Kiln-AI/

Kiln

GitHub Website

Kiln is a free, local-first workbench and open-source Python library for AI development tasks including evals, RAG, agents, fine-tuning, and synthetic data generation. It runs locally with optional Ollama offlining and supports team collaboration via Git integration.

5.0kstars

377forks

79issues

2024since

Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap

open-webui/

open-webui

▲ 729/wk

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

148k21kPython

hiyouga/

LlamaFactory

▲ 162/wk

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

74k9.0kPython

unslothai/

unsloth

▲ 524/wk

Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, GLM and other models.

70k6.3kPython

run-llama/

llama_index

▲ 198/wk

LlamaIndex is the leading document agent and OCR platform

51k7.9kPython

chatchat-space/

Langchain-Chatchat

▲ 24/wk

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and Llama) RAG and Agent app with langchain

39k6.3kPythonquiet

ollama/

ollama

▲ 640/wk

Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

178k17kGo

CompareKiln vs open-webui Kiln vs LlamaFactory Kiln vs unsloth

Reviewgenerated from repository data · Aug 5, 2026

What it is

Kiln is a workbench for the full AI development loop: evals, optimization, prompts, RAG, fine-tuning, synthetic data, agents, and tools. The desktop app enables team collaboration without code, and a MIT-licensed Python library enables deployment to production. Runs locally with optional offline mode via Ollama.

How it works

Kiln provides a desktop app and an open-source Python library (kiln-ai) to perform evals, auto-prompt optimization, RAG, agent orchestration, and fine-tuning across many models. The app supports git-based collaboration, and the library can load Kiln projects, run tasks, build fine-tunes, and integrate with dataframes. The project emphasizes tracking quality across evaluation, optimization, and deployment dimensions.

Getting started

Install Kiln Desktop for macOS, Windows, or Linux via the download page.
Quickstart: follow the 5-minute quickstart in the docs to run your first task.
For code usage: install the Python library with the command shown in the README.

Command shown in README:

pip install kiln-ai

Other starting points include the Docs Quickstart and Python library quickstart links.

Recent releases

Latest releases:

v1.0.4 Kiln Desktop - v1.0.4 (2026-07-16)
v1.0.3 Kiln Desktop - v1.0.3 (2026-06-23)
v1.0.2 Kiln Desktop - v1.0 (2026-05-11)
v0.28.0 Kiln Desktop - v0.28.0 (2026-04-22)
v0.26.0 Kiln Desktop - v0.26.0 (2026-03-18)

Traction

The repository shows 5010 stars and 377 forks, with 79 open issues.

Behind the repo

Kiln is developed by Kiln-AI (Chesterfield Laboratories Inc.) and is open-source under the MIT license for the core library and a source-available desktop app. Kiln Pro offers paid features, while the core app remains functional without it.

Caveats

License: MIT for the library; desktop app is source-available. The README notes no explicit license field in the provided facts.
Age: Created 2024-07-23.
Open issues: 79.
Last push: 2026-08-04.

SharePost on X LinkedIn