Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words

Pycodemath

by cybersora9version 0.5.2i★ 8iRuns on your computerOfficial site ↗
Registry nameio.github.cybersora9/pycodemath

How to install

What it does

Checks the math in your code and gives AI agents an exact math engine (SymPy + NumPy).

  • Connects Runs on your computer
  • Account or key No key needed
  • Category Developer tools

Use together with

Skills that teach the AI this kind of work; they work alongside this one

rea

Reverse engineer anything with agents, from app behavior down to native binaries.

by morluto★ 468,7131 skills

Skill · How-to guide

andrej-karpathy-skills

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

by multica-ai★ 234,3281 skills

Skill · How-to guideNo license stated

graphify

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

by Graphify-Labs★ 150,2761 skills

Skill · How-to guide

Why it ranks here

Lists are ordered by a usage score (out of 100) built from these parts

Popularity11/80GitHub stars or weekly downloads: the larger counts 60, the smaller 20
Freshness12/12Full marks for a release or code change within 30 days
Still answering0/8The cloud endpoint answered at the last check
Usage score23/100

Quality: Passed 3/3 basic checks (shown, not used for ordering) · Momentum: No data yet (Used only on the Trending tab)

Install

Pick the AI app you use, then copy the settings.

Let your AI install it with one sentence

Please install Pycodemath. Follow https://mcp.popnx.com/i/cybersora9-pycodemath.md, show me the commands and wait for my OK before running them.

Paste it into an AI that can work on your computer (such as Claude Code or Cursor). It reads our steps, shows you the commands and waits for your OK. No key, no sign-up. · See the full text your AI reads

Passed 3/3 checks · Runs on your computer · ✓ Commands checked Nov 14, 2026

First: which AI do you use?

Pick your app and the steps appear below.

Works with Claude, with some setup first

Install Python (uv) on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone

Let AI install it

Copy this message into a Claude chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Pycodemath for Claude on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "pycodemath": { "command": "uvx", "args": [ "pycodemath", "mcp" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Pycodemath tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install uv (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    uv --version
    • A version number such as uv … = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required

    Open the uv download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version

    Install once; it works for everything that needs uv

  2. Open the Claude desktop app’s settings file

    SettingsDeveloperEdit Config

  3. Paste these settings and save the file

    {
      "mcpServers": {
        "pycodemath": {
          "command": "uvx",
          "args": [
            "pycodemath",
            "mcp"
          ]
        }
      }
    }
  4. Quit Claude and open it again

  5. Try it

    Use Pycodemath and tell me what you can do for me, then show me one thing

    ✓ If Claude says it is using Pycodemath or shows a Pycodemath tool in the answer, you are connected

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

ChatGPT cannot connect Pycodemath yet

Pycodemath runs on your computer, but ChatGPT can only connect servers that run on the web

What you can do instead

A · Use an app that can connect Pycodemath

  • Install Python (uv) on your computer first (one time) · Only the Claude desktop app (Windows or Mac), not the web or phone
  • Install Python (uv) on your computer first (one time)
  • Install Python (uv) on your computer first (one time)
  • Install Python (uv) on your computer first (one time)

B · Others in Developer tools that work with ChatGPT

Picked from the most used in the same category, only ones that connect by address with no key

Works with Claude Code, with some setup first

Install Python (uv) on your computer first (one time)

Let AI install it

Copy this message into a Claude Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Pycodemath for Claude Code on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): claude mcp add --scope user pycodemath -- uvx pycodemath mcp 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Pycodemath tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install uv (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    uv --version
    • A version number such as uv … = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required

    Open the uv download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version

    Install once; it works for everything that needs uv

  2. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: open PowerShell

  3. Paste this command and press Enter

    claude mcp add --scope user pycodemath -- uvx pycodemath mcp
  4. Type /mcp in Claude Code

    You should see Pycodemath listed as connected

  5. Try it

    Use Pycodemath and tell me what you can do for me, then show me one thing

    ✓ If Claude Code says it is using Pycodemath or shows a Pycodemath tool in the answer, you are connected

Menu names checked against Anthropic’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with Cursor, with some setup first

Install Python (uv) on your computer first (one time)

Let AI install it

Copy this message into a Cursor chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Pycodemath for Cursor on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "mcpServers": { "pycodemath": { "command": "uvx", "args": [ "pycodemath", "mcp" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Pycodemath tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install uv (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    uv --version
    • A version number such as uv … = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required

