# Kiln-AI/Kiln

Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.

Repository: https://github.com/Kiln-AI/Kiln
Canonical: https://ross.abutalabs.com/products/kiln
Homepage: https://kiln.tech
Language: Python
License: NOASSERTION
License Family: other
Topics: ai, chain-of-thought, collaboration, dataset-generation, fine-tuning, machine-learning, macos, ml, ollama, openai, prompt, prompt-engineering, python, rlhf, synthetic-data, windows, evals, evaluation, evaluation-framework, mcp
Last push: 2026-08-26T19:20:36+00:00

## Health v2 (maintenance only)
Score: 90/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 98, longevity 55
- inputs: {"age_days": 771, "days_push": 7, "days_rel": 13, "gap_med": 19, "n_releases_24m": 34}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5034, forks 375 (observed 2026-08-28T04:09:08.693019+00:00)

## What it is
Kiln is a free desktop app and MIT-licensed Python library for the full AI development loop: evals, prompt optimization, RAG, agents, fine-tuning, synthetic data generation, and MCP tooling. It emphasizes team collaboration with git-based dataset versioning and lets non-engineers rate outputs and contribute data without code.

## Use cases
- evaluate llm output quality with llm-as-judge evals
- build a rag pipeline over my pdf documents
- auto-optimize prompts against evals
- fine-tune a smaller model from gpt-4o outputs
- generate synthetic training data for fine-tuning
- build multi-agent systems with subagents and mcp tools
- collaborate with PMs and QA on rating ai outputs
- run ai models locally offline with ollama

## When to choose
- you need an end-to-end workbench covering evals, RAG, agents, and fine-tuning in one tool
- non-technical teammates (PMs, QA, domain experts) must contribute ratings and datasets
- you want eval-driven prompt optimization or model comparison with cost/latency data
- you want local-first datasets versioned in git with no vendor lock-in

## When to avoid
- you only need a lightweight programmatic library without a desktop app
- you require a fully permissive license for the app itself (the app is source-available, only the Python library is MIT)
- you need heavy custom infrastructure-level orchestration beyond Kiln's abstractions
- you depend on Kiln Pro features but cannot use hosted services

## Facets
- artifact type: application
- maturity: active
- function: machine-learning, rag, agent-framework, prompt-engineering, llm-training, data-generation, mcp, chatbot, developer-tools
- domain: artificial-intelligence, machine-learning, large-language-models, developer-tools, data-science
- platform: windows, python, cross-platform
- tags: evals, fine-tuning, synthetic-data, llm-as-judge, prompt-optimization, dataset-management, collaboration, desktop-app, ollama, rlhf, ai-agents, retrieval-augmented-generation, macos, linux, desktop

## Member repositories
- Kiln-AI/Kiln (main) score 90

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:08.693019+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:17:26.453444+00:00, confidence not recorded.
  - readme: https://github.com/Kiln-AI/Kiln (fetched 2026-08-28T04:09:08.693019+00:00, sha 31c85e0abe6d)
  - homepage: https://kiln.tech (fetched 2026-08-29T08:58:08.792864+00:00, sha 18bef926fcc9)
  - site_page: https://docs.kiln.tech (fetched 2026-08-29T08:58:08.802177+00:00, sha 64fa3474254e)
  - site_page: https://kiln.tech/features/rag (fetched 2026-08-29T08:58:08.805681+00:00, sha 117f7a3e03cc)
  - site_page: https://kiln.tech/features/skills (fetched 2026-08-29T08:58:08.807472+00:00, sha 627874ae22c6)
  - site_page: https://kiln.tech/features/tools-mcp (fetched 2026-08-29T08:58:08.809085+00:00, sha 8b50e4f6ccb9)
  - site_page: https://kiln.tech/features/agents (fetched 2026-08-29T08:58:08.810679+00:00, sha 499f5449914f)
  - site_page: https://kiln.tech/features/evals (fetched 2026-08-29T08:58:08.812128+00:00, sha 7d86f823499c)
  - site_page: https://kiln.tech/features/auto-optimize (fetched 2026-08-29T08:58:08.814029+00:00, sha 8124226e4253)
  - site_page: https://kiln.tech/pricing (fetched 2026-08-29T08:58:08.804022+00:00, sha 789ea9281240)
- Data as of 2026-08-30T08:39:29.467469+00:00.