Staatsgeheim/MathKernel

Evidence-aware multi-engine mathematics runtime for LLMs: exact, symbolic, formal, certified-interval and numeric computation with typed MathIR, trust labels, and full provenance

Language modelsPython

0.3 Steady Magnitude out of 10. Star growth looks organic. Data as of September 14, 2026.

Open on Seismograph Open on GitHub

About the project

Evidence-aware multi-engine mathematics kernel for LLMs (SymPy, Z3, Lean, mpmath) that computes exactly, symbolically, formally and in certified intervals while tracking trust levels and provenance. Usable as a Python library and as an MCP server.

Useful for

Connect the MCP server to an LLM so the model computes math instead of hallucinating answers
Verify symbolic or formal derivations while keeping the provenance trail
Get certified interval enclosures for arbitrary-precision numerical computations

README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.

Why it’s trending

The repository is 8 days old and already has 58 stars.
Hacker News: “MathKernel: An evidence-aware multi-engine mathematics kernel and MCP server” — 37 points, 6 days ago.

Stars per day

Bars are daily stars, the line is the usual pace. Red marks spike days.

Numbers

Total stars: 58
Stars in a day: 0
Forks: 3
Issues and pull requests: 1
Watchers: 0
Language: Python
License: MIT
Created: September 6, 2026
Last push: September 9, 2026

Star trust

Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.

These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.

Hacker News discussions

MathKernel: An evidence-aware multi-engine mathematics kernel and MCP server37 points, September 7, 2026

Spotted in

September 14, 2026Spotted on Hacker News
September 13, 2026Spotted on Hacker News

README badge

Paste it into your README — the badge shows the current magnitude and links to this page.

[![Seismograph](https://gitnova.dev/badge/Staatsgeheim/MathKernel.svg?lang=en)](https://gitnova.dev/en/r/Staatsgeheim/MathKernel)

Similar projects

6.4
JustVugg/colibri
A pure-C, zero-dependency inference engine for running large MoE models (744B–2.8T parameters) on consumer hardware by treating VRAM, RAM, and storage as a single multitier hierarchy and streaming experts from disk.

BreakoutLanguage modelsC+1,049 stars in a day
5.6
asgeirtj/system_prompts_leaks
A collection of extracted system prompts from Anthropic, OpenAI, Google, xAI and others — the hidden instructions chatbots receive before a user's first message.

BreakoutLanguage modelsJavaScript+419 stars in a day
5.1
huggingface/transformers
Model-definition framework for state-of-the-art pretrained ML models (text, vision, audio, multimodal) for inference and training, compatible with most training and inference engines.

BreakoutLanguage modelsPython+273 stars in a day
5.0
MiaAI-Lab/DeepSeek-v4.1-Flash-EXL3-2x-DGX-Sparks
A local EXL3 2.9 bpw checkpoint of DeepSeek-V4.1-Flash (196 GiB, 39 shards) served via an OpenAI-compatible vLLM API on a 2x NVIDIA GB10 (DGX Spark) kit with tensor-parallel 2. Includes DSpark speculative decoding and…

Early signalLanguage modelsPython+80 stars in a day
4.7
unclecode/crawl4ai
Open-source web crawler and scraper that turns pages into clean, LLM-ready Markdown for RAG, agents and data pipelines. Runs via Python API, CLI and Docker with no API keys.

BreakoutLanguage modelsPython+407 stars in a day
4.6
Edge0-AI/Edge0
An open-source streaming MoE inference framework: expert weights are offloaded from SSD on demand while a trained prerouter predicts routing ahead of time. Runs on Apple Silicon via MLX and ships with two ready-to-run…

CoolingLanguage modelsPython+116 stars in a day