Open Source
436 items on noze.it
R&D Projects

CMOS: Content Management Open Source
A fully Open Source content-management platform for multi-channel and multi-device publishing, built with Bassilichi S.p...

Extra-EU Internationalisation: Swiss Market
noze's internationalisation programme towards the extra-EU market, with the opening of a Geneva office to oversee projec...
Articles (425)
8 September 2026Human Atlas: 2,234 anatomical meshes and two licences
A 3D anatomy explorer running entirely in the browser, with no accounts or API keys, offering 2,234 individually selecta...
7 September 2026Agentic reverse engineering: x64dbg exposed over MCP
A native plugin in Zig exposes x64dbg over MCP with 80 tools, from disassembly to conditional breakpoints through OEP de...
6 September 2026Anthropic releases commerce-agents: two agents, Apache-2.0
On 1 September Anthropic published commerce-agents, an Apache-2.0 blueprint with two agents, one for customers and one f...
3 September 2026NVIDIA acquires Hugging Face: commitments and dependencies
On 3 September NVIDIA announced the acquisition of Hugging Face for 12,930,300,000 dollars. The announcement lists preci...
2 September 2026GLM-5.3: the weights, the licence and the benchmark method
On 25 August Z.ai published the GLM-5.3 weights, three days ahead of the deadline it had set itself. What arrived with t...
16 August 2026DeepSeek Harness: plugins, core and capability seams
DeepSeek opened the Harness repository on 13 August, a TypeScript agent runtime under the MIT licence, built on Cordis. ...
6 August 2026Local inference on DGX Spark: the recipes for DeepSeek V4 Flash, GLM-5.2 and Qwen3.6
On one NVIDIA DGX Spark, DeepSeek V4 Flash runs at 26 tokens per second and Qwen3.6-35B in NVFP4 at 81; on two units Dee...
4 August 2026MCP 2026-07-28: a stateless protocol, MRTR and the deprecation of Roots, Sampling and Logging
The Model Context Protocol 2026-07-28 revision drops the initialize handshake and the Mcp-Session-Id header: every reque...
3 August 2026Qwen3.8-Max: a 2.4-trillion MoE and the benchmarks it claims
Qwen3.8-Max is a Mixture of Experts with 2.4 trillion parameters and context up to one million tokens, accessible from 3...
1 August 2026DeepSeek V4 Flash 0731: same architecture, new post-training
On 31 July 2026 DeepSeek moved V4 Flash out of preview. Architecture and size stay as they were in April, 284B total wit...
29 July 202626 years of noze: four technical challenges ahead
Software has stopped merely answering: it acts. Four challenges this opens, all of them designed in at the start rather ...
28 July 2026Cyber Resilience Act: a practical guide after the Commission's clarifications
On 27 July 2026 the Commission published its guidance on the Cyber Resilience Act: scope, substantial modification, supp...




