100% yes – currently converting all reachy’s moves into a CLI to use w/ an LLM as an orchestrator haha
CODE
-
Kimi-writer Open Sourced: AI Writing Tool Released
By
–
Open sourcing Kimi-writer.https://t.co/6jOQj8K1a0 https://t.co/odPRM1LG4w
— Pietro Schirano (@skirano) 8 novembre 2025Open sourcing Kimi-writer. https://
github.com/Doriandarko/ki
mi-writer
… -
Stock Research Agent V3 Reduces Financial Analysis Costs by 73%
By
–
Stock Research Agent V3 (Made by the LangChain Community) An AI platform transforming financial research, leveraging LangGraph and LangSmith for agent collaboration and real-time monitoring while delivering 73% cost savings. Check it out on GitHub!
-
Overcomplication in Programming: Know Your Position
By
–
"In programming, if someone tells you 'you’re overcomplicating this,' they’re either 10 steps behind you or 10 steps ahead of you." — Andrew Clark credit: @CodeWisdom
-
AI System Generates Historical Timelines Using LangGraph Multi-Agent Architecture
By
–
Event Deep Research (Made by the LangChain Community) An AI-powered system that generates historical timelines using LangGraph's multi-agent architecture. Automatically researches and compiles comprehensive JSON timelines of significant life events. Explore this
-
Streaming App Created for Testing and Validation
By
–
Interesting point. Technically shouldn’t be an issue. I have created this streaming app that you can run and test this.
-
Tech Stack: Unsloth AI and Lightning AI for Model Deployment
By
–
Tech Stack: – @UnslothAI to run and fine-tune the model
– @LightningAI environments for hosting and deployment Find all code and everything you need here: -
Fine-tune DeepSeek-OCR Locally for Your Language
By
–
Fine-tune DeepSeek-OCR on your own language!
— Akshay 🚀 (@akshay_pachaar) 8 novembre 2025
(100% local)
DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs.
It handles tables, papers, and handwriting without killing your GPU or budget.
Why it… pic.twitter.com/SfBXY4Is8oFine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it
-
DeepSeek OCR Project Reproduction: Quality Data Requirements
By
–
Very nice project reproducing deepseek OCR. More (good quality) data needed, but great start
-
Hugging Face Top 10 Models and Spaces Now Available in Anycoder
By
–
top 10 trending models and spaces on Hugging Face now show up in anycoder you can load tranformers/diffusers code for models and entire spaces apps as a starting point for vibe coding