# anthropics/FlashProve

> A Lean 4 research prototype for zero-knowledge proofs of AI inference: a provider proves which model produced a reply without revealing its weights. Not maintained.

- Magnitude: 5.0 out of 10 — Early signal
- Stars: 243 total · +39 stars measured 2026-11-03, 15:31–18:00 UTC, ≈ 50 by evening
- Star trust: star growth looks organic
- Category: Security · Language: Lean · License: Apache-2.0 · Created: 2026-10-30 · Last push: 2026-10-30
- GitHub: https://github.com/anthropics/FlashProve · Page: https://gitnova.dev/en/r/anthropics/FlashProve

## Useful for

- Verify a stored example proof with cp_verify on an ordinary CPU
- Build and run toy proofs on CPU via blocks/first_look.sh
- Run CPU tests with run_suite.py to check verifier correctness

## Why it’s here

- Star-counter measurements on 2026-11-03 (UTC), 15:31–18:00: 204 → 243 stars (+39). This is the change over that interval.
- Estimated end-of-day forecast: about +50 stars, using observed gains and the previous day.
- The repository is 4 days old and already has 243 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #127.
- About 56 forks a day — people are taking the code.
- Recent forks include notable developers: @developerfred (488 followers), @mbrukman (399 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 20
- Issues and pull requests: 1
- Watchers: 0
- Average over the last week: 17 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 15

## Stars per day, last 5 days (oldest → newest, today is partial)

2026-10-30 … 2026-11-03: 0, 0, 0, 36, 39

## Spotted in now

- Top new repositories this week: #127

## Similar by description

1. **Z3Prover/z3** — 0.9 · Steady · Developer tools · C++ · +3 stars measured 2026-11-03, 00:41–18:14 UTC, ≈ 4 by evening
   Z3 is an open-source SMT solver (theorem prover) from Microsoft Research that checks satisfiability of logical formulas and proves theorems. It is used for formal verification, symbolic execution, and optimization problems.
   Full card: https://gitnova.dev/en/r/Z3Prover/z3.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-03 18:16 UTC, updated every 30 minutes.