Blog

GitHub - microsoft/VibeVoice: Open-Source Voice AI

GitHub - GVCLab/PersonaLive: PersonaLive! : Expressive Portrait Image Animation for Live Streaming

GitHub - NevaMind-AI/memU: Memory infrastructure for large language models and AI agents

GitHub - VibiumDev/vibium: Browser automation for AI agents and humans

GitHub - yichuan-w/LEANN: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.

GitHub - DGoettlich/history-llms: Information hub for our project training the largest possible historical language models.

LLMRouter - LLMRouter

Everything as Code: How We Manage Our Company In One Monorepo At Kasava, we've embraced the concept of "everything as code" to streamline our operations and ensure consistency across our projects. This approach allows us to manage our entire company within a single monorepo, providing a unified source of truth for all our configurations, infrastructure, and applications. **Why a Monorepo?** A monorepo offers several advantages: 1. **Unified Configuration**: All our settings, from development environments to production, are stored in one place. This makes it easier to maintain consistency and reduces the risk of configuration drift. 2. **Simplified Dependency Management**: With all our code in one repository, managing dependencies becomes more straightforward. We can easily track which versions of libraries and tools are being used across different projects. 3. **Enhanced Collaboration**: A single repository fosters better collaboration among team members. Everyone has access to the same codebase, making it easier to share knowledge and work together on projects. 4. **Consistent Build and Deployment Processes**: By standardizing our build and deployment processes, we ensure that all our applications follow the same best practices. This leads to more reliable and predictable deployments. **Our Monorepo Structure** Our monorepo is organized into several key directories: - **/config**: Contains all configuration files for various environments, including development, staging, and production. - **/infrastructure**: Houses the infrastructure as code (IaC) scripts for provisioning and managing our cloud resources. - **/apps**: Includes all our applications, both internal tools and customer-facing products. - **/lib**: Stores reusable libraries and modules that can be shared across different projects. - **/scripts**: Contains utility scripts for automating various tasks, such as data migrations and backups. **Tools and Technologies** To manage our monorepo effectively, we use a combination of tools and technologies: - **Version Control**: Git is our primary version control system, and we use GitHub for hosting our repositories. - **Continuous Integration/Continuous Deployment (CI/CD)**: We employ Jenkins for automating our build, test, and deployment processes. - **Infrastructure as Code (IaC)**: Terraform is our tool of choice for managing cloud infrastructure. - **Configuration Management**: Ansible is used for configuring and managing our servers and applications. - **Monitoring and Logging**: We use Prometheus and Grafana for monitoring,

GitHub - Search code, repositories, users, issues, pull requests...: 🔥 A tool to analyze your website's AI-readiness, powered by Firecrawl

Fundamentals of Building Autonomous LLM Agents This paper is based on a seminar technical report from the course Trends in Autonomous Agents: Advances in Architecture and Practice offered at the Technical University of Munich (TUM).

GitHub - Tencent-Hunyuan/HunyuanOCR

Effective harnesses for long-running agents Anthropic

GitHub - pixeltable/pixeltable: Pixeltable — Data Infrastructure providing a declarative, incremental approach for multimodal AI workloads

AI Explained - Stanford Research Paper.pdf - Google Drive

We present Olmo 3, our next family of fully open, leading language models

A2UI

Nano Banana Pro is making millions of interior designers obsolete I upload my floor plan and it design the whole house for me, and even generate real images for each room based on the dimension

How to Segment Videos with Segment Anything 3 (SAM3)

Introducing MagicPath, an infinite canvas to create, refine, and explore with AI

Nano Banana Pro is wild

Next up… Slide Decks! Turn your sources into a detailed deck for reading OR a set of presentation-ready slides

Presentations — Benedict Evans

Nano Banana Pro: Gemini 3 Pro Image model from Google DeepMind

GitHub - GibsonAI/Memori: Open-Source Memory Engine for LLMs, AI Agents & Multi-Agent Systems

