"DeepInnovator: AI Research Assistant - Idea Spark & Scientific Discovery"

Train the smallest LM you can that fits in 16MB. Best model wins!

"ClawTeam: Agent Swarm Intelligence" (One Command → Full Automation)

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

Thin and vendor agnostic layer to access, control and monitor underlying on-prem or cloud quantum computers

AI agents running research on single-GPU nanochat training automatically

Minimal and scalable research codebase in JAX, designed for rapid iteration on frontier research in LLM and other autoregressive models.

Open-source Agent Operating System

Trick Simulation Environment. Trick provides a common set of simulation capabilities and utilities to build simulations automatically.

TaskForge runs AI agents in sandboxed Docker containers with capability-based security. Agents start with minimal permissions and must request new capabilities (packages, network access, tools) thr…

"ClawWork: OpenClaw as Your AI Coworker - 💰 $15K earned in 11 Hours"

"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"

Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity

Runs 405B LLMs on 8GB VRAM

The Core Flight System (cFS)

Interactive HTML BOM generation plugin for KiCad, EasyEDA, Eagle, Fusion360 and Allegro PCB designer

Example apps for the Apps SDK

A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Python and .NET.

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.5, DeepSeek, gpt-oss locally.

F´ - A flight software and embedded systems framework

Anki is a smart spaced repetition flashcard program

AGENTS.md — a simple, open format for guiding coding agents

🤘 TT-NN operator library, and TT-Metalium low level kernel programming model.

🔥 Clone and recreate any website as a modern React app in seconds

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Cosmos-Transfer1-DiffusionRenderer: High-quality video de-lighting and re-lighting based on Cosmos video diffusion framework

AgentSociety: Large-scale Social Simulation to Understand Human Behaviors and Society through LLM-driven Agents

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

sharing current agents in use