    Open the uv download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version

    Install once; it works for everything that needs uv

  2. Click this button to open Cursor

    Open in Cursor

    Cursor asks you to confirm; click Install

  3. Open the AI chat in Cursor in Agent mode

  4. Try it

    Use Pycodemath and tell me what you can do for me, then show me one thing

    ✓ If Cursor says it is using Pycodemath or shows a Pycodemath tool in the answer, you are connected

Menu names checked against Cursor’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Works with VS Code, with some setup first

Install Python (uv) on your computer first (one time)

Let AI install it

Copy this message into a VS Code chat. The AI checks your computer, tells you which file it will change, and waits for your OK every time.

Please install the MCP server Pycodemath for VS Code on this computer, in this order: 1) Check uv with uv --version. If it is missing, tell me to install it from https://docs.astral.sh/uv/getting-started/installation/; do not install it yourself. 2) Use only this config (already checked by PopNx MCP): { "servers": { "pycodemath": { "type": "stdio", "command": "uvx", "args": [ "pycodemath", "mcp" ] } } } 3) Tell me the full path of the file you will change, or the command you will run, and wait for my OK. 4) No key is needed. 5) Do what we agreed, then check that the Pycodemath tools really show up.

This message has no key in it. If a key is needed, the AI will ask you to paste it yourself into the file or the app’s field.

  1. Install uv (if you don’t have it)

    Already installed? Check first · Open Terminal, type this command and press Enter

    uv --version
    • A version number such as uv … = installed, skip this step
    • "command not found" (on Windows: "is not recognized") = not installed yet, or installed but Terminal needs to be closed and reopened
    How to open Terminal

    Mac: press ⌘ + Space, type Terminal, press Enter

    Windows: open Start, type Windows PowerShell, then Open

    Not installed: uv has no click-through installer. Copy the one-line command for your system (macOS or Windows) from uv’s official page into Terminal · no separate Python install needed; uv downloads it when required

    Open the uv download page ↗

    When it’s done, close Terminal, open it again and run the same command. You should see a version number: uv --version

    Install once; it works for everything that needs uv

  2. Click this button to open VS Code

    Open in VS Code

    VS Code asks you to confirm; click Install

  3. Open the AI chat in VS Code in Agent mode

  4. Try it

    Use Pycodemath and tell me what you can do for me, then show me one thing

    ✓ If VS Code says it is using Pycodemath or shows a Pycodemath tool in the answer, you are connected

Menu names checked against VS Code’s help page on Nov 11, 2026 · your screen may differ slightly by app version

Other apps that use MCP, such as Windsurf, Zed or Gemini CLI, each add servers differently. See how in the app list.

See every app that uses MCP →

JSON settings are under “For developers” below

Stuck? Ask people who use Pycodemath💬 Discussion →
For developers: Terminal commands and JSON settings

Installed on your computer

Claude Code

claude mcp add --scope user pycodemath -- uvx pycodemath mcp

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "pycodemath": {
      "command": "uvx",
      "args": [
        "pycodemath",
        "mcp"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "pycodemath": {
      "command": "uvx",
      "args": [
        "pycodemath",
        "mcp"
      ]
    }
  }
}

VS Code (mcp.json)

{
  "servers": {
    "pycodemath": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "pycodemath",
        "mcp"
      ]
    }
  }
}

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

At a glance

Downloads per weeki
42/wk
Connection
Runs on your computer
Latest versioni
0.5.2
Published to registryi
Nov 14, 2026
Code last changedi
Nov 14, 2026
Maker
cybersora9
Packages
pypi: pycodemath
Registry status
Active

Which apps can use it

Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.

Run on your computer in

ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast

All apps, with pros and cons →

Related guides

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 19, 2026

  • ✓ Pass

    Maker matches the repo

    The registry name was verified with the GitHub account cybersora9, which owns the repo

  • ✓ Pass

    Still maintained

    Code last changed 5 days ago

  • ✓ Pass

    Has a licence

    Uses MIT

  • – Not applicable

    Endpoint responds

    This one runs on your computer; there is no internet endpoint

  • – Not applicable

    Sign-in with OAuth

    Runs on your computer and uses local settings instead

  • … Not checked yet

    No hidden instructions in tool descriptions

    Runs on your computer; we can only read tool lists from internet endpoints

Published vulnerabilities (OSV.dev)

