Agentic AI

Agentic AI AI Shorts

JetBrains Releases Mellum2: A 12B MoE Model for Fast, Specialized Tasks in Multi-Model AI Pipelines
ByRicardo June 2, 2026

JetBrains launched Mellum2, open-sourcing the weights underneath the Apache 2.0 license. The first model of Mellum was a completion-focused 4B dense mannequin. Mellum2 is its successor: a general-purpose mannequin specialised in software program engineering. It covers code era and modifying, debugging, multi-step reasoning, software use and performance calling, agentic coding, and conversational programming help. JetBrains…

Read More JetBrains Releases Mellum2: A 12B MoE Model for Fast, Specialized Tasks in Multi-Model AI Pipelines
Agentic AI AI Agents

MiniMax Releases MiniMax M3 with MSA Architecture Supporting 1M-Token Context, Native Multimodality, and Agentic Coding
ByRicardo June 1, 2026

MiniMax formally launched MiniMax M3 on June 1, 2026. The mannequin introduces MSA (MiniMax Sparse Attention), a brand new sparse consideration structure that provides M3 a 1M-token context window. M3 additionally helps picture and video enter and desktop laptop operation natively. The API is reside now. MiniMax M3 is accessible right this moment by way…

Read More MiniMax Releases MiniMax M3 with MSA Architecture Supporting 1M-Token Context, Native Multimodality, and Agentic Coding
Agentic AI AI Infrastructure

Meet Memory OS: A 6-Layer Open-Source Memory Stack Built on Top of Hermes Agent
ByRicardo June 1, 2026

Hermes Agent already remembers throughout periods. The open-source agent from Nous Research ships with curated reminiscence recordsdata and full-text session search. But a brand new neighborhood undertaking argues that in-built reminiscence is just too shallow for critical work. A new library named ‘Memory OS‘ has been launched underneath an MIT license by a developer (ClaudioDrews)….

Read More Meet Memory OS: A 6-Layer Open-Source Memory Stack Built on Top of Hermes Agent
Agentic AI Editors Pick

An Implementation of the Microsoft Agent Governance Toolkit for Safe AI Agent Tool Use with Policies, Approvals, Audit Logs, and Risk Controls
ByRicardo May 31, 2026May 31, 2026

In this tutorial, we construct a ruled AI-agent workflow utilizing Microsoft’s Agent Governance Toolkit as the reference level. We create a Colab-ready implementation the place brokers don’t straight execute instruments; as an alternative, each motion first passes by way of a governance layer that checks the agent’s identification, belief rating, danger tier, requested device, motion…

Read More An Implementation of the Microsoft Agent Governance Toolkit for Safe AI Agent Tool Use with Policies, Approvals, Audit Logs, and Risk Controls
Agentic AI Editors Pick

Build Skill-Augmented AI Agents with SkillNet for Search, Evaluation, Graph Analysis, and Task Planning
ByRicardo May 31, 2026May 31, 2026

In this tutorial, we implement a SkillNet use case as a sensible framework for discovering, putting in, inspecting, evaluating, and organizing reusable AI expertise. We begin by establishing a sturdy SkillInternet consumer with SDK and REST fallback help, then evaluate key phrase search with semantic search to grasp how expertise may be discovered for totally…

Read More Build Skill-Augmented AI Agents with SkillNet for Search, Evaluation, Graph Analysis, and Task Planning
Agentic AI Artificial Intelligence

Best Text-to-Speech TTS Models in 2026: A Benchmark-Based Comparison
ByRicardo May 30, 2026

Text-to-speech TTS moved quick over the previous 12 months. The line between artificial and human speech narrowed. Latency dropped beneath 100 milliseconds for some real-time techniques. Emotional management grew to become a normal function somewhat than a analysis demo. This information critiques the fashions that basically matter in 2026. It is written for AI professionals…

Read More Best Text-to-Speech TTS Models in 2026: A Benchmark-Based Comparison
Agentic AI AI Agents

Hermes Agent Ships Tool Search for MCP: Anthropic Evals Show 49% to 74% Accuracy Gain on Opus 4
ByRicardo May 30, 2026May 30, 2026