GitHub Projects Community (@GithubProjects) on X

I’m starting to get into a habit of reading everything (blogs, articles, book chapters,…) with LLMs

Love this framing！ This is exactly what we’re building at Weco: - you write an eval script (your verifier) - Weco iterates on the code to optimize it against that eval Software 1

Supercharge your OCR Pipelines with Open Models

[2511.09030] Solving a Million-Step LLM Task with Zero Errors

[2511.10395] AgentEvolver: Towards Efficient Self-Evolving Agent System

GitHub - rbalestr-lab/lejepa

Use Cases | Claude

Improving frontend design through Skills | Claude

Sim: Open-source platform to build and deploy AI agent workflows

Context Retrieval for AI Agents across Apps & Databases

said we should delete tokenizers

You Should Write An Agent · The Fly Blog

"🚀 Hello, Kimi K2 Thinking! The Open-Source Thinking Agent Model is here"

Link to the Strix GitHub repo: (don't forget to star 🌟)

Source: Thanks and Bharat for showing the world you can in fact tra...

This Claude Code prompt literally turns Claude Code into ultrathink...

Wren AI | Official Blog

Tongyi DeepResearch: A New Era of Open-Source AI Researchers | Tongyi DeepResearch

Syllabi – Open-source agentic AI with tools, RAG, and multi-channel deploy

OpenSkills

MiniMax-M2

AI Act Single Information Platform | AI Act Service Desk

eurollm.io

Introducing Mistral AI Studio. | Mistral AI

OpenSnowcat - Enterprise-grade behavioral data platform.

Dr Milan Milanović (@milan_milanovic) on X

Game Theory | Open Yale Courses

DeepSeek-OCR

Airbyte: The Leading Data Integration Platform for ETL/ELT Pipelines

Enterprise Deep Research

I quite like the new DeepSeek-OCR paper

olmOCR 2: Unit test rewards for document OCR | Ai2

We used DeepSeek OCR to extract every dataset from tables/charts ac...

Scripts I wrote that I use all the time

DeepSeek OCR - More than OCR - YouTube

How to Get Consistent Classification From Inconsistent LLMs? "How to Obtain Consistent Classification From Inconsistent Language Models?"

Production RAG: what I learned from processing 5M+ documents

Stanford's ALL FREE Courses [2024 & 2025] ❯ CS230 - Deep Learni...

Syllabus

Make Any App Searchable for AI Agents

PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model

Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting

nanochat

ROMA: Recursive Open Meta-Agents

NeuTTS Air

Cua: Open-source infrastructure for Computer-Use Agents

MCP Analytics and Authentication Platform

My trick for getting consistent classification from LLMs

If you're late to the whole "memory in AI agents" topic like me, I recommend investing 43 minutes to watch this video

DeepLearning.AI: Start or Advance Your Career in AI

Claude Code best practices | Code w/ Claude - YouTube

EU-funded TildeOpen LLM delivers European AI breakthrough for multilingual innovation | Shaping Europe’s digital future

The RAG Obituary: Killed by Agents, Buried by Context Windows

Anthropic releases Claude Sonnet 4.5 in latest bid for AI agents and coding supremacy

RAG-Anything: All-in-One RAG Framework

RAGLight

Turns Codebase into Easy Tutorial with AI

Failing to Understand the Exponential, Again

Prompt Packs | OpenAI Academy

AI-Researcher: Autonomous Scientific Innovation

Context Engineering for AI Agents: Lessons from Building Manus

AgenticSeek: Private, Local Manus Alternative

Learn Your Way

Qwen-Image-Edit-2509: Multi-Image Support，Improved Consistency

Qwen-Image

Introducing Tongyi Deep Research

💾🎉 copyparty

AI Engineering Hub

Deep Chat

ibm-granite/granite-docling-258M · Hugging Face

Google just dropped an ace 64-page guide on building AI Agents

opcode - The Elegant Desktop Companion for Claude Code

NocoDB Cloud

A Step-by-Step Implementation of Qwen 3 MoE Architecture from Scratch

MemoRAG: Moving Towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery