LangChain BlogLangChain has developed a model router for its open-source coding agent Open SWE, which dispatches requests to different models (GLM-5.3-Flash, GPT-5.6 Sol, GPT-6 Astra) based on task type and complexity, balancing cost, speed, and intelligence, reducing the median cost per thread by 64% without compromising quality.
Microsoft AI NewsMAI-Transcribe-2-Streaming provides low-latency real-time transcription for 60 languages and supports automatic language detection, achieving the top accuracy in both final and partial transcription on Artificial Analysis.
Browser UseBrowser Use offers usage-based AI agent infrastructure, supporting cloud browser control via CDP, Playwright, or Puppeteer, with reusable browser profiles
LangChain Deep Agents releases3232LangChain Deep Agents 0.7.21 released, adding `FilesystemMiddleware` for blob storage functionality in the backend. Updated urllib3 dependency to 2.8.0 and increased the minimum version requirement for dependencies.
Google DevelopersFeatured2222Google's October 1 Developer Knowledge release notes add knowledge.workspace.google.com to the corpus. Earlier September updates made the developer-knowledge CLI generally available and introduced an agent skill that selects an MCP tool or falls back to the REST API. The API provides documentation search, document retrieval and grounded answers.
Why it matters: Editorial takeaway: documentation retrieval can be part of an agent's toolchain instead of relying entirely on memorized APIs. Check supported domains and access requirements; this is a corpus update, not the API's original launch.
Baseten BlogBaseten collaborates with OpenAI to integrate support for open-source models into the agentic workflows of OpenAI customers, enabling organizations to optimize agentic workflows across open and closed models and route tasks to the best model. Baseten provides features such as Day zero model access, full-stack performance optimization, multi-cloud capacity and reliability, developer experience, and enterprise governance to support fast and reliable inference and seamless integration into enterprise toolchains.
Microsoft Official BlogMicrosoft launched Fabric IQ, Azure Databases, and other data innovations at the European Microsoft Fabric + SQL Community Conference in Barcelona, integrating unique business contexts into Microsoft Copilot.
Ollama BlogOllama 0.35 version adds support for decision models based on the TypeSafe Jev API through the new /v1/systemone endpoint, allowing local operation for low latency, typed rapid decision-making.
OpenClaw Blog7575OpenClaw Enterprise (OCE) is an open-source, vendor-neutral agent management platform designed for sensitive environments. The platform introduces an enterprise-grade control plane before the 1.0 release through multi-tenancy, hard security boundaries, and standardized agent primitives, supporting governance and auditing, and allowing core components like harness, models, and sandboxes to replace third-party or internal implementations.
Mistral AIMistral AI opens a German center in Munich to advance industrial AI in Europe's largest economy. Germany is the EU's largest industrial economy, with its companies accumulating multi-generational proprietary data and process knowledge, covering automotive, energy, aerospace, and advanced manufacturing sectors.
Baseten Blog7070Baseten becomes a launch partner of the NVIDIA Agent Safety Platform, collaborating with NVIDIA OpenShell and Blaxel sandboxes to advance the open and secure frontiers of AI
GitHub Blog · AI & MLThe canvas in GitHub Copilot is a customizable interface that can be shared between users and agents, supporting various forms like Kanban, issue filtering, and release lists. It can be automatically generated by describing the requirements via the /create-canvas skill, and both parties can collaborate in real-time to modify the status.
OpenClaw Blog7575Microsoft's released Autopilot personal agent based on OpenClaw, Microsoft and OpenClaw Foundation collaborate to enhance its enterprise-level runtime capabilities, has opened the preview to the first batch of customers. Microsoft improves OpenClaw through upstream contributions, including enhancing agent security configuration checks, building native Windows experience, improving interaction reliability, and optimizing background task processing and database recovery response.
Baseten Blog7575LangChain announced the launch of the LangSmith fine-tuning feature at the Interrupt 26 conference in New York today. The feature is based on the open-source CLI smithtune, which reads LangSmith traces to generate supervised fine-tuning datasets and trains them on Baseten Loops, finally deploying them to Baseten's dedicated inference service. The CLI uses the user's Baseten API key, and training and inference costs are charged to the Baseten account.
GitHub Blog · AI & MLGitHub Security Lab Taskflow Agent automates the fuzzing process for C/C++ projects using LLM, completing entry point identification, build system analysis, test case generation, AFL++ execution, coverage analysis, and vulnerability report writing without manual intervention. The Agent uses the Claude Sonnet 5 model and manages state via an SQLite database to achieve iterative coverage improvement, doubling the time budget for each iteration until coverage growth stagnates.
Google DeepMindGemini 3.8 Live with Live Avatar released, enhancing near real-time visual presentation capabilities for Gemini conversational AI by natively coupling real-time video generation with speech, supporting 97 languages simultaneously, and available in Gemini Enterprise.
Qoder Blog00Qoder Agent released, providing Agent SDK and cloud-based agents, supporting collaboration with humans in environments such as IDEs, CLI, etc.
Google Developers BlogGoogle Cloud API Gateway is now available in public preview as a remote MCP server. By annotating an OpenAPI specification and deploying it, existing REST operations can be converted into callable MCP tools for agents without the need for an additional server.
