# huggingface/aisheets

Build, enrich, and transform datasets using AI models with no code

Repository: https://github.com/huggingface/aisheets
Canonical: https://ross.abutalabs.com/products/aisheets
Homepage: https://huggingface.co/spaces/aisheets/sheets
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: ai, nocode, oss, synthetic-data, llms, llm-evaluation
Last push: 2026-05-26T10:33:23+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 84, release rhythm 35, longevity 42
- inputs: {"age_days": 594, "days_push": 99, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1642, forks 139 (observed 2026-08-28T04:05:15.390810+00:00)

## What it is
Hugging Face AI Sheets is an open-source no-code web application for building, enriching, and transforming datasets using AI models. It can be deployed locally via Docker or on the Hugging Face Hub, and connects to thousands of open models via Inference Providers or local inference servers.

## Use cases
- build datasets with llms without writing code
- enrich existing datasets with model-generated columns
- generate synthetic training data from prompts
- transform and clean csv-like data using ai models
- evaluate and compare llm outputs across rows
- run large-scale dataset generation jobs on hf jobs

## When to choose
- you want a spreadsheet-like no-code ui for llm-powered data generation
- you need to enrich or extend datasets with thousands of open hub models
- you want to self-host the tool locally or deploy it as a hf space

## When to avoid
- you need programmatic dataset pipelines in python rather than a gui
- you require offline operation without any model inference access
- you need heavy-duty etl orchestration beyond row-level ai transformations

## Facets
- artifact type: application
- maturity: active
- function: llm-inference, data-generation, etl, rag, prompt-engineering
- domain: data-science, machine-learning, large-language-models, artificial-intelligence, developer-tools
- platform: self-hosted, cross-platform
- tags: no-code, spreadsheet-ui, synthetic-data, dataset-enrichment, huggingface-hub, inference-providers, web-server, docker, nodejs

## Member repositories
- huggingface/aisheets (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:15.390810+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 2026-08-30T03:46:20.174445+00:00, confidence not recorded.
  - readme: https://github.com/huggingface/aisheets (fetched 2026-08-28T04:05:15.390810+00:00, sha 1e2be0efc1cd)
  - homepage: https://huggingface.co/spaces/aisheets/sheets (fetched 2026-08-29T11:19:23.059531+00:00, sha da0db118a79f)
- Data as of 2026-08-30T08:39:29.467469+00:00.