Reasoning Python Packages

owlrl

A simple implementation of the OWL2 RL Profile on top of RDFLib: it expands the graph with all possible triples that OWL RL defines. It can be used together with RDFLib to expand an RDFLib Graph object, or as a stand alone service with its own serialization.

pageindex

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

miniful

A minimal fuzzy library

arbiter-engine

A detection engine that reports what it did not check. Eight axiom families over a domain model declared in YAML, with every declined evaluation recorded as a machine-readable reason.

semantica

Graph-Native Infrastructure for Context and Accountable AI Systems

agentmake

AgentMake AI: a kit for developing agentic AI applications that support 24 AI backends and and work with 7 agentic components, such as tools and agents. (Developer: Eliran Wong) Supported backends: anthropic, azure, azure_any, cohere, custom, deepseek, genai, github, github_any, googleai, groq, llamacpp, mistral, ollama, openai, vertexai, xai

dialectical-framework

An open-source AI reasoning framework that uses dialectics, semantic graphs, and polarity management to drive LLMs toward objective synthesis and advanced human-AI collaborative decision-making.

graqle

Persistent organisational intelligence for AI agents. Turn codebases, documents, policies and decisions into a knowledge graph — 13 LLM backends, impact analysis, evidence + confidence. Works with Claude Code, Cursor, Copilot.

reasongraph

Graph memory for AI agents: facts in, entities and cause->effect relations extracted with small open models, multi-hop recall with a cited chain. Library, HTTP/MCP service, LangChain, hosted at memory.primaxiom.ai

opendsstar

OpenDsStar is an open-source implementation of the DS-Star agent that replaces file-based workflows with a flexible, tool-centric architecture. It supports incremental execution, reuses intermediate results, and makes complex multi-step agents more modular, efficient, and extensible.

awex

A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from training to inference in RL workflows

ripple-down-rules

A python implementation of the various ripple down rules versions, including Single Classification (SCRDR), Multi Classification (MCRDR), and Generalised Ripple Down Rules (GRDR).

ixentbench

iXentBench™ — The Benchmark Beyond AI Reasoning

open-ontologies-lite

Plan, apply and roll back changes to a production ontology, with a blast radius report and a proof an auditor can re-check.

quantum-reasoning-skill

Model-agnostic Agent Skill: keep multiple hypotheses alive, test them against evidence, revive alternatives, collapse to the best-supported answer. Ships the skill contract, a reference branch controller and a benchmark harness. No model evaluation published yet, so no performance claim.

cmem-plugin-reason

Perform reasoning tasks and validate OWL consistency.

abstractllm

A unified interface for Large Language Models with memory, reasoning, and tool capabilities. Supports OpenAI, Anthropic, Ollama, HuggingFace, and MLX with hierarchical memory system and agent development features.

entity-query-language

A relational query language that is pythonic and intuitive.

fpf-thinking-map

Small MIT-licensed runtime for bounded LLM traversal, inspired by FPF and focused on practical agent behavior. ISO/IEC 25010 · 27001 · ISO 9001 aligned evidence (not certified).

hrm-pytorch

Exploration into the proposed architecture from Sapient Intelligence of Singapore 🇸🇬

mship

Self-hosted, OpenAI-compatible inference for the agentic era: reasoning LLMs, universal tool calling, and the Responses API alongside embeddings, speech, and image models — many models sharing your GPUs, one gateway. Powered by Ray Serve.

ntloss

PyPI package for Number Token Loss (ICML 2025)

bhv

Boolean Hypervectors with various operators for experiments in hyperdimensional computing (HDC).

cognigraph

Persistent organisational intelligence for AI agents. Turn codebases, documents, policies and decisions into a knowledge graph — 13 LLM backends, impact analysis, evidence + confidence. Works with Claude Code, Cursor, Copilot.