# google-deepmind/alphageometry

Repository: https://github.com/google-deepmind/alphageometry
Canonical: https://ross.abutalabs.com/products/alphageometry
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-01-13T19:18:14+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 62, release rhythm 35, longevity 75
- inputs: {"age_days": 1059, "days_push": 232, "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 4879, forks 572 (observed 2026-08-28T04:09:01.777531+00:00)

## What it is
Google DeepMind's implementation of AlphaGeometry and DDAR, AI systems that solve Olympiad-level geometry theorem proving problems. It combines a neural language model with a symbolic deduction engine to produce human-readable proofs without human demonstrations.

## Use cases
- solve olympiad geometry problems automatically
- reproduce AlphaGeometry research results from the Nature 2024 paper
- run symbolic deduction for geometry theorem proving with DDAR
- generate synthetic geometry proofs with a language model
- research neuro-symbolic mathematical reasoning

## When to choose
- you need a state-of-the-art automated geometry theorem prover
- you are reproducing or extending published AI math reasoning research
- you have GPU resources and want to run the full proof search pipeline

## When to avoid
- you need a general-purpose theorem prover beyond Euclidean geometry
- you lack the compute (multiple GPUs and many CPU workers) for full-scale search
- you want a production-ready library with pip installation and stable API

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, llm-inference, math, parser
- domain: artificial-intelligence, machine-learning, mathematics
- platform: python
- tags: geometry-prover, theorem-proving, olympiad-math, symbolic-reasoning, research-code, algorithms, linux, gpu

## Member repositories
- google-deepmind/alphageometry (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:01.777531+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 2026-08-29T18:18:16.855220+00:00, confidence not recorded.
  - readme: https://github.com/google-deepmind/alphageometry (fetched 2026-08-28T04:09:01.777531+00:00, sha aaadae0c6238)
- Data as of 2026-08-30T08:39:29.467469+00:00.