# MadcowD/ell

A language model programming library.

Repository: https://github.com/MadcowD/ell
Canonical: https://ross.abutalabs.com/products/ell
Homepage: http://docs.ell.so/
Language: Python
License: MIT
License Family: permissive
Topics: ai, prompt-engineering
Last push: 2025-06-05T21:41:57+00:00

## Health v2 (maintenance only)
Score: 34/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 25, release rhythm 35, longevity 55
- inputs: {"age_days": 773, "days_push": 454, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5864, forks 341 (observed 2026-08-28T04:09:31.768979+00:00)

## What it is
ell is a lightweight Python library for language model programming that treats prompts as functions (language model programs) rather than strings. It provides automatic prompt versioning, serialization, and a local monitoring/visualization tool called Ell Studio.

## Use cases
- write prompts as python functions for llm calls
- version and track prompt changes over time
- monitor and visualize llm calls locally
- build multimodal llm applications with images and audio
- iterate on prompt engineering like an optimization process
- manage prompt regressions with a local store

## When to choose
- you want prompts defined as typed, reusable Python functions
- you need automatic versioning and commit history for prompts
- you want a local, open-source alternative to prompt monitoring SaaS
- you work with OpenAI or Anthropic models in Python

## When to avoid
- you need a full LLM application framework with agents and chains
- you require non-Python languages
- you need hosted team collaboration for prompt management
- you only make simple one-off API calls without iteration

## Facets
- artifact type: library
- maturity: active
- function: prompt-engineering, llm-inference, monitoring, version-control
- domain: large-language-models, artificial-intelligence, developer-tools
- platform: python, cross-platform, cli
- tags: llm, prompts-as-functions, prompt-versioning, ell-studio, multimodal, openai, anthropic, natural-language-processing

## Member repositories
- MadcowD/ell (main) score 34

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:31.768979+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:51:37.395822+00:00, confidence not recorded.
  - readme: https://github.com/MadcowD/ell (fetched 2026-08-28T04:09:31.768979+00:00, sha e892af643613)
  - homepage: http://docs.ell.so/ (fetched 2026-08-29T08:47:09.995839+00:00, sha 7db0e8cd21a7)
  - site_page: https://docs.ell.so/installation.html (fetched 2026-08-29T08:47:10.004866+00:00, sha 87c29f1e8675)
- Data as of 2026-08-30T08:39:29.467469+00:00.