# ExtensityAI/symbolicai

A neurosymbolic perspective on LLMs

Repository: https://github.com/ExtensityAI/symbolicai
Canonical: https://ross.abutalabs.com/products/symbolicai
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: large-language-models, neurosymbolic-ai, probabilistic-programming
Last push: 2026-08-25T15:50:48+00:00

## Health v2 (maintenance only)
Score: 94/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 85, longevity 98
- inputs: {"age_days": 1372, "days_push": 8, "days_rel": 20, "gap_med": 5.0, "n_releases_24m": 65}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1750, forks 93 (observed 2026-08-28T04:05:31.073265+00:00)

## What it is
SymbolicAI is a Python neuro-symbolic framework that blends classical programming with LLM capabilities through composable Symbol primitives and contracts. It provides a modular engine system supporting custom engines, local models, and tool integrations like web search and image generation.

## Use cases
- build neuro-symbolic applications that mix python logic with llm calls
- compose semantic operations on text like native python operators
- swap between cloud and locally hosted llm engines
- integrate web search or image generation into llm pipelines
- prototype probabilistic programming with large language models

## When to choose
- you want llm calls embedded naturally into python code with composable primitives
- you need a modular framework to plug in custom or local llm engines
- you are exploring neuro-symbolic or probabilistic programming approaches to llms

## When to avoid
- you need a simple chatbot wrapper with minimal abstraction
- you require a production-proven framework with a large community and ecosystem
- your project avoids experimental research-oriented frameworks

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, prompt-engineering, sdk
- domain: large-language-models, artificial-intelligence, machine-learning, developer-tools
- platform: python, cross-platform
- tags: neurosymbolic-ai, probabilistic-programming, llm-abstraction, symbolic-programming

## Member repositories
- ExtensityAI/symbolicai (main) score 94

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:31.073265+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 2026-08-30T03:28:34.175017+00:00, confidence not recorded.
  - readme: https://github.com/ExtensityAI/symbolicai (fetched 2026-08-28T04:05:31.073265+00:00, sha 2648d3165087)
  - registry_pypi: https://pypi.org/pypi/symbolicai/json (fetched 2026-08-29T11:06:25.371837+00:00, sha 5bf74ef11bbd)
- Data as of 2026-08-30T08:39:29.467469+00:00.