No entries on OSV.dev for pycodemath@0.5.2

Checks only this package version, not every dependency · checked Nov 15, 2026

What we check → · JSON

Makers: ask for a re-check or report wrong info
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/cybersora9-pycodemath.svg)](https://mcp.popnx.com/en/servers/cybersora9-pycodemath)

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

User reviews

No reviews yet

Sign in to write a review

Compared with others in Developer toolsi

  • More stars than 88% of the other 6136 servers in this category
  • Published to the registry more recently than 89% of the other 6136 servers in this category
  • Basic checks equal to or better than 99% of the other 6136 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is Pycodemath safe?

It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

The registry does not list a required key, though some servers ask you to sign in on first use.

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed 5 days ago, and the latest version (0.5.2) reached the registry 5 days ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.

What can I use instead?

In the same category: GitDiagram, Appllama, Cloudflare MCP, Omnara, Repowise

Similar alternatives

Same category, other makers, commands already checked. Official ones first, then by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

GitDiagram

Architecture diagrams, explanations and Mermaid source for public GitHub repositories.

by ahmedkhaleel2004Widely used★ 19KUpdated 2 months ago

Runs in the cloud✓ service owner · gitdiagram.comTried by the PopNx team

Appllama

Study screens, flows and paywalls from top-earning iOS apps, then build from what wins.

by AppllamaWidely used★ 5.2KUpdated 3 months ago

Runs in the cloud✓ service owner · appllama.io

Repowise

Codebase intelligence for AI coding agents: graph, git history, docs, decisions, code health.

by repowise-devWidely used↓ 6.5K/wk★ 8.2K Stars for the whole repoUpdated 6 days ago

Computer or cloud✓ service owner · repowise.dev
Compared with similar ones
This one
Pycodemath
GitDiagramAppllamaCloudflare MCPOmnaraRepowise
Runs whereInstalls on your computerRuns in the cloud, nothing to installRuns in the cloud, nothing to installRuns in the cloud, nothing to installRuns in the cloud, nothing to installCloud or install on your computer
Needs a keyNoNoNoNoNoNo
Add with + in ClaudeNoNoNoYesNoNo
Basic checks3/34/44/44/44/45/5
LicenseMITMITMITApache-2.0Apache-2.0AGPL-3.0
PriceNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registryNo cost listed in the registry

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

Your code looks right. Is the math?

Pycodemath checks the math in your Python code. Give it a function and the formula it should compute. You get a proof that they match, or the exact input that breaks the function. No guessing, no random samples.

pip install pycodemath
# example.py

from pycodemath import check_code

SRC = ''' def sum_to(n: int) -> int: # should return 0 + 1 + ... + n total = 0 for k in range(n): # off by one: stops at n-1 total += k return total '''

if name == "main": # needed on Windows: your function runs in a worker process r = check_code(SRC, "n*(n+1)/2") print(r.verdict) # refuted print(r.counterexample.call) # sum_to(n=1) print(r.reason) # sum_to(n=1) returns 0, the formula gives 1 ...

REFUTED always comes with a concrete input that was really executed (the *witness*). VERIFIED is a proof. Anything else is UNDECIDED, with a reason. Fix the loop to range(n + 1), tell it n is a non-negative integer (domain={"n": "integer, n>=0"}), and the same call comes back VERIFIED.

Pycodemath is also an exact math engine and an MCP server for AI agents (SymPy + NumPy): write math in a few characters, get an exact answer or standalone, optimized Python/NumPy code back, instead of asking a language model to "do arithmetic in its head".

*Polska wersja tego dokumentu: README.pl.md.*

Contents: Check the math in your code · Install · First run · Quick start · Verify · Results you can branch on · Code generation · Design contracts

Four checks in 0.5.1, in one minute

1. A solver that silently drops a root. exp(x) = 3x has two real solutions; SymPy's solve returns one. certify re-checks the answer and finds the missing root:

$ python -m pycodemath "certify solve exp(x) = 3*x for x"

-LambertW(-1/3) certificate: REFUTED (sign-scan) — a root is missing: the expression changes sign at x ≈ 1.51213455165784 (confirmed at 30 and 60 digits), where no listed root lies