OpenHands Blog7575OpenHands Enterprise's latest version has added organizational-level features such as management credentials, usage, integration, and automation, and updated the interface aligned with Agent Canvas. Administrators can configure organizational key sharing, monitor usage through the 'Your Budget' dashboard, support OAuth authentication to connect to MCP servers, and achieve cross-organizational visibility and management automation.
Google DeepMindGoogle DeepMind introduces Private AI Compute, a new architecture that achieves cross-device AI persistent memory through cloud-based encrypted storage and device key management, ensuring data privacy. The architecture temporarily decrypts user data in a cloud-isolated environment to process requests and immediately encrypts and stores new contexts, while the device holds the decryption keys. Users can verify the authenticity of server software and audit security protocols, supporting AI in maintaining device-level privacy standards even when processing complex tasks efficiently in the cloud.
Google DeepMindGoogle DeepMind releases Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, supporting the creation of custom character voices from scratch and direct control of scene dialogue.
Liquid AI BlogLiquid AI announced at the Snapdragon Summit 2026 that its device-side context layer, Liquid Context, has been optimized for Snapdragon® processors, specifically using Qualcomm® Hexagon™ NPU.
Cursor ChangelogCursor launches Rollouts and Security Review, two code deployment security Bots. Rollouts monitors the deployment process to report environment health status, and Security Review reports exploitable vulnerabilities in each pull request. Both are now available on Teams and Enterprise plans.
Browser Use6565Browser Use and Browserbase are leading browser intelligence infrastructure options. Browser Use offers a $0.02/hour browser hour rate with 81% stealth success rate, no subscription and supports custom models; Browserbase uses a subscription model with hourly fees of $0.10-0.12 and a stealth success rate of 42% (basic)/70.3% (advanced), but advanced stealth features are only available for paid plans.
OpenAI Agents SDK releases55OpenAI Agents SDK released version v0.22.3, fixes core module conditional approval and validation tool parameter synchronization, tool not found output in server managed session recovery, command path POSIX compatibility on Windows host.
Mistral AIThe Mistral model is now powering Mozilla's AI browsing assistant, Firefox Smart Window (beta), to help users handle complex searches, remember important information, and get information based on browser tabs. It currently serves users in France and North America, with the UK and Germany expected to join later this year.
Cognition BlogDevin Desktop and CLI are now integrated with the Fusion architecture, improving efficiency by up to 39% compared to other code generation frameworks. Fusion allows users to select a cutting-edge model for planning and review ('lead') and a more cost-effective model for execution ('sidekick').
Mistral AICloudera collaborates with Mistral to integrate Mistral models into Cloudera's hybrid data platform, enabling businesses to deploy AI models in private clouds, public clouds, on-premises, and fully isolated environments while maintaining full control; Mistral allows businesses to train AI models with proprietary data in a controlled environment, transforming decades of institutional data into custom AI models while retaining ownership of both data and intelligence.
Cursor ChangelogCursor launches the Projects feature today, supporting the handling of large workloads such as feature development, migration, or full applications, capable of maintaining context across months and automatically assigning tasks to thousands of sub-intelligent agents. The project runs independently in the cloud, synchronizing codebase knowledge and work preferences through shared files, coordinating agents responsible for planning and task allocation. The feature is currently in Beta and is gradually being rolled out to all users starting today.
OpenAI Agents SDK releases1212OpenAI Agents SDK v0.22.2 released, adds support for current image generation tool options, fixes file API symbolic link race condition in sandbox module and compressed response chain reset issue in sessions module, and updates behavior documentation for v0.22.1.
Dify Blog6565Dify has added featured banners and real-time update functions, allowing users to find works more conveniently and give likes, ratings, and text feedback. The market collects nearly 1000 plugins and over 300 templates, supporting the construction of applications on the existing basis. Featured banners display top works and platform updates, and the direct feedback mechanism ensures creators receive feedback on the real-world use experience, forming a closed loop from construction to learning.
Cognition Blog7070Cognition has completed a $200 million Series E funding, Devin intelligent agents collaborate with engineers to improve software engineering efficiency, and have been deployed in top companies such as NVIDIA, GE, and Citi, supporting multiple system integration and automated tasks.
Mastra BlogMastra Factory Beta released, this open-source software factory can now automate 25-35% of PRs and close 50-60% of issues, based on the Mastra infrastructure and changing collaboration processes. It connects GitHub, Linear, and Slack, supports configurable workflows, and each agent works in a sandbox environment. Since the alpha version was launched in July, the aforementioned efficiency improvements have been achieved.
LangChain BlogLangChain has moved MCP support into the main package and upgraded to the FastMCP protocol, enabling stateless interaction, tool list caching, and interruptible extraction features. The new protocol, supported by LangGraph, enables a 98x increase in ChatGPT tool calls, allowing clients to cache tool directories and handle model request parameters. MCPAdapter supports multi-server connections and OAuth 2.1 authentication, enabling servers to be independently configured for authentication and transport layers.
OpenHands BlogThrough eight updates, OpenHands Agent Canvas has made it easier to track agent work, configure more securely, and automate more conveniently, and has launched the Canvas Apps Beta version and new automation runtime stages, supporting running agent work in the correct environment, understanding the execution process, reviewing results, and reusing workflows. The new version has added agent activity indicators, context and cost monitoring, custom app support, and form-based configuration and automation runtime management features for pre-built workflows.
.png&mode=card&exp=1794873600&sig=3d0151be74acba48)
