📐 Symbolic Algebra solver

SLM Math Agent

Specialized arithmetic reasoning model. Handles math formulations, algebraic simplifications, and steps through complex equations offline.

🚀 Overview & Capabilities

Specialized arithmetic reasoning model. Handles math formulations, algebraic simplifications, and steps through complex equations offline.

Key Features

Symbolic algebra calculator mapping using local SymPy
Parses equations and graphs steps to final result
Verifies intermediate steps to prevent math hallucinations
Optimized math tokens prompt training templates

💻 Installation

Install the local CPU-optimized package using pip:

Terminal

              # Install local CPU-optimized package
pip install slm-math
            

🐙 Checkout from GitHub

Clone only this agent's folder from the monorepo using Git sparse-checkout — no need to download the full repository:

Option 1 — Sparse Checkout (Recommended)

Terminal — Git Sparse Checkout

              # 1. Create and enter a new directory
$ mkdir slm_math && cd slm_math

# 2. Initialise empty git repo and add remote
$ git init
$ git remote add origin https://github.com/t00114218-stack/SLMAgents.git

# 3. Enable sparse-checkout and set target folder
$ git sparse-checkout init --cone
$ git sparse-checkout set slm_math

# 4. Pull only that agent's source
$ git pull origin main
            

Option 2 — Full Repository Clone

Terminal — Full Clone

              $ git clone https://github.com/t00114218-stack/SLMAgents.git
$ cd SLMAgents/slm_math
            

💡 Tip: After checkout, install the package locally with pip install -e ./slm_math to run in editable mode without publishing to PyPI.

⚙️ Configuration API

Constructor Parameters

Instantiate SLMMathAgent with performance options:

Parameter	Type / Default	Description
model_path	str \| None	Explicit path to ONNX model weights. If omitted, downloads standard checkpoints.
cache_dir	str \| None	Directory to store model weights offline. Defaults to `~/.cache/slm-math/`. Also settable via SLM_MATH_AGENT_CACHE_DIR.
n_threads	int \| 4	CPU thread count for ONNX inference. Optimize for CPU core count. Also settable via SLM_MATH_AGENT_N_THREADS.

Methods

Method Signature	Return Type	Description
`solve(equation_text, system_prompt=None, user_input=None)`	`dict`	Steps through equation parameters to simplify, expand, or integrate math queries.

Method Parameters (Execution Customization)

All main execution methods accept optional system routing parameters:

Parameter	Type / Default	Description
system_prompt	str \| None	Optional custom system prompt instruction to override the default system template response parameters.
user_input	str \| None	Optional additional user-supplied target text variables or contextual keys.

Quick Start

from slm_math import SLMMathAgent

agent = SLMMathAgent()
steps = agent.solve(
    "integrate x^2 from 0 to 3",
    system_prompt="Limit decimal rounding to 2 places",
    user_input="Render steps in latex format"
)
print(steps)

Environment Variables

Configure agent parameters globally using environment values:

Environment Variable	Default	Purpose
SLM_MATH_AGENT_N_THREADS	4	Sets CPU inference execution threads.
SLM_MATH_AGENT_CACHE_DIR	~/.cache/slm-math/	Default directory to store downloaded ONNX weights.

CPU Performance Tuning

To run the SLMMathAgent engine efficiently on CPU under 1.5 GB memory footprint:

Match Threads to Core Count: Set n_threads or SLM_MATH_AGENT_N_THREADS to match the physical CPU core count.
Sequential Processing: Avoid concurrent processing when batch files are large.
Garbage Collection: Clear variables and run gc.collect() to release model RAM blocks after execution.

Verified Input & Output Logs

Diagnostic execution console response running locally on CPU:

→ INPUT:
"integrate x^2 from 0 to 3"

← OUTPUT:
{
  'equation': 'integrate(x^2, 0, 3)',
  'result': '9'
}