SigNoz released a Semantic Kernel dashboard that monitors token usage, error rates, latency, and model distribution for applications using Microsoft's Semantic Kernel, requiring SigNoz v0.135.0 or new…
Microsoft Research released EvoLib on July 30th, a test-time learning framework that enables large language model agents to improve across tasks without updating their underlying weights. The framewor…
Microsoft Foundry's Toolboxes introduce a tool search capability that reduces token costs and context bloat by exposing only two meta-tools—tool_search and call_tool—instead of loading every tool on e…
Microsoft released a reference architecture for routing agent traffic on Azure Kubernetes Service that combines the Kubernetes Gateway API Inference Extension, agentgateway, and RouteLLM into one Open…
Microsoft's Azure Kubernetes Service engineering team published a reference implementation on June 29 that separates agent-request routing into three layers: semantic model selection via RouteLLM, gat…
A developer calculated the hidden costs of AI vendor lock-in, estimating that migrating a production document analysis pipeline from a proprietary stack to an open-source alternative could cost $200,0…
The Premier League and Microsoft have launched the Fantasy Premier League Companion powered by Copilot, built with Microsoft Foundry, Azure OpenAI, and ChatGPT 5.4, to help managers make informed deci…
Microsoft Foundry, Azure AI Search, and Azure Cosmos DB are combined to build a grounded search agent that uses function calling to route between unstructured document retrieval and structured data qu…
TokenHub, a private enterprise AI gateway developed by Asta Xie, provides role-based workspaces for users, team leaders, and administrators, separating model usage, team governance, and platform admin…
A small team built Gatekeeper, a single-file AI PR reviewer for Azure DevOps that enforces compliance gates and runs four parallel AI analysis streams. In a benchmark against CodeRabbit, Qodo Merge, a…
Microsoft released agent-framework, an open-source framework for building and deploying AI agents and multi-agent workflows in Python and .NET, with support for Microsoft Foundry, Azure OpenAI, OpenAI…
LogGuardAI, a Log4j2 plugin that automatically detects and masks sensitive data in Java logs using rule-based analysis and AI, has been released on May 27, 2026. The tool supports 20+ sensitive keywor…
LLMrPro, a new self-hosted LLM router, pools users' own machines as inference workers with automatic per-tier cloud fallback, exposing a single OpenAI-compatible API. The open-source project, released…
Microsoft Project Online will retire on September 30, 2026, according to a confirmed announcement from Microsoft. Onplana, an AI-native project management platform powered by Claude and Azure OpenAI, …
A developer built Stylifyword, a Microsoft Word add-in that formats documents using local AI, addressing data sovereignty concerns for regulated industries. The tool runs entirely on the user's machin…
An engineer details the architecture of production-ready Agentic AI systems, explaining that autonomous agents require a brain (LLM), tools, memory, and a goal to function reliably. The post covers th…
Microsoft released a public preview of its Agent Framework for Go on July 10, bringing production-grade AI agent development to Go developers for the first time. The Go SDK supports tool calling, mult…
Microgpt's 100,000-token context window costs 14x more than benchmark claims due to an undocumented architectural decision in line 127 of its multi-head attention implementation, according to a techno…
Lightport, a maintained fork of Portkey AI Gateway, is a lightweight AI gateway that makes 77 LLM providers OpenAI-compatible by transforming requests and responses, explicitly excluding retries, cach…
Embedcache, a new open-source proxy from developer Ajay6601, cuts embedding API costs by caching redundant requests, reporting that it can eliminate duplicate work for platform and ML-infra teams proc…