maybe buried the lede a bit – we're working on LangGraph Java 🙂 If that is interesting – get in touch
OPEN SOURCE
-
Claude Code Ports LangGraph to Java: Real World Application
By
–
good thread on using claude code to do a real world task (porting langgraph to java)
-
QwQ-32B Matches DeepSeek R1 at 20X Smaller Scale
By
–
DeepSeek just got DeepSeek'd. QwQ-32B is on par with DeepSeek R1 671B but ~20X smaller. AGI will run on your computer. Then it'll run on your phone.
-
QwQ-32B Powers Qwen Chat with Reasoning
By
–
Qwen has released a new reasoning model, QwQ-32B, which now powers Qwen Chat when you select Qwen2.5-Plus with Thinking (QwQ).
-
Hugging Face Libraries Surge: 25% Created in Early 2025
By
–
wow! >25% of Hugging Face libraries with the highest GitHub star counts (10k+) have been created in the first two months of 2025 alone staying relevant in the long run is the hardest skills in AI. each wave changes everything, our community keeps growing
-
SambaNova Cloud expands with SoftBank, Llama and Qwen access
By
–
Making waves We're expanding our SambaNova Cloud deployment with @SoftBank
! Devs will get access to … Swallow, Japan's premier open-source model @AIatMeta
's Llama @Alibaba_Qwen … all through SambaNova Cloud Read the press release #AI -
ASLP Labs Releases DiffRhythm: AI Song Generation Model
By
–
ASLP Labs debuted DiffRhythm, an open-weights model capable of generating 4-minute songs with vocals
— Rowan Cheung (@rowancheung) 5 mars 2025
All you have to do is give it lyrics and style reference, and it produces a song—taking just 10 seconds
See it in action:pic.twitter.com/HuaUt7iYK9ASLP Labs debuted DiffRhythm, an open-weights model capable of generating 4-minute songs with vocals All you have to do is give it lyrics and style reference, and it produces a song—taking just 10 seconds See it in action:
-
Cohere For AI Launches Aya Vision Open Multilingual AI
By
–
Cohere For AI unveiled Aya Vision, an open multilingual AI with vision capabilities
— Rowan Cheung (@rowancheung) 5 mars 2025
— Available in two sizes: 8B & 32B parameters
— Can describe images across 23 languages
— Also answers visual questions, translates content
— CC non-commercial licensepic.twitter.com/I3nzr7NI1fCohere For AI unveiled Aya Vision, an open multilingual AI with vision capabilities — Available in two sizes: 8B & 32B parameters
— Can describe images across 23 languages
— Also answers visual questions, translates content
— CC non-commercial license -
LangGraph BigTool: Scalable Agent Tool Access Library
By
–
LangGraph BigTool langgraph-bigtool is a Python library for creating LangGraph agents that can access large numbers of tools. – Scalable access to tools: Equip agents with hundreds or thousands of tools.
– Storage of tool metadata: Control storage of tool descriptions, -
Blended Labs Uses Llama Models for Personalized AI-Native Learning
By
–
Blended Labs, an EdTech company in Germany, is using Llama 3.1 + 3.2 models to enable a wide range of AI-native flows for personalized learning pathways, real-time feedback, instant educational content generation and social gamification