agentic coding

Alibaba's agentic coding platform Qoder now ships builds for Linux ARM64 and Loongson's LoongArch64 instruction set. It has also been adapted for UnionTech UOS Desktop V20 and Galaxy Kylin Desktop V10, with both the international and China editions updated on October 23.

Reflection AI has released Beam 1.0, an open-weight sparse mixture-of-experts model with 501 billion total and 23 billion active parameters, built for agentic coding. Weights ship under Apache 2.0 on Hugging Face, and the model is available through Amazon SageMaker JumpStart in two US regions.

Google DeepMind has released Gemini 4 Argon, its latest frontier model, globally via the API at an introductory $2 per 1M input tokens and $10 per 1M output tokens. Google claims it ranks #1 on the Vals Index. Context window, parameter count and training cutoff were not disclosed in the announcement.

OpenAI has released GPT-6.1 Sol, an incremental upgrade to GPT-6 Sol positioned below flagship GPT-6 Astra in its GPT-6 lineup. The model features a 1.1M token context window, priced at $2 per 1M input tokens and $10 per 1M output tokens, with claimed improvements in factual accuracy and instruction-following on agentic tasks.

Kilo Code released version 7.1.9-rc.1 of its JetBrains plugin, a pre-release patch that adds automatic conversation compacting when providers hit context limits, renders agent board messages as Markdown, and unifies goal scheduling for long-running agent tasks.

Anthropic has released Sonnet 5.5, the latest version of its mid-tier Claude model, claiming 30% faster performance and significantly lower token costs than its predecessor. The company says the model now outperforms Opus 5.5 on agentic coding tasks and carries cyber capabilities comparable to Opus 5.

GitHub has introduced local sandboxing in the GitHub Copilot app, a configurable feature that limits access to files, network resources, and credentials on a user's machine. The change targets risk reduction from unintended or unexpected command execution during agentic coding sessions.

GitHub used its own Copilot agent to help migrate the Copilot runtime to Rust, producing roughly 800,000 lines of production code. The company says the scale of the rewrite would not have been feasible without agentic coding assistance.

A stealth model called Ox Alpha has appeared on OpenRouter, offering a 1 million token context window at no cost during its preview period. The model's developer remains anonymous, and OpenRouter says it is acting only as a router, not the model's owner or provider.

ByteDance Seed has released Seed-2.0-Code, a model optimized for agentic coding workflows with a 262K token context window. The model accepts text, image, and video input and is priced at $0.50 per million input tokens and $3.00 per million output tokens.

GitHub has added stacked sessions and pull requests to the GitHub Copilot app, allowing developers to break large coding tasks into a sequence of dependent Copilot sessions that each produce their own PR. GitHub demonstrated the feature by using it to modernize an old codebase.

Anthropic's Claude Opus 5 is now available on Amazon Bedrock and Claude Platform on AWS, marking the first release in the company's fifth-generation Opus line. Anthropic claims the model matches its top-tier Claude Fable 5 intelligence at Opus-tier pricing, though specific pricing and benchmark figures remain undisclosed.

OpenAI released GPT-5.6 Sol, Terra, and Luna models broadly on Thursday following initial limited deployment. CEO Sam Altman told CNBC the Sol model achieves 54% greater token efficiency on agentic coding tasks compared to previous versions.

Apple's Xcode 27 adds native support for Google Gemini, joining existing integrations with Anthropic's Claude and OpenAI's Codex. The update also introduces improved interfaces, interactive planning, and multiturn Q&A capabilities for AI-assisted development.

OpenAI released GPT-5.5 on April 23, 2026, seven weeks after GPT-5.4. The model features a 400K context window in Codex and claims improvements in multi-step tasks, agentic coding, and computer use, though at higher pricing than its predecessor.