Nous Research’s open-source Hermes Agent now ships a Tool Search characteristic. It immediately addresses a rising bottleneck in AI agent methods: too many MCP instruments filling up the context window. In this explainer article, we’ll breaks down what Tool Search does, the way it works, and when to use it. The Problem: MCP Tools Are…

Read More Hermes Agent Ships Tool Search for MCP: Anthropic Evals Show 49% to 74% Accuracy Gain on Opus 4
Agentic AI Editors Pick

How to Use AgentTrove: Streaming 1.7M Agentic Traces and Building a Clean ShareGPT SFT Dataset in Python
ByRicardo May 30, 2026

In this tutorial, we discover AgentTrove, one of many largest open-source collections of agentic interplay traces, and find out how to work with it effectively. Instead of downloading the complete dataset, we use streaming to examine rows, detect the dialog schema, normalize agent turns, and perceive how person, assistant, system, and device messages are structured….

Read More How to Use AgentTrove: Streaming 1.7M Agentic Traces and Building a Clean ShareGPT SFT Dataset in Python
Agentic AI AI Paper Summary

NVIDIA Introduces X-Token: Projection-Guided Cross-Tokenizer KD That Outperforms GOLD by +3.82 Average Points on Llama-3.2-1B
ByRicardo May 30, 2026May 30, 2026

Knowledge distillation (KD) transfers “darkish data” from a big instructor mannequin to a smaller pupil. The pupil learns from the instructor’s full output chance distribution over tokens, not simply appropriate solutions. This is finished through per-position Kullback–Leibler (KL) divergence over next-token chance distributions. This formulation requires a shared tokenizer. A practitioner dedicated to Llama-3.2-1B can…

Read More NVIDIA Introduces X-Token: Projection-Guided Cross-Tokenizer KD That Outperforms GOLD by +3.82 Average Points on Llama-3.2-1B
Agentic AI AI Shorts

StepFun Releases Step 3.7 Flash: A 198B MoE Vision-Language Model for Coding Agents and Search Workflows
ByRicardo May 29, 2026

StepEnjoyable right this moment launched Step 3.7 Flash, a multimodal Mixture-of-Experts mannequin concentrating on agentic use circumstances. It provides native imaginative and prescient enter and improved tool-use reliability over Step 3.5 Flash. What is Step 3.7 Flash? Step 3.7 Flash is a 198B-parameter sparse Mixture-of-Experts (MoE) vision-language mannequin. It pairs a 196B-parameter language spine with…

Read More StepFun Releases Step 3.7 Flash: A 198B MoE Vision-Language Model for Coding Agents and Search Workflows

Agentic AI

JetBrains Releases Mellum2: A 12B MoE Model for Fast, Specialized Tasks in Multi-Model AI Pipelines

MiniMax Releases MiniMax M3 with MSA Architecture Supporting 1M-Token Context, Native Multimodality, and Agentic Coding

Meet Memory OS: A 6-Layer Open-Source Memory Stack Built on Top of Hermes Agent

An Implementation of the Microsoft Agent Governance Toolkit for Safe AI Agent Tool Use with Policies, Approvals, Audit Logs, and Risk Controls

Build Skill-Augmented AI Agents with SkillNet for Search, Evaluation, Graph Analysis, and Task Planning

Best Text-to-Speech TTS Models in 2026: A Benchmark-Based Comparison

Hermes Agent Ships Tool Search for MCP: Anthropic Evals Show 49% to 74% Accuracy Gain on Opus 4

How to Use AgentTrove: Streaming 1.7M Agentic Traces and Building a Clean ShareGPT SFT Dataset in Python

NVIDIA Introduces X-Token: Projection-Guided Cross-Tokenizer KD That Outperforms GOLD by +3.82 Average Points on Llama-3.2-1B

StepFun Releases Step 3.7 Flash: A 198B MoE Vision-Language Model for Coding Agents and Search Workflows

Curated by experts. Filtered for relevance.

Resources

About

Subscribe & learn more every day!