AI for AI · A Liquid AI product · Private beta

From zero to a fine-tuned LFM
in under an hour.

An AI platform for building better AIs, faster. Liquid Harness is an autonomous agent that takes a plain-English description of your task and ships a deployable model. It writes the data pipeline, scores and filters samples, runs baselines, fine-tunes, and iterates — no ML experience required.

Request beta access How it works

Get started

$ curl -LsSf https://astral.sh/uv/install.sh | sh  # install uv (one-time)
$ uv tool install lqh
$ lqh

Then hands-off, once the agent has written your spec

$ lqh --auto ./my-task
[stage: rubric]           writing scorer from spec
[stage: data_gen_draft]   5 samples generated, all valid
[stage: filter_validation] 1,427 / 2,000 kept
[stage: sft_initial]      score 6.8/10  (baseline 4.1)
[stage: dpo]              iter 3/5, score 7.4/10
[final: success]           DPO checkpoint beats baseline by +3.3

Fine-tuning is one step. lqh does the other eight.

One command runs the full pipeline. Each stage is a real component you can inspect, stop at, or hand off.

spec
rubric
data gen
filter
baseline
SFT
DPO
eval
checkpoint

Specify in plain English

The agent interviews you about the task and writes a SPEC.md that drives every downstream stage. No DSL, no boilerplate, no ML jargon.

Synthetic data, scored & filtered

lqh authors a per-task data pipeline, generates samples concurrently, and scores each one with an LLM judge against your rubric. The dataset that hits training is already curated.

Hands-off with `--auto`

Point lqh at a directory and walk away. It either delivers a checkpoint that beats baseline or returns an explicit failure with the reason — never a hang, never a prompt.

Watch lqh ship a model in one run.

A short walkthrough — spec to deployable checkpoint, end to end.

Built on Liquid Foundation Models

The first-party way to customize an LFM.

Liquid Harness is built and maintained by Liquid AI as the official tool for adapting Liquid Foundation Models — small, capable models that run anywhere — to your specific task. Default base model: LFM2-1.2B-Instruct.

Pricing

Simple per-seat plans, credits included.

Each seat includes monthly credits that cover everything — data generation, scoring, training, and inference. Pay only for usage beyond your included credits.

Private beta · invite-only for now

Individual

$39 / month

$39 of included credits / month

Single user
Up to 5 GPUs concurrent
Standard scoring & data-gen rates
Up to $5,000 / mo usage beyond credits

Professional

Enterprise

Custom

Committed or negotiated credits

Unlimited members
Custom GPU concurrency & rate limits
Audit log
Dedicated hardware on request
Custom usage caps

Prices in USD and shown with platform margin included — what you see is what you're billed. Enterprise is sales-led; everything else is self-serve at general availability.

Customize your first model in an afternoon.

Liquid Harness is in private beta. Drop your email and we'll send an install link.

From zero to a fine-tuned LFM in under an hour.