Skip to main content

Acumen CLI

Transform raw CSV datasets into executive-ready business insights using statistical analysis and Large Language Models via OpenRouter.

pip install acumen-cli
acumen sales_data.csv

Features

  • Load CSV files — Read any CSV with automatic encoding detection
  • Validate datasets — Check for empty data, malformed rows, missing values
  • Generate statistics — Descriptive stats per column: mean, median, std, quartiles, unique counts, missing values
  • LLM-powered insights — Send only the statistical summary (never raw data) to OpenRouter for business-level analysis
  • Beautiful terminal output — Rich-formatted tables, panels, and color-coded insights
  • Privacy-first — Raw dataset rows never leave your machine

Installation

pip install acumen-cli

Or install from source:

git clone https://github.com/acumen-cli/acumen.git
cd acumen
pip install -e .

Quick Start

  1. Set your OpenRouter API key:
export OPENROUTER_API_KEY=sk-or-v1-your-api-key-here
  1. Run Acumen on any CSV file:
acumen dataset.csv

Options

Flag Description
--model LLM model to use (default: openai/gpt-4o-mini)
--verbose Enable detailed logging
--version Show version and exit
--help Show help message

How It Works

CSV File → Validate → Statistics → JSON Summary → Prompt Builder → OpenRouter → Parse → Rich Output
  1. Load — Reads CSV with encoding detection using chardet
  2. Validate — Ensures dataset is non-empty, rows are consistent
  3. Statistics — Computes descriptive statistics per column
  4. JSON Summary — Builds a structured summary (no raw data)
  5. Prompt — Constructs a focused prompt for the LLM
  6. Analyze — Sends to OpenRouter for business insights
  7. Display — Renders insights in a beautiful Rich terminal UI

Configuration

Acumen uses environment variables loaded from a .env file (optional).

Variable Required Default Description
OPENROUTER_API_KEY ✅ Yes — Your OpenRouter API key
ACUMEN_MODEL No openai/gpt-4o-mini LLM model identifier
ACUMEN_TIMEOUT No 30 API timeout in seconds
ACUMEN_LOG_LEVEL No WARNING Logging verbosity
ACUMEN_MAX_RETRIES No 3 API retry attempts

Development

# Clone and install in editable mode
git clone https://github.com/acumen-cli/acumen.git
cd acumen
pip install -e ".[dev]"

# Run tests
pytest

# Lint
ruff check src/

# Type check (requires pyright or mypy)
mypy src/

Architecture

Acumen CLI follows a clean, modular architecture:

  • acumen/models/ — Data types and value objects
  • acumen/orchestration/ — Pipeline orchestrator tying all steps together
  • acumen/*.py — Each processing step is a standalone module

License

MIT

Metadata

Release files for acumen-cli 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for acumen-cli 0.2.0
File Size Uploaded Provenance
acumen_cli-0.2.0.tar.gz 26.7 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for acumen-cli 0.2.0
File Interpreter ABI Platform
acumen_cli-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 51.4 kB

Release files / acumen_cli-0.2.0.tar.gz

Download URL acumen_cli-0.2.0.tar.gz
Size 26.7 kB
Tags Source
SHA-256 checksum
How to use checksums
b6cb262fbd308c6c3a4f5530fc0db804fe0eb0a0edbc55128c3b44479d52df78
BLAKE2b-256 checksum
How to use checksums
2bf4eaf170bc8880135be53fc770e34e437fd3a15e82a33cd12a81df0adf799c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.3

Release files / acumen_cli-0.2.0-py3-none-any.whl

Download URL acumen_cli-0.2.0-py3-none-any.whl
Size 24.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
9e1b92db16d203d36aebab4fd37ff564187d801cb34a5064e6e00a8be10f113e
BLAKE2b-256 checksum
How to use checksums
4fbc7c4cc96ceaf2477932a21003c5dd13d81f7f3f45ad301b61bca6fe32c297
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.3

Security for acumen-cli 0.2.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

Release history Release notifications | RSS feed

This release

0.2.0 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page