your own API keys, or go fully offline with Ollama. Your data never leaves your control. Team-sync is provided via Git infrastructure you already own.\n\n- **190+ models tested across every provider.** Skip the guesswork — we've tested every model's capabilities across all major providers. OpenAI, Anthropic, Gemini, Bedrock, Ollama, OpenRouter, Fireworks, Groq, any OpenAI-compatible endpoint, and more. Swap models with confidence.\n\n## Open-source Python Library\n\nBuild AI tasks in the app. Deploy with the open-source library. Same engine, same project files, no rewrite. The MIT-licensed `kiln-ai` library is the same library used in the app. Load Kiln projects, run tasks, build fine-tunes, work in notebooks, integrate Pandas\u002FPolars dataframes, and more.\n\n```bash\npip install kiln-ai\n```\n\n[📚 Library docs](https:\u002F\u002Fdocs.kiln.tech\u002Fdevelopers\u002Fpython-library-quickstart) · [REST API](https:\u002F\u002Fdocs.kiln.tech\u002Fdevelopers\u002Frest-api) · [PyPI](https:\u002F\u002Fpypi.org\u002Fproject\u002Fkiln-ai\u002F)\n\n## Docs\n\nFull docs at [docs.kiln.tech](https:\u002F\u002Fdocs.kiln.tech). Common starting points:\n\n- [Quickstart](https:\u002F\u002Fdocs.kiln.tech\u002Fgetting-started\u002Fquickstart) — run your first task in 5 minutes\n- [Evals](https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fevaluations)\n- [Auto-Optimize](https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fprompts\u002Fautomatic-prompt-optimizer)\n- [RAG](https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fdocuments-and-search-rag)\n- [Agents](https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fagents)\n- [Fine-Tuning](https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Ffine-tuning-guide)\n- [Python Library](https:\u002F\u002Fdocs.kiln.tech\u002Fdevelopers\u002Fpython-library-quickstart)\n- [End-to-end project demo](https:\u002F\u002Fdocs.kiln.tech\u002Fdocs\u002Fend-to-end-project-demo) (20-min video)\n\n## Community\n\n- Chat with the community on [Discord](https:\u002F\u002Fkiln.tech\u002Fdiscord).\n- Subscribe to the [newsletter](https:\u002F\u002Fkiln.tech\u002Fblog) for new features.\n- File issues, request features, or open a discussion on [GitHub](https:\u002F\u002Fgithub.com\u002FKiln-AI\u002FKiln\u002Fissues).\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for development setup and contribution guidelines.\n\n## License & Trademarks\n\nKiln's core Python library and REST server are [MIT-licensed](libs\u002Fcore\u002FLICENSE.txt). The desktop app is [source-available](app), free to use, and built on the [fair-code](https:\u002F\u002Ffaircode.io) model — so Kiln stays free for individuals while remaining sustainable.\n\nDatasets are open JSON. You own and control your datasets.\n\n[Kiln Pro](https:\u002F\u002Fkiln.tech\u002Fpricing) is our service that adds the AI Assistant, Auto-Optimize, and the Eval Builder. It's opt-in, and the core Kiln app remains fully functional without it.\n\nThe Kiln name and logos are trademarks of Chesterfield Laboratories Inc.\n\nCopyright 2024 — Chesterfield Laboratories Inc.\n\n","Kiln是一个用于构建、评估和优化AI系统的平台，集成了评价、RAG、代理、微调、合成数据生成、数据集管理和更多功能。其核心功能包括自动优化提示、RAG（检索增强生成）、细粒度调整及合成数据生成等，支持链式思维和强化学习的人工智能开发。技术上，Kiln采用Python语言编写，并提供了一个直观的桌面应用程序与开源库，允许非技术人员如产品经理、领域专家参与AI产品的测试与改进过程。该工具非常适合需要快速迭代并优化AI模型的企业或研究团队使用，在保证数据安全的同时提高了跨部门协作效率。",2,"2026-06-11 03:40:29","high_star"]