Most LLM agents work well for small tool-calling loops, but they start to break down when the task becomes multi-step, stateful, and artifact-heavy. langchen’s deep agent Designed for that difference. …
Tag:
Releases
-
-
Generative AI
NVIDIA releases Nemotron 3 Super: a 120B parameter open-source hybrid Mamba-Attention MOE model that delivers 5x higher throughput for agent AI.
by ai-intensifyThe gap between the proprietary frontier model and the highly transparent open-source model is narrowing faster than ever. NVIDIA has officially pulled back the curtain nemotron 3 superA staggering 120 …
-
Generative AI
ByteDance releases Dearflow 2.0: an open-source superagent harness that orchestrates sub-agents, memory, and sandboxes to perform complex tasks
The era of ‘Copilot’ is officially getting an upgrade. While the tech world has spent the last two years getting comfortable with AI that suggests code or drafts emails, the …
-
AI Tools
Andrew Ng’s team releases Context Hub: an open source tool that gives your coding agent the updated API documentation they need
In the fast-paced world of agentic workflows, even the most powerful AI model is still only as good as its documentation. Today, Andrew Ng and his team officially launched DeepLearning.AI …
-
Generative AI
Microsoft Releases Phi-4-Reasoning-Vision-15B: A Compact Multimodal Model for Mathematics, Science, and GUI Understanding
Microsoft has released fi-4-logic-vision-15bA 15 Billion Parameter Open-Weight Multimodal Reasoning Model Designed for image and text tasks that require both perception and selective reasoning. It is a compact model designed …
-
AI News
Google AI releases Android Bench: an assessment framework and leaderboard for LLMs in Android Development
Google has officially released android benchA new leaderboard and evaluation framework designed to measure how large language models (LLMs) perform specifically on Android development tasks. The dataset, methodology and test …
-
AI News
Google AI releases a CLI tool (gws) for the Workspace API: providing a unified interface for humans and AI agents
Integrating Google Workspace APIs – like Drive, Gmail, Calendar, and Sheets – into applications and data pipelines typically requires writing boilerplate code to handle REST endpoints, pagination, and OAuth 2.0 …
-
AI News
OpenAI Releases Symphony: An Open Source Agent Framework for Orchestrating Autonomous AI Agents through Structured, Scalable Implementation Runs
OpenAI has released symphonyAn open-source framework designed to manage autonomous AI coding agents through structured ‘implementation runs’. This project provides a system to automate software …
-
AI News
YuanLab AI Releases Yuan 3.0 Ultra: A Flagship Multimodal MOE Foundation Model, Built for Strong Intelligence and Unmatched Efficiency
How can a trillion-parameter large language model achieve state-of-the-art enterprise performance while reducing its total parameter count by 33.3% and increasing pre-training efficiency by 49%? Yuan Lab AI releases Yuan3.0 …
-
AI Tools
Alibaba releases OpenSandbox to provide software developers with a unified, secure, and scalable API for autonomous AI agent execution
Alibaba has released opensandboxis an open-source tool designed to provide AI agents with a secure, isolated environment for code execution, web browsing, and model training. Issued under Apache 2.0 LicenseThe …
Newer Posts