Open Source

Auto Added by WPeMatico

Deep Principle Releases Hydrogen-1.0: A 753B Open-Weight Model for Scientific Discovery

agentic ai, ai, AI (Artificial Intelligence), AI Shorts, Applications, Artificial Intelligence, Editors Pick, For Devs, Language Model, Large Language Model, Machine Learning, New Releases, Open Source, Staff, Tech News, Technology

Deep Principle has released Hydrogen-1.0, an open-weight scientific model for chemistry, materials science and life sciences. It is built by post-training Z.ai’s GLM-5.3 on domain data, laboratory records and agent discovery trajectories. For developers, it offers open weights that report a FrontierScience-Research win over GPT-6-Astra. The weights ship under the MIT License. TL;DR Size: 753B

Deep Principle Releases Hydrogen-1.0: A 753B Open-Weight Model for Scientific Discovery Read More »

Meet qwenGPU: Qwen3.5-2B With 45 Compiled GPU Layers That Run CUDA

agentic ai, ai, AI (Artificial Intelligence), AI Infrastructure, Artificial Intelligence, Editors Pick, For Devs, Language Model, Large Language Model, New Releases, Open Source, Staff, Technology

qwenGPU is an experimental model that compiles a SIMT GPU directly into the weights of Qwen3.5-2B. Developer Vixhal (@TheVixhal) released it on GitHub under the MIT license. The model runs real CUDA, compiled to NVIDIA PTX, inside its own forward passes. For developers, it tests one idea: exact computation inside a pretrained LLM, not beside

Meet qwenGPU: Qwen3.5-2B With 45 Compiled GPU Layers That Run CUDA Read More »

Nace AI Open-Sources Drex Max v1: A 27B Decision Model That Runs Locally on Apple Silicon

agentic ai, ai, AI (Artificial Intelligence), AI Shorts, Applications, Artificial Intelligence, Context Engineering, Decision Models, Editors Pick, For Devs, Harness, Language Model, Large Language Model, New Releases, Open Source, Promote, Software engineering, sponsored, Staff, Tech News, Technology

Nace AI has released Drex Max v1 as open weights. Drex Max is its most capable decision model, and it now runs on your own hardware. The release ships bf16 weights, a Q8_0 GGUF, an affine Q4 checkpoint and forks of llama.cpp and Ollama. For developers, Drex Max open weights mean routing, classification and policy

Nace AI Open-Sources Drex Max v1: A 27B Decision Model That Runs Locally on Apple Silicon Read More »

DeepSeek Open-Sources dsh-superagent, a Router-Worker Coding Agent

agentic ai, ai, AI (Artificial Intelligence), AI Agents, AI Infrastructure, AI Shorts, Applications, Artificial Intelligence, Editors Pick, For Devs, Harness, Language Model, New Releases, Open Source, Python, Software engineering, Staff, Tech News, Technology

The DeepSeek Harness team just released dsh-superagent, an MIT-licensed research prototype. DeepSeek dsh-superagent is a proactive coding agent for one GitHub repository. It is packaged as a bundle for DeepSeek Harness. It listens to GitHub and, optionally, Feishu. It turns allowed requests into parallel work items, each in its own agent session. The release shipped

DeepSeek Open-Sources dsh-superagent, a Router-Worker Coding Agent Read More »

Vercel Labs Open-Sources agent-desktop for Agent Computer Use

agentic ai, ai, AI (Artificial Intelligence), AI Agents, AI Shorts, Applications, Artificial Intelligence, Editors Pick, For Devs, New Releases, Open Source, Python, Software engineering, Staff, Tech News, Technology

Vercel Labs has released agent-desktop, an open-source CLI for AI agent computer use on macOS, Windows and Linux. agent-desktop reads each app through the operating system’s accessibility tree, not through screenshots. An agent gets a JSON snapshot with a ref for every element it can act on. Version 1.0.2 shipped on October 30, 2026, under

Vercel Labs Open-Sources agent-desktop for Agent Computer Use Read More »

Meet TokenEconomizer: Microsoft’s Plugin That Cuts Coding Agent Costs by Up to 30.9%

agentic ai, ai, AI (Artificial Intelligence), AI Agents, AI Infrastructure, AI Shorts, Applications, Artificial Intelligence, Editors Pick, For Devs, Language Model, Machine Learning, New Releases, Open Source, Staff, Tech News, Technology

A team of researchers from Microsoft Research and UC Berkeley have released TokenEconomizer, an open-source cost controller for coding agents. TokenEconomizer is a plugin that learns from past sessions in a repository to cut waste in later ones. It works with Claude Code, Codex, GitHub Copilot CLI and Pi. It does not touch model weights

Meet TokenEconomizer: Microsoft’s Plugin That Cuts Coding Agent Costs by Up to 30.9% Read More »

Baseten Releases joey-1, a 2B Decision Model at $0.01 per 1M Tokens

agentic ai, ai, AI (Artificial Intelligence), AI Infrastructure, AI Shorts, Applications, Artificial Intelligence, Decision Models, Editors Pick, For Devs, Language Model, New Releases, Open Source, Staff, Tech News, Technology, Uncategorized

Baseten has released joey-1, a 2B model from its in-house research lab, Base Labs. The joey-1 decision model returns a label and a calibrated probability instead of generated text. It targets high-volume routing, classification and guardrail checks. Baseten prices it at $0.01 per million input tokens, with open weights on Hugging Face under MIT. TL;DR

Baseten Releases joey-1, a 2B Decision Model at $0.01 per 1M Tokens Read More »

▶

Infini-AI-Lab Releases Hermit, an Open-Source Harness Adapter Framework for AI Agents

agentic ai, ai, AI (Artificial Intelligence), AI Agents, AI Infrastructure, AI Shorts, Applications, Artificial Intelligence, Editors Pick, For Devs, Harness, New Releases, Open Source, Staff, Technology

Infini-AI-Lab has released Hermit, an open-source harness adapter framework for AI agents. Hermit is a framework from Infini-AI-Lab that trains an external ‘harness adapter’ while the agent’s model and harness stay frozen. The first release, v0.1.0, shipped on October 25, 2026. CMU postdoc Haizhong Zheng announced it on X on October 27. For developers, the

Infini-AI-Lab Releases Hermit, an Open-Source Harness Adapter Framework for AI Agents Read More »

▶

NVIDIA Releases Nemotron 3.5 Transcribe: An Open 30B MoE Model for 40-Language Transcription with ~4B Active Parameters

agentic ai, ai, AI (Artificial Intelligence), AI Paper Summary, AI Shorts, Applications, Artificial Intelligence, Audio Language Model, Editors Pick, For Devs, Language Model, Large Language Model, New Releases, Open Source, Staff, Tech News, Technology, Uncategorized, Voice AI

NVIDIA has released Nemotron 3.5 Transcribe, an open-weights speech LLM built for transcription. One model handles 40 languages and recordings up to 1 hour. A text instruction picks the output style for each request. Options include verbatim, written form, speaker-attributed, contextual and translated output. For developers, it can replace separate ASR, diarization and alignment tools.

NVIDIA Releases Nemotron 3.5 Transcribe: An Open 30B MoE Model for 40-Language Transcription with ~4B Active Parameters Read More »

MiniMax Open-Sources MCode Stack: 15 Agent Skills Its Coding Team Uses Daily

agentic ai, ai, AI (Artificial Intelligence), AI Infrastructure, AI Shorts, Applications, Artificial Intelligence, Editors Pick, For Devs, Language Model, New Releases, Open Source, Software engineering, Staff, Tech News, Technology

MiniMax has open-sourced MCode Stack, the workflows and agent skills its team uses to build MiniMax Code. The MiniMax MCode Stack agent skills went public on October 28, 2026 under the MIT license. It is not a prompt collection. Each piece is a SKILL.md skill or checklist that installs directly into MiniMax Code. For developers,

MiniMax Open-Sources MCode Stack: 15 Agent Skills Its Coding Team Uses Daily Read More »