Search

The self-driving agent platform

Generating Efficient AI-Centric Kernels

'Personal AGI' that thinks on its own. Autonomous cognitive cycle, earned autonomy, 60+ tools. It decides what to do without being told.

Neural Simulator for AGI research and development

A curated archive of breakthroughs in Agents, Architecture, Training, RAG, and On-Device AI.

AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. Includes AI personas, AGI functions, world-class Beam multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud.

Extensible AGI Framework

Training code and resources for AMD-135M language models on AMD GPUs.

A curated list of recent style transfer methods with diffusion models

Open Source AI Tracing Framework built on Opentelemetry for AI Applications and Frameworks

Virtual Community: An Open World for Humans, Robots, and Society

Graph-Native Infrastructure for Context and Accountable AI Systems

NexAU (AU for Agent Universe), a general-purpose agent framework for building intelligent agents with tool capabilities.

EvoSkill — An open-source framework that automatically discovers and synthesizes reusable agent skills from failed trajectories to improve coding agent performance.

Programmatic memory for long-horizon LLM agents: the harness appends everything to one log, and the agent searches it with code. 97.4% on ARC-AGI-3 (arXiv:2607.20064)

One of the ground zero for AGI, maybe, probably. Free and Open Source forever and ever!

The first distributed AGI system. Thousands of autonomous AI agents collaboratively train models, share experiments via P2P gossip, and push breakthroughs here. Fully peer-to-peer. Join from your browser or CLI.

An agentic system that auto-optimizes LLM workloads on AMD GPUs.

Claude-Code-Python: Reconstructing Claude Code in Python

A collection of ai skills built on Warren Buffett's investing framework.

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.

MAX API Next 社区是由来自科研机构和高校的 AGI 爱好者组织发起、维护和运营的研究驱动型技术社区，聚焦 AI Models 与 Agents 治理方向，致力于建设面向 AGI 应用时代的开放基础设施。社区关注多模型与多平台接入、国产模型持续适配、AgentOps 工程实践、成本审计、权限与安全边界、私有化部署和长期运营优化，目标是把模型服务、Agent 应用、用户组织和上游平台之间的共性治理问题沉淀为稳定、可复用、可持续演进的工程能力。

fskill-creator turns your long-text SKILL into functions, making it modular, testable and trackable for better long-term maintenance and iteration

Generates original ARC-AGI-1-style tasks distribution-matched to the public eval set.

Apeireth — a digital companion that grows with you. Pure Safe Rust AGI cognitive microkernel: memory that fades like a person's, human approval before every side effect, honest boundaries. 31-member workspace (30 crates + 1 bench).

Continual learning model trained from scratch on 8GB VRAM laptop with batch-1 stream of data.