Search “GitHub”

Anthropic donates Agent Skills to the Agentic AI Foundation

Anthropic announced that it will donate Agent Skills to the Agentic AI Foundation (AAIF). According to its first-party information, MCP had previously also been donated to the same foundation; since December 2025, more than 70 agent platforms have adopted the standard, including ChatGPT, Cursor, GitHub Copilot, and VS Code. Subsequent reports stated that AAIF, under the Linux Foundation, announced on October 22, 2026 that it had accepted four projects: in addition to Anthropic's Agent Skills, these include OpenAI's Open Responses, Hugging Face's OpenEnv, and Alibaba's OpenSandbox; Agent Skills is a universal format that allows different agents to reuse business knowledge and workflows, and Anthropic made it public as an open standard in December 2025. Reports also stated that the donation includes the name, logo, the GitHub organization account agentskills, and the agentskills.io domain; going forward, a technical operations committee composed of core maintainers from multiple organizations will decide the development direction, with Anthropic's David Soria Parra and Mahesh Murag serving as lead maintainers; the number of projects under AAIF has grown from three at its founding to ten.

Ai2 releases PLANTEUR, a benchmark for tropical crop mapping

Ai2 releases PLANTEUR, a benchmark for tropical crop mapping. The benchmark extends the PASTIS benchmark to six tropical regions—Réunion, Guadeloupe, Martinique, French Guiana, Mayotte, and Saint-Martin—and includes 2,750 aligned time series from Sentinel-2, Sentinel-1, and Landsat-8, as well as parcel labels covering 7 crop types across 4,506 km2. Ai2 says all evaluated methods score significantly lower on PLANTEUR than on PASTIS, and that each model's accuracy drops by about half when tested on small islands it never saw during training. PLANTEUR is open on Hugging Face and GitHub. There are no follow-up developments at present.

Aravind Srinivas announces Computer credits for checking PHP vulnerabilities

Aravind Srinivas announced that checking PHP vulnerabilities using Perplexity's Computer earns Computer credits. The relevant skill PHP2Shell is now live; it can check PHP sites and GitHub deployment configurations for exposure risks and prioritize fixes. The quoted post states that it is free until October 31, with up to 5,000 credits per user. There are no further developments at this time.

Peter Yang releases the /video-short skill

On October 22, 2026, Peter Yang released the free AI skill /video-short. This skill can turn raw single-person recording footage into a polished short video, automatically adding B-roll, motion graphics, subtitles, AI video, and music, and can be used with commonly used AI agents; it is now freely available on GitHub. A report the same day mentioned that the skill includes a built-in review page where users can pause on a frame and leave comments for the AI to correct; the agent applies each piece of feedback before loading the next draft. Peter Yang described this as being like Google Docs comments for video, and provided a free GitHub access link and tutorial.

iX-Workshop launches Agentic Engineering course

On October 22, 2026, iX-Workshop launched the online workshop "Agentic Engineering statt Vibe Coding." According to heise online, the course explains how to integrate coding agents into a controllable development process using GitHub Copilot, Spec-Driven Development, and TDD—from requirements specifications and acceptance criteria to technical planning—demonstrating agents executing tasks and verifying results with tests, while comparing the workload with and without agent support. The workshop is led by Microsoft MVP Gregor Biswanger, limited to 16 participants, and runs from 09:00 to 17:00. There are currently no subsequent developments.

Microsoft Report Says Storm-0940 Used AI Agent Artex to Launch Cyberattacks

Microsoft released a report stating that the China-linked actor Storm-0940 used the open-source AI agent ARTEX to automate attacks against hundreds of organizations across different industries worldwide. The report notes that ARTEX was released as open source on GitHub and chains together multiple LLM agents, requiring almost no human intervention from reconnaissance to data theft; it uses ConnectWise's Microsoft 365 backup and management application keys to log in, bypassing user login and MFA, and in several intrusions it achieved cloud privileged access from the initial target in under 3 hours. The report also notes that most attack attempts failed, including one password spray that logged 151K+ failures with none succeeding, and that application login alone does not prove data was stolen. There are currently no further developments.

Nadella's shareholder letter proposes matching token costs to business outcomes

On October 22, 2026, Microsoft CEO Satya Nadella proposed building a frontier ecosystem in the 2026 annual shareholder letter, and put forward "cost-to-outcome" (the business outcomes obtained per unit of token spending) as a new software economics optimization metric. The letter also disclosed that Microsoft's fiscal 2026 revenue was $331.8 billion, up 18% year over year; Azure grew 41% and surpassed $100 billion for the first time; M365 Copilot paid seats exceeded 30 million, and GitHub Copilot users reached 50 million. The letter also stated that interaction is shifting from synchronous chat to asynchronous agents, with Harness separated from models; Foundry offers more than 11,000 models and has over 100,000 customers, and Microsoft Frontier Co. was established, dispatching 6,000 experts to work on-site. Currently, the content of this letter is reported by a single source, with no subsequent independent developments yet.

Claude Code fixes the not-logged-in error for claude -p in cloud sessions

Claude Code fixed an issue in cloud sessions where claude -p incorrectly reported "Not logged in" when the session environment variables were not loaded. The fix was released with Claude Code v2.1.306, and the related notes were provided by Claude Code's GitHub Releases on October 21, 2026. The same version also fixed another issue: when there were many MCP tools, API errors in the session were replaced with "prompt is too long," triggering unnecessary compaction. There are currently no subsequent developments; the status is based on the release notes for that version.

