Skip to content
SPECIFICTION
Get listed

Kiln

kiln.tech

Free plan WindowsmacOSLinuxAPISelf-hosted
Visit kiln.tech
Spec score 7.8 #13 of 27 in AI Data Analysis Tools

What it is

Kiln is an AI workbench for teams building and improving AI systems, with evaluation, fine-tuning, and optimization tools. Users can describe an evaluation goal and generate prompts and synthetic datasets, then compare judge results with human ratings. Kiln supports composing agents and subagents, inspecting tool calls, and evaluating each level of an agent hierarchy. It supports MCP servers and providers including AWS Bedrock, Azure OpenAI, Vertex AI, OpenAI, Anthropic, Fireworks, Gemini, Ollama, and OpenAI-compatible endpoints. Datasets, traces, and evaluations sync to Git. Prompts, outputs, ratings, and fine-tuning jobs are stored as JSON files on the user's filesystem, while provider API calls go directly from the user's machine to the chosen provider. Kiln says it can run fully offline with Ollama, vLLM, Llama.cpp, or another compatible local server. The free Individual plan includes a Python library, source-available desktop app, Git-synced local datasets, rate-limited standard models, and community support.

Spec sheet

Product
Kiln describes itself as an AI workbench for teams to build and optimize AI systems, including evals, fine-tuning, and optimization.Read 7 Oct 2026 · kiln.tech
Intended users
Kiln describes its audience as engineers, data scientists, product managers, QA, and subject matter experts working on AI systems.Read 7 Oct 2026 · kiln.tech
Integrations
Kiln supports MCP servers and lists providers including AWS Bedrock, Azure OpenAI, Vertex AI, OpenAI, Anthropic, Fireworks, Gemini, Ollama, and OpenAI-compatible endpoints.Read 7 Oct 2026 · kiln.tech
Security
Kiln says its Python library is MIT-licensed and its source-available desktop app has public CI builds and checksums for every release.Read 7 Oct 2026 · kiln.tech
Support
The Individual plan includes community support, Team includes email support, and Enterprise includes SLA and priority support.Read 7 Oct 2026 · kiln.tech
Company
The website footer identifies Kiln AI as Chesterfield Laboratories Inc.Read 7 Oct 2026 · kiln.tech
Agents
Kiln supports composing agents and subagents, inspecting tool calls, and evaluating each level of an agent hierarchy.Read 7 Oct 2026 · kiln.tech
Collaboration
Kiln automatically syncs datasets, traces, and evals to Git, and its enterprise page names GitHub Enterprise, GitLab, Bitbucket, and Azure DevOps.Read 7 Oct 2026 · kiln.tech
Enterprise controls
Enterprise services can include SSO, VPC deployment, and telemetry controls.Read 7 Oct 2026 · kiln.tech
Evaluation
Kiln can generate evaluation prompts and synthetic datasets from a description of the goal, then benchmark judges against human ratings.Read 7 Oct 2026 · kiln.tech
Local data
Kiln stores prompts, outputs, ratings, and fine-tuning jobs as JSON files on the user's filesystem, while provider API calls go directly from the user's machine to the chosen provider.Read 7 Oct 2026 · kiln.tech
Offline use
Kiln says it can run fully offline with Ollama, vLLM, Llama.cpp, or another OpenAI-compatible local server.Read 7 Oct 2026 · kiln.tech
Telemetry
The desktop app collects UI analytics through PostHog, while the Python library sends no analytics; the company says telemetry can be disabled for enterprise contracts.Read 7 Oct 2026 · kiln.tech

Plans and prices

Individual Free Open Source Python Library · Desktop App (source-available) · Local datasets with git sync · Kiln Pro standard models, rate limited · Community support Read 7 Oct 2026 · kiln.tech
Enterprise Priced on request Custom Everything in Team · SSO / SAML · Annual contracts & procurement support · SLA & priority support · Dedicated solutions engineer · Custom onboarding & training Read 7 Oct 2026 · kiln.tech
Team Priced on request Request access Everything in Individual · Kiln Pro enhanced models, higher limits · Automatic agent optimization · Priority access to new features · Email support Read 7 Oct 2026 · kiln.tech

Every Kiln plan and price →

Strong points and limits

Strong points

  • Generates evaluation prompts and synthetic datasets.
  • Supports agents, subagents, and hierarchy-level evaluation.
  • Can run offline with listed local servers.
  • Free Individual plan includes desktop app and Python library.
  • Stores work as JSON files on the user's filesystem.

Limits

  • Desktop app collects UI analytics through PostHog.

Who it suits

Kiln is for engineers, data scientists, product managers, QA specialists, and subject matter experts working on AI systems. It may suit teams that want local files, Git sync, or offline operation.

Verdict

Kiln offers a broad development workflow for evaluating and refining AI systems, including local and offline options. Teams should weigh the undisclosed paid-plan prices and note the desktop app's analytics collection.

Where Specifiction places it

Alternatives to KilnAll alternatives →