2. A system of equations, with proof the list is complete:

$ python -m pycodemath "solve x^2 + y^2 = 25, x + y = 7 for x, y"

x = 3, y = 4; x = 4, y = 3 proof: every solution substituted gives 0; the number of distinct complex solutions equals the dimension of Q[vars]/radical(I) (Seidenberg), so the list is complete certificate: VERIFIED (groebner) — every solution substituted gives 0; the number of distinct complex solutions equals the dimension of Q[vars]/radical(I) (Seidenberg), so the list is complete

3. A formula that loses precision, rewritten and proved equal:

$ python -m pycodemath "improve sqrt(x+1)-sqrt(x) for x in [1e6, 1e12]"

1 / (sqrt(x + 1) + sqrt(x)): 28.5 -> 0.4 bits of error on average (39.9 -> 1.6 at worst), proved by check_equal proof: verified (check_equal) — left - right simplifies to 0; agree numerically at 32 of 32 sample points certificate: VERIFIED (symbolic) — left - right simplifies to 0; agree numerically at 32 of 32 sample points

4. Money split to the cent, with no lost grosz:

$ python -m pycodemath "money split 100 PLN into 3"

33.34 + 33.33 + 33.33 = 100.00 PLN (hamilton; sums exactly: True) certificate: VERIFIED (exact) — shares sum to the total exactly (rational sum); zero weights get zero; every share within one unit of its quota; equal split: spread <= one unit; shares re-added in exact fractions

88 commands in 11 sections: run pycodemath commands for the full list, or pycodemath tour.

What it does

Built as a thin, disciplined layer over SymPy + NumPy:

  1. Cut tokens — one short command in, one exact result out. Perfect as an agent tool (MCP server included).
  2. Better code than naive Python — the generator applies symbolic simplification + common-subexpression elimination (CSE) before emitting code (measured ~1.7x faster than naive expansion on repeated subexpressions).
  3. Answers you can branch on — a failure is a TYPE, not a message, and a numerical answer can hand back the evidence behind it. See Results you can branch on.
  4. Check instead of compute — an identity, a derivation step by step, or an engine answer, judged VERIFIED / REFUTED (with a counterexample) / UNDECIDED. See Verify.
  5. Check the math in your code — a function against its formula, float accuracy, overflow, money, units and geometry, each with a witness or a proof. See Check the math in your code.
text → [parser] → IR (expression tree) → [engine]     evaluate / simplify / solve

→ [generator] IR → CSE → Python/NumPy source

Check the math in your code

Code that computes a formula can be checked like an identity. Pycodemath reads a Python function, proves it equal to the formula it should compute, or hands back the exact call that breaks it — really executed, never "it disagreed on some random samples". The same contract runs through every check below: VERIFIED is a proof, REFUTED always carries a concrete witness checked exactly, and anything else is UNDECIDED with a reason. Every answer ends with a certificate: line — the check written down, re-runnable from the file alone (see Certificates).

Does this function compute that formula? The classic off-by-one:

>>> from pycodemath import check_code, emit_test

>> src = "def sum_to(n: int) -> int:\n total = 0\n for k in range(n):\n total += k\n return total\n"

>> r = check_code(src, "n*(n+1)/2")

>> r.verdict, r.counterexample.call

('refuted', 'sum_to(n=1)')

>> r.reason

'sum_to(n=1) returns 0, the formula gives 1 — confirmed by executing the function and evaluating the formula exactly'

>> check_code(src, "n*(n-1)/2", domain={"n": "integer, n>=0"}).verdict

'verified'

>> "assert sum_to(n=1) == 1" in emit_test(r, module="sums")

True

Correct code comes back VERIFIED with a proof (symbolic, branch by branch, or an exact certificate for integer code with // and %). Float rounding alone never counts as a bug here — that is what stability is for. emit_test writes the pytest that pins the counterexample. From the shell, on your own file (its function is executed in an isolated worker to confirm a refutation):

python -m pycodemath "verify code sums.py:sum_to == n*(n+1)/2 --emit-test"

python -m pycodemath "verify code sums.py:sum_to == n*(n-1)/2 where n: integer, n>=0"

Floating-point accuracy, with proof. How many bits does float64 lose, where, and why — and a rewrite that is proved equal and measured better:

