HN Explorer

Show HN: SymDerive – A functional, stateless symbolic math library

26 points by dinunnob ↗ HN
Hey HN,

I’m a physicist turned quant. Some friends and I 'built' SymDerive because we wanted a symbolic math library that was "Agent-Native" by design, but still a practical tool for humans.

It boils down to two main goals:

1. Agent Reliability: I’ve found that AI agents write much more reliable code when they stick to stateless, functional pipelines (Lisp-style). It keeps them from hallucinating state changes or getting lost in long procedural scripts. I wanted a library that enforces that "Input -> Transform -> Output" flow by default.

2. Easing the transition to Python: For many physicists, Mathematica is the native tongue. I wanted a way to ease that transition—providing a bridge that keeps the familiar syntax (CamelCase, Sin, Integrate) while strictly using the Python scientific stack under the hood.

What I built: It’s a functional wrapper around the standard stack (SymPy, PySR, CVXPY) that works as a standalone engine for anyone—human or agent—who prefers a pipe-based workflow.

  # The "Pipe" approach (Cleaner for agents, readable for humans)
  result = (
      Pipe((x + 1)**3)
      .then(Expand)
      .then(Simplify) 
      .value
  )
The "Vibes" features:

Wolfram Syntax: Integrate, Det, Solve. If you know the math, you know the API.

Modular: The heavy stuff (Symbolic Regression, Convex Optimization) are optional installs ([regression], [optimize]). It won’t bloat your venv unless you ask it to.

Physics stuff: I added tools I actually use—abstract index notation for GR, Kramers-Kronig for causal models, etc.

It’s definitely opinionated, but if you’re building agents to do rigorous math, or just want a familiar functional interface for your own research, this might help.

I have found that orchestrators (Claude Code, etc) are fairly good at learning the tools and sending tasks to the right persona, we have been surprised by how well it has worked.

Repo here: https://github.com/closedform/deriver

I will cry if roasted too hard

9 comments

[ 1654 ms ] story [ 3019 ms ] thread
OutOfHere
Please never use `from something import *`, not even for a demo. It is not explicit, not maintainable, and goes against all Python guidelines. Certainly never expect any user to use it either.
marcelbundle
You would be suprised on how many large scale project I saw this beauty lamao, not saying that this is okay, people just dgaf
dinunnob
Yeah, you’re not wrong. Makes the syntax a bit annoying here (goal was to lower barrier of entry for physicists). I agree this is bad practice.
viraptor
> The "Pipe" approach (Cleaner for agents

How did you verify the benefit?

dinunnob
Not rigorous, but intuition derived from expression string complexity for postfix operations vs standard sympy style. I’ll take this out, readme was written from sleazy used car salesman advertising point of view. Was more rigorous in examples/test
nchagnet
This looks wonderful, I've dreamt of something like this back when I was in academia!

You mention some advanced stuff like abstract index notation which is usually the hardest part to get right with things like simpy and even mathematica, how does your package handle simplifications of complex tensor expressions (GR, hydrodynamics, etc.)?

dinunnob
You can specify symmetry/antisymmetry patterns for tensor index slots and it takes advantage of that to speed up the calculations. This part was pretty important for me so i spent some time thinking about it. I wanted to try to put xACT’s patterns in but it would have been quite the undertaking.