REPOGEO REPORT · LITE

lean-dojo/LeanDojo

Default branch main · commit 7a9f600b · scanned 6/12/2026, 10:52:10 AM

GitHub: 806 stars · 117 forks

AI VISIBILITY SCORE

40 /100

Critical

Category recall

0 / 2

Not recommended in any query

Rule findings

2 pass · 0 warn · 0 fail

Objective metadata checks

AI knows your name

3 / 3

Direct prompts that named your repo

HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface lean-dojo/LeanDojo, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION

highreadme#1

Clarify README's deprecation notice to reflect transition

Why:

CURRENT

### Note: This original LeanDojo library is deprecated. Please use LeanDojo-v2 for all new projects. The information below is kept for historical reference. We will soon be moving LeanDojo-v2 here.

COPY-PASTE FIX

### Note: This repository is transitioning to become LeanDojo-v2. While we prepare for the full migration, please refer to the LeanDojo-v2 repository for all new projects. The information below pertains to the original LeanDojo library and is kept for historical reference during this transition.

mediumreadme#2

Strengthen README's opening value proposition for AI research

Why:

CURRENT

LeanDojo is a Python library for learning–based theorem provers in Lean, providing two main features: * Extracting data (proof states, tactics, premises, etc.) from Lean repos. * Interacting with Lean programmatically.

COPY-PASTE FIX

LeanDojo is a comprehensive Python library designed for AI research in theorem proving, specifically enabling programmatic interaction with the Lean proof assistant. It provides robust tools for: * **Data Extraction:** Systematically extracting proof states, tactics, premises, and other crucial data from Lean repositories for machine learning model training. * **Programmatic Interaction:** Facilitating real-time, automated interaction with Lean, allowing AI agents to apply tactics and observe proof environments.

lowreadme#3

Complete the 'Questions and Bugs' section with a clear support channel

Why:

CURRENT

* For general questions and

COPY-PASTE FIX

* For general questions and bug reports, please open an issue on our [GitHub Issues page](https://github.com/lean-dojo/LeanDojo/issues).

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall

0 / 2

0% of queries surface lean-dojo/LeanDojo

Avg rank

—

Lower is better. #1 = top recommendation.

Share of voice

Of all named tools, what % are you?

Top rival

Coq

Recommended in 1 of 2 queries

COMPETITOR LEADERBOARD

Coq · recommended 1×
SerAPI · recommended 1×
Coq-Elaborator · recommended 1×
coqtop · recommended 1×
Lean · recommended 1×

CATEGORY QUERY
How can I extract proof states and tactics from formal verification systems for machine learning?
you: not recommended
AI recommended (in order):
1. Coq
2. SerAPI
3. Coq-Elaborator
4. coqtop
5. Lean
6. lean --server
7. lean --json
8. Elan
9. Isabelle/HOL
10. PIDE
11. Isabelle/ML
12. Sledgehammer
13. F*
14. fstar.exe --json
15. Dafny
16. Boogie
17. Z3
18. Dafny Language Server
19. ACL2
20. Common Lisp
AI recommended 20 alternatives but never named lean-dojo/LeanDojo. This is the gap to close.
Show full AI answer
CATEGORY QUERY
Python library to programmatically interact with proof assistants for AI research and automation.
you: not recommended
AI recommended (in order):
1. PyCoq
2. Ltac2Py
3. Proof General
4. Isabelle/PIDE
5. Z3Py
6. Lean 4
AI recommended 6 alternatives but never named lean-dojo/LeanDojo. This is the gap to close.
Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

Metadata completeness
pass
README presence
pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

Compared to common alternatives in this category, what is the core differentiator of lean-dojo/LeanDojo?
pass
AI named lean-dojo/LeanDojo explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
If a team adopts lean-dojo/LeanDojo in production, what risks or prerequisites should they evaluate first?
pass
AI named lean-dojo/LeanDojo explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?
In one sentence, what problem does the repo lean-dojo/LeanDojo solve, and who is the primary audience?
pass
AI named lean-dojo/LeanDojo explicitly
AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of lean-dojo/LeanDojo. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

Live preview

MARKDOWN (README)

[![RepoGEO](https://repogeo.com/badge/lean-dojo/LeanDojo.svg)](https://repogeo.com/en/r/lean-dojo/LeanDojo)

HTML

<a href="https://repogeo.com/en/r/lean-dojo/LeanDojo"><img src="https://repogeo.com/badge/lean-dojo/LeanDojo.svg" alt="RepoGEO" /></a>

Pro

Subscribe to Pro for deep diagnoses

lean-dojo/LeanDojo — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

Deep reports10 / month
Brand-free category queries5 vs 2 in Lite
Prioritized action items8 vs 3 in Lite