ashr · the agent

Your 100x AI Engineer.

You give it the job in plain words, and it handles the data, fine-tuning, RL, evals, quantization and serving. It runs in your terminal on your machine. It runs jobs on your GPUs, and its model calls run on Ashr credits: 2,000 free to start, no API key needed.

Install

ashr is in early access. We email you a private install link, then it's three commands in Terminal.

Email me an install link
Terminal
# install (the link from your email) $ curl -fsSL https://ashr.io/i/<your-link> | sh # in your repo: start ashr (the first run signs you in), then type /init $ cd ~/code/your-repo $ ashr

Example tasks

Write the job the way you'd brief an ML engineer: the data, the target and the constraints. Any modality. ashr runs independent pieces in parallel with subagents.

Language: replace an API model with your own

~/acme-support
> We send about 40k support conversations a day to GPT-6 Astra. The logs are in s3://acme-logs/support/. Distill them into Qwen3.8-27B until it matches Astra on evals/support/, serve it on our H100s behind an OpenAI-compatible endpoint, and give me cost per 1k conversations against the API.
$aws s3 ls s3://acme-logs/support/ --recursive --summarize
1,214 files, 38.2 GB, 6.1M conversations
evalGPT-6 Astra on evals/support/: 0.874 baseline
datasubagent dedupe, drop PII, keep resolved threads
servesubagent vLLM for Qwen3.8-27B on h100-1..4
working

Agents: train on your agent's own traces

~/coding-agent
> Our coding agent's sessions are in traces/ with pass/fail labels. Run SFT and then GRPO on Qwen3.8-27B to raise the pass rate on the 300 held-out tasks in evals/heldout/. Stop any run that will cost more than $2k.
$wc -l traces/*.jsonl
18,402 sessions, 61% pass
evalbase Qwen3.8-27B on evals/heldout/: 112 of 300
sftsubagent passing sessions only, 2 epochs, cap $600
planGRPO on the SFT checkpoint, cap $2,000 per run
working

Robotics: fine-tune a manipulation policy

~/ur5-picking
> Fine-tune our VLA policy on the 600 teleop demos in data/teleop/ (LeRobot format) for bin picking on the UR5. Beat the current 62% success rate in the sim eval in sim/bin_pick/, then export it to run at 30 Hz on the Jetson Orin.
$python -m lerobot.scripts.info data/teleop
600 episodes, 30 fps, wrist + overhead cameras
evalcurrent policy in sim/bin_pick/: 62.0% over 200 trials
trainsubagent fine-tune from checkpoint, action chunks of 50
exportsubagent TensorRT build for Jetson Orin, target 30 Hz
working

Biology: predict binding from assay data

~/binding
> Fine-tune ESM-2 650M on the 40k binding measurements in data/binding.csv. Split by sequence cluster so nothing leaks, beat the Spearman of our XGBoost baseline, then rank the 2M candidates in library.fasta and send me the top 500.
$python -c "import pandas as pd; print(pd.read_csv('data/binding.csv').shape)"
(40118, 4) sequence, target, kd_nm, assay_date
splitMMseqs2 clusters at 30% identity, 80/10/10
evalXGBoost baseline on held-out clusters: Spearman 0.41
trainsubagent ESM-2 650M with a regression head, LoRA
working

Speech: cut errors on your own vocabulary

~/call-asr
> Fine-tune Whisper large-v3 on the 800 hours of labeled call audio in s3://acme-calls/. Cut the word error rate on drug names and account numbers in half on evals/asr/ without making general WER worse.
$aws s3 ls s3://acme-calls/ --recursive --summarize
312,480 segments, 800.4 hours
evallarge-v3 on evals/asr/: WER 9.8%, entity WER 31.5%
datasubagent mine segments with drug names and account numbers
trainsubagent 3 learning rates in parallel, one per GPU
working

Vision: extract fields from documents

~/invoices
> Fine-tune Qwen3.5-VL-8B to extract line items from the scanned invoices in data/invoices/ (labels in labels.jsonl). Reach 98% field accuracy on the held-out split, and it has to run on one L4.
$ls data/invoices | wc -l && wc -l labels.jsonl
12,480 scans, 12,480 labels
evalzero-shot Qwen3.5-VL-8B: 81.3% field accuracy
checkL4 has 24 GB: plan for int8 weights at serve time
trainsubagent LoRA at 1,024px, hold out 10% by vendor
working

Serving: cut latency and cost

~/inference
> Our 70B endpoint has a p95 latency of 2.1s. Get p95 under 800ms on the same hardware, losing less than 1 point on evals/prod-sample/. Try FP8, a speculative-decoding draft model and vLLM tuning, and tell me what each one gets us.
loadreplay 2,000 prod requests: p95 2.14s
evalcurrent model on evals/prod-sample/: 0.712
fp8subagent quantize weights and KV cache, re-score
draftsubagent train a 1B draft model on prod traffic
vllmsubagent sweep batch size and chunked prefill
working

Training infra: fix a slow run

~/llm-8b
> Our 8B run on gpu-box is stuck at 41% MFU. Get it past 55% without changing the loss curve, then watch it overnight and roll back to the last checkpoint if the loss spikes.
profilessh gpu-box nsys profile torchrun train.py --steps 1
38% of step time in NCCL all-gather, attention unfused
fsdpsubagent overlap all-gather with backward
flashsubagent swap in FlashAttention 3, bf16
compilesubagent torch.compile the decoder block
working

Results

0.626
vs 0.433 for Claude Code, same model

Post-training on Frontier ML

Qwen3-4B-Base into a chat model for math, science and code. 12 hours, $50 of GPU.*

* Frontier ML, 12 hours and $50 of GPU per task, both agents on Claude Opus 5.5. Single runs graded with Frontier ML's verifier, not submitted to Frontier ML.

Book a call

30 minutes. Bring a training task and we'll scope it with you. Or email founders@ashr.io.

Pick a time

Get ashr

Enter your work email and we'll get in touch to help you set it up.

By continuing you agree to our Terms and Privacy Policy.