01Updates
v2.1.248
What's changed Added --restricted (or CLAUDE_CODE_RESTRICTED=1 ): removes the built-in tools that run commands or code and WebFetch (unless named in --tools ).
The Anthropic Claude Code Releases release records v2.1.248 for Anthropic.
Anthropic added control-plane detail for v2.1.248; enterprise adoption depends on permissions, auditability, and data boundaries. Metric cue: v2.1.248.
- Watch next
- Watch admin controls, audit logs, default permissions.
02Updates
OpenAI Codex documents how banked usage resets work
The official page explains that a banked reset is a one-time Codex usage-limit reset saved until use or expiration.
The OpenAI Codex Banked Reset Guidance page documents the OpenAI Codex update.
For developers using OpenAI Codex, test The official page explains that a banked reset is a one-time Codex usage-limit reset saved against an existing repository and review workflow before rollout.
- Watch next
- Watch the OpenAI Codex release for patch notes and rollout issues.
03Updates
Cursor updates Start from scratch, without a repo
Cloud Agents now work without a connected repo, plus live preview and Vercel publishing.
The Cursor Changelog release records preview for Cursor.
Teams evaluating Cursor Cloud Agents can test how Cursor updates Start from scratch, without a repo changes the documented workflow.
- Watch next
- Watch the Cursor release for patch notes and rollout issues.
04Updates
Cursor is now available in the AI SDK harness layer
The AI SDK harness layer now supports Cursor through the official @ai-sdk/harness-cursor adapter. The harness layer lets your application run different coding agents.
The Vercel Changelog release records now available for Cursor.
Developers evaluating Cursor SDK can compare compatibility and migration impact before updating integrations.
- Watch next
- Watch supported plans, rollout notes, rate limits.
05Updates
Experiment with Qwen3.8-Flash-Next on NVIDIA GB300 NVL72 for Agentic Coding
Alibaba released the model weights for Qwen3.8-Flash-Next as a preview of the upcoming Qwen4 architecture for developers to experiment with and evaluate. It's.
The NVIDIA AI Blog release records preview for Qwen.
Teams evaluating Qwen preview can compare its documented input scope, limits, and deployment fit.
- Watch next
- Watch reproducible benchmark details, dataset coverage.
06Updates
Release v0.22.2-nightly.20260828.7357136dd1
What's Changed fix(web-shell): restore saved session diffs by @ytahdn in #10093 fix(channels): preserve DingTalk rich-text multi-image messages by @BenGuanRan in #9922.
The Qwen Code Releases release records v0.22.2 for Qwen.
Teams evaluating Qwen Nightly nightly.20260828 can test how Release v0.22.2-nightly.20260828.7357136dd1 changes the documented workflow.
- Watch next
- Watch the Qwen release for patch notes and rollout issues.
07Updates
arXiv updates From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench
In real world software development, code review typically involves iterative interactions between developers and reviewers to improve software quality, making the process costly.
The arXiv Coding-Agent Research page documents the arXiv update.
Teams evaluating arXiv Code Review rules can test how arXiv updates From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench changes the documented workflow.
- Watch next
- Watch final pricing, quotas, billing edge cases.
08Updates
arXiv updates RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution
LLM based agents are increasingly deployed in product level execution harnesses, where jailbreaks can trigger harmful tool use and persistent state changes, creating greater.
The arXiv Coding-Agent Research page documents the arXiv update.
Teams evaluating arXiv Agent can test how arXiv updates RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution changes the documented workflow.
- Watch next
- Watch the arXiv release for patch notes and rollout issues.
09Updates
Vercel updates Run Claude Managed Agents with Chat SDK
Vercel updates Run Claude Managed Agents with Chat SDK.
The Vercel Changelog page documents