# ebhy/budgetml

Deploy a ML inference service on a budget in less than 10 lines of code.

Repository: https://github.com/ebhy/budgetml
Canonical: https://ross.abutalabs.com/products/budgetml
Language: Python
License: Apache-2.0
License Family: permissive
Topics: mlops, deployment, machine-learning, api, fastapi, inference, data-science
Last push: 2024-02-12T17:29:24+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2075, "days_push": 933, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1343, forks 65 (observed 2026-08-28T04:04:27.064576+00:00)

## What it is
BudgetML is a Python library that deploys machine learning models as secured HTTPS API endpoints on cheap GCP preemptible instances in under 10 lines of code. It auto-generates a FastAPI server with Swagger docs, OAuth2 security, and LetsEncrypt SSL certificates while keeping costs minimal and uptime high.

## Use cases
- deploy a machine learning model as a REST API cheaply
- serve model predictions on a low-budget cloud endpoint
- quickly put a trained model into production without DevOps knowledge
- host an inference API on a preemptible GCP instance
- get an HTTPS prediction endpoint with SSL in minutes
- avoid setting up Kubernetes for a single model deployment

## When to choose
- you are a data scientist who wants a model endpoint fast without learning Docker, SSL, or backend servers
- cost is a primary concern and you can tolerate brief periodic downtime
- you need a simple single-model API rather than a full production MLOps setup
- you want automatic FastAPI server generation with interactive Swagger docs

## When to avoid
- you need a fully production-grade, highly available serving infrastructure
- you are not deploying on Google Cloud Platform
- you need multi-model orchestration, autoscaling, or Kubernetes features
- you require active maintenance and long-term support, since the project is unmaintained

## Facets
- artifact type: library
- maturity: maintenance
- function: deployment, api-framework, http-server, machine-learning, llm-inference
- domain: machine-learning, cloud-computing, apis, data-science
- platform: python, cloud
- tags: mlops, fastapi, model-serving, inference-endpoint, gcp, preemptible-instances, ssl, low-cost-deployment, docker, linux

## Member repositories
- ebhy/budgetml (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:27.064576+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 2026-08-30T04:42:53.753718+00:00, confidence not recorded.
  - readme: https://github.com/ebhy/budgetml (fetched 2026-08-28T04:04:27.064576+00:00, sha 0bca60cd2d1a)
  - registry_pypi: https://pypi.org/pypi/budgetml/json (fetched 2026-08-29T12:02:15.522682+00:00, sha 9dea722df4f8)
- Data as of 2026-08-30T08:39:29.467469+00:00.