$ python -m pycodemath "stability sqrt(x + 1) - sqrt(x) for x in [1e10, 1e15]"

sqrt(x + 1) - sqrt(x) [float64]: loses 41.0 bits on average (max 49.9); worst at {'x': '510800533960562.3'} worst: at x = 510800533960562.3 computes 1.862645149230957e-08, exact 2.2123015980434279398e-8 (49.9 bits) culprit: sqrt(x + 1) - sqrt(x) — cancellation: subtracting nearly equal values (41.0 bits on average); try p - sqrt(q) -> (p^2 - q) / (p + sqrt(q)) (conjugate) certificate: REFUTED (re-evaluation) — at x = 510800533960562.3: float64 computes 1.862645149230957e-08 (emitted NumPy code), exact 2.2123015980434279398E-8 (SymPy, 40 digits): 49.9 bits lost (more than 3)

>>> from pycodemath import diagnose, improve

>> rep = diagnose("sqrt(x + 1) - sqrt(x)", {"x": (1e10, 1e15)})

>> round(rep.mean_bits, 1), rep.culprits[0].cause

(41.0, 'cancellation: subtracting nearly equal values')

>> imp = improve("sqrt(x + 1) - sqrt(x)", {"x": (1e10, 1e15)})

>> imp.best.expression, imp.best.proof.status, round(imp.best.mean_bits, 1)

('1 / (sqrt(x + 1) + sqrt(x))', 'verified', 0.4)

improve ... emit python|numpy|c prints the code that computes exactly what was measured. No rewrite is ever returned without a proof. Compared with Herbie on the 11 Hamming benchmarks the optimizer was not tuned on: 7.25 bits of error left vs 8.08 for Herbie's outputs (better on 3, worse on 5, tied on 3) — against Herbie's published 2017 report (the 1.1 era), not today's Herbie 2.x, which could not be installed in the measuring environment.

Will it overflow? The 2006 binary-search bug, with the input that breaks it (executed in NumPy int32) and a fix that is proved equivalent:

$ python -m pycodemath "ranges (lo + hi) // 2 for lo in [0, 2^31-1], hi in [0, 2^31-1] as int32"

(lo + hi) // 2 [int32] -> problems confirmed overflow lo + hi at {'hi': '2147483647', 'lo': '2147483647'} -> -2 advice: lo + (hi - lo) // 2 [int32] removes overflow advice: (lo + hi) // 2 [int64] removes overflow advice proof: lo + (hi - lo) // 2 — verified (symbolic (integer parity cases)) advice proof: (lo + hi) // 2 — verified (same expression) certificate: REFUTED (execution) — overflow at lo + hi: lo + hi at hi=2147483647, lo=2147483647: got -2, exact 4294967294

$ python -m pycodemath "maxsafe exp(x) for x as float32" x <= 88.72283172607422 is safe in float32 (exact bound 11629079/131072; interval/exhaustive proof below, executed witness above) first failure: exp(x) at x=88.72283935546875: got inf, exact 3.4028244988034356558e+38 x <= 88.72283172607422 is proved safe; x = 88.72283935546875 fails (overflow at exp(x)) certificate: VERIFIED (proof) — no event in float32 over the given ranges

int8…uint64, float16, bfloat16, float32, float64: overflow, underflow, subnormals, NaN, division by zero, lost integer precision (for t_ms in [0, 2^31-1] int as float32 — millisecond timestamps in float32). "Safe" is a proof, not a guess. In Python: pycodemath.code.analyze(expr, ranges, dtype) and max_safe_input.

Calculator that proves its answers
$ python -m pycodemath "factor 2^64+1"

274177 * 67280421310721 certificate: VERIFIED (proof) — product of the factors equals 18446744073709551617 exactly; each factor is proven prime; re-multiplied: the factors give the number back

$ python -m pycodemath "special zeta 3 digits 50" 1.2020569031595942853997381615114499907649862923405 certificate: VERIFIED (cross-check) — precision ladder: values at 65 and 130 digits agree; Euler-Maclaurin summation agrees with the default (Borwein) algorithm

$ python -m pycodemath "var sample 1 2 3 4" 5/3 certificate: VERIFIED (proof) — exact rational sample variance over a common denominator

Primality is proved (deterministic Miller–Rabin below 3.3·10²⁴, Lucas–Lehmer or a re-checkable Pocklington certificate above it; anything only BPSW-probable is UNDECIDED and says so). Number theory, combinatorics, 13 special functions at any precision, exact descriptive statistics, 7 distributions and a

Only the beginning is shown; read the rest in the repo