deeplethe/utopia

8941

Local-first, agent-assisted document-to-ontology workbench

You built it. Now brag. Turn the project you just created into a short, shareable launch video with one command.

Private source preview: native Jianying drafts, isolated editing/export, and standalone Agent Skill.

Free antidetect browser stealth for Playwright: undetected headless Firefox fingerprint. Python scraping, recaptcha and bot detection bypass. Open source

A nano replica of Jev: parallel decisions, dynamic candidates, and an end-to-end training pipeline.

An Open-World Foundation Model for General-Purpose Embodied Intelligence.

Dexbotic: Open-Source Vision-Language-Action Toolbox

Assignments for CS146S: The Modern Software Dev (Stanford University Fall 2025)

Computer use for about $0.0002 a step: OCR the screen, classify the next action with TypeSafe, click. macOS.

Get your documents ready for gen AI

tiny Jev-like model built on top of Qwen2.5-0.5B you can train and run on your MacBook

Autonomous research system for measurable, computer-executable research.

A curated list of public-source, research, and commercial tools for AI security and AI-assisted cybersecurity — autotriage, agent security, AI/ML supply chain, pentest agents, AI SAST, LLM-driven fuzzing, threat intelligence, SOC/SIEM triage, reverse engineering, LLM red-teaming, and more.

Turn any open model into a classifier/jev endpoint

A local inference engine for Apple silicon, built around the model.

A straightforward method for training your LLM, from downloading data to generating text.

Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.

An Open-Source World Model for Action-Conditioned Embodied Intelligence.

A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.

A skill to stop your coding agent from burying the answer. ADHD-friendly output.