Microsoft releases multiple new cloud sovereignty tools

On October 21, 2026, Microsoft announced multiple new digital sovereignty features for its cloud services at the Frontier Tour in Paris. Microsoft CEO Satya Nadella and cloud business head Douglas Phillips jointly unveiled a modular cloud sovereignty solution that lets enterprises decide for each computing task the degree of control, transparency, and local execution. A new Sovereign Control Panel aggregates Azure sovereignty signals and will gradually roll out Data Guardian and the Production Touch Ledger, which records remote operations by Microsoft engineers. Azure Managed HSM external key management is now generally available, and on the Azure Local side, DocumentDB, Blob Storage, GitHub Enterprise Local, and Foundry Local have been added. The German Informatics Society (GI) and others criticized such solutions as merely surface-level add-on controls, with the underlying software stack still controlled by U.S. vendors. There have been no further developments so far.

Cloudflare launches Cloudflare OS managed service

Cloudflare has announced a managed service for its AI business platform Cloudflare OS, with a waitlist now open for registration. Cloudflare OS was open-sourced in August this year and can be deployed in Cloudflare environments, on-premises, or in the cloud. It supports integration with Cloudflare Workers AI as well as AI services from Anthropic, OpenAI, Google, and others, and has the ability to securely access enterprises' internal data. This release also adds two new features: first, connecting GitHub repositories, allowing AI agents to add features, debug, view PRs, create commits, and push code based on repository code; second, enhanced Google Workspace integration, enabling agents to read and search Gmail conversations, draft and send emails, and connect to Google Drive, Docs, and Sheets.

Aerial offers Agent-based automatic deployment to replace the TV's default launcher

Aerial is a tool that can replace the default launcher on Chinese smart TVs without root, and its deployment is completed automatically with the help of an Agent. According to an October 22, 2026 report by Huxiu, users connect the TV and computer to the same WiFi, enable ADB and find the TV's IP address, then copy the prompt from the Aerial official website and hand it to an Agent such as Doubao or WorkBuddy to execute; they only need to allow USB debugging in the pop-up on the TV, and the whole process takes about five minutes. The tool uses a "launcher guard" to cover the original launcher when it is woken up, and leverages Android notification listening to revive within 0.5 seconds after standby cleanup, so home-screen ads disappear, but boot ads still cannot be blocked. The report says that everything from the code and APK to the official website was produced through AI Vibe Coding; it gained more than 200 stars on GitHub within one day of launch, and subsequently added features such as icon hiding and adding signal input sources to the home page, and was adapted to multiple TV models.

MiniCPM-V 4.7 achieves 20.51 tokens/s decoding on iPhone 18 Pro Max

ModelBest's MiniCPM-V 4.7 achieves an average decoding speed of 20.51 tokens/sec on iPhone 18 Pro Max (12GB), a 6.07x speedup over the unoptimized SSD expert-loading baseline on the same device. This speed comes from Lookahead Expert Scheduling (LES), optimized expert loading, fine-grained quantization, and DSpark speculative decoding. Follow-up reports further explain that the approach prefetches experts likely needed by the next layer via cross-layer routing prediction, loads remaining experts in parallel, and performs contiguous storage reordering and layer-wise mixed-precision quantization of expert weights, together with DSpark speculative sampling; the model is a MoE architecture with 35B total parameters and 3B activated per token, with the original model architecture and expert routing unchanged and no additional training required. The model is open-sourced on GitHub and Hugging Face.

English translation is being prepared.

Amazon launches the TorchNeuron open-source toolkit

On October 19, 2026, Amazon launched the TorchNeuron open-source toolkit, making AWS Trainium a standard PyTorch device. According to the PyTorch blog, this native backend lets model code run simply by changing it to .to('neuron'); it is built on the PrivateUse1 and torch.accelerator extension points, supports eager, adaptive eager, and torch.compile, and covers distributed APIs such as DDP, FSDP2, and tensor parallelism as well as NKI custom operators; the company says it has conducted coverage testing on 100,000 Hugging Face models and plans to open a public beta on October 20 under the Apache 2.0 license at github.com/aws-neuron/torch-neuronx. Hugging Face released an introduction the same day stating that the plugin supports eager mode, torch.compile, and distributed interfaces such as FSDP2 and DTensor, that the public beta begins October 20 and can be installed via pip install torch-neuronx, and that Transformers, Diffusers, Accelerate, PEFT, and TRL can run directly on Trainium without going through Optimum Neuron; in text generation, the first 1

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

English translation is being prepared.

The author comments that REA is essentially an engineering wrapper that chains Ghidra with large models

On October 21, 2026, Ayi AI Notes published an article offering the judgment: the open-source project REA (Reverse Engineer Anything), which has gone viral on GitHub, has not invented a new reverse-engineering algorithm; it essentially receives instructions in the terminal, automatically invokes Ghidra and the file command to decompile into pseudocode, and then lets a large model explain the logic in natural language—an engineering wrapper that strings old tools into an SOP workflow. The author points out that the decompiled variable names may appear to match up, but they are actually blind guesses by the model based on programming habits; the smoother the report, the easier it is to mistake guesses for facts, and using it for security audits carries hallucination risks; the official protocol limits it to research on software one owns or is authorized to use. The author also believes that this kind of wrapper still has reference value for beginners. At present, this judgment appears only in this source, and there are no subsequent developments or facts.