Thanks! I think it shouldn't be too hard. I have a Qwen3.5 from-scratch implementation here: https://
github.com/rasbt/LLMs-fro
m-scratch/blob/main/ch05/16_qwen3.5/qwen3.5-plus-kv-cache.ipynb
… that you can use as a drop-in replacement. Perhaps the easiest thing to do here is to take that and put it into the qwen. py (
https://
github.com/rasbt/LLMs-fro
m-scratch/blob/main/pkg/llms_from_scratch/qwen3.py
…). If you
CODE
-
Qwen3.5 Implementation Integration Guide for LLMs
By
–
-
LangChain Launches Day 0 Support for Nvidia Nemotron 3 Super
By
–
Day 0 support for Nvidia's Nemotron 3 Super! We're excited to support open source models that push the frontier of model intelligence, cost, and latency Try it out in deepagents today!
-
Project Migration to Codeberg with Improved Action Runners
By
–
REMINDER: The project and releases are now hosted on Codeberg. Enjoying it very much, easier to customize the Action Runners.
-
Agents in Production: Unpredictability Beyond Traditional Software Testing
By
–
New Conceptual Guide: You don’t know what your agent will do until it’s in production With traditional software, you ship with reasonable confidence. Test coverage handles most paths. Monitoring catches errors, latency, and query issues. When something breaks, you read the
-
Agentic Organizations Can Be Forked Through IDE Code
By
–
All of these patterns as an example are just matters of “org code”. The IDE helps you build, run, manage them. You can’t fork classical orgs (eg Microsoft) but you’ll be able to fork agentic orgs.
-
Open Source Code and AI Training: A Matter of Legitimacy
By
–
It is absurd to have a problem with AI learning from code you have open sourced. If github trained models on the contents of your private repos, that would be a violation.
-
IDE Evolution: From Files to AI Agents Programming
By
–
Expectation: the age of the IDE is over
Reality: we’re going to need a bigger IDE
(imo). It just looks very different because humans now move upwards and program at a higher level – the basic unit of interest is not one file but one agent. It’s still programming. -
Genie Code: Autonomous AI Agent for Data Teams
By
–
Today we're announcing Genie Code, your autonomous AI partner for data.
— Databricks (@databricks) 11 mars 2026
Genie Code is a state-of-the-art agent that lets data teams move from prompting a copilot to delegating real work: building pipelines, machine learning models, debugging failures, and shipping dashboards.… pic.twitter.com/q1tl0WRypIToday we're announcing Genie Code, your autonomous AI partner for data. Genie Code is a state-of-the-art agent that lets data teams move from prompting a copilot to delegating real work: building pipelines, machine learning models, debugging failures, and shipping dashboards.
-
Replit Agent 4: Plan, Design, Build Simultaneously for Enhanced Creativity
By
–
Introducing Replit Agent 4 – built to unlock your creativity.
— Replit ⠕ (@Replit) 11 mars 2026
Plan. Design. Build. All at once. Stay in the flow.
What’s new:
1. Design freely on an infinite canvas
2. Move faster with parallel agents
3. Ship anything like mobile apps, websites, slides, and data… https://t.co/uqHWDP3SMTIntroducing Replit Agent 4 – built to unlock your creativity. Plan. Design. Build. All at once. Stay in the flow. What’s new: 1. Design freely on an infinite canvas 2. Move faster with parallel agents 3. Ship anything like mobile apps, websites, slides, and data