Agi Python Packages

lmms-eval

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

ansys-stk

The next generation Python API for STK

arifos

arifOS — Constitutional MCP kernel for governed AI execution. AAA trinity: AGI (Mind) · ASI (Heart) · APEX (Judge). Built for the sovereign agentic era.

dialectical-framework

Turn stories, strategies, or systems into insight. Auto-generate Dialectical Wheels (DWs) from any text to reveal blind spots, surface polarities, and trace dynamic paths toward synthesis. DWs are semantic maps that expose tension, transformation, and coherence within a system—whether narrative, ethical, organizational, or technological.

airborne-antara

Production-grade adaptive meta-learning framework for continual model improvement. Implements research DOI: 10.5281/zenodo.17839490.

anton-agent

AI coworker self-improving agent

agentforge

Extensible AGI Framework

hipcortex

Persistent causal memory for AI agents. 295x faster than Mem0. LangChain, LlamaIndex, AutoGen, CrewAI. Rust, zero deps.

yamtam-engine

Audits your AI coding agent setup before it can damage your repo. Scan first. Guard later.

tinyagent-py

🛠️ Build your own AI coding assistant with any model you want. Revolutionary agent framework with secure sandboxed execution, parallel subagents, and freedom to choose any LLM provider - OpenAI, Anthropic, Ollama, or 100+ others.

smrti

AtomSpace-inspired memory + personality engine for AI agents

ceo-py

A ReAct-Based Highly Robust Autonomous Agent (Harness) Framework.

airbornehrs

Production-grade adaptive meta-learning framework for continual model improvement. Implements research DOI: 10.5281/zenodo.17839490.

causaltorch

CausalTorch is a PyTorch library for building generative models with explicit causal constraints. It integrates graph-based causal reasoning with deep learning to create AI systems that respect logical causal relationships.

reworkd-platform-ollama

A platform for reworkd

andromeda-llm

andromeda - Pytorch

andromeda-torch

An all-new Language Model That Processes Ultra-Long Sequences of 100,000+ Ultra-Fast

andromeda-transformer

An all-new Language Model That Processes Ultra-Long Sequences of 100,000+ Ultra-Fast

carl-studio

CARL (Coherence-Aware Reinforcement Learning) — information-theoretic reward signals for LLM training via token-level probability distributions

lmm-rs

A language agnostic framework for emulating reality: A pure Rust, training-free, equation-based intelligence.

nextpy

🤖Self-Modifying Framework from the Future 🔮 World's First AMS

opendesk

Control 1 or more machines using computer use tools that integrates with your agents

xenoverse

Benchmarking general decision-making with open & random worlds

arifosmcp

arifOS v2026.03.20-CONSOLIDATION — The World's First Production-Grade Constitutional AI Governance System with Protocol Trinity (MCP + A2A + WebMCP). 11 Mega-Tools (37 modes), 13 constitutional floors (F1-F13), immutable VAULT999 ledger. Trinity architecture (ΔΩΨ): AGI Mind, ASI Heart, APEX Soul. Install: pip install arifosmcp. https://arifos.arif-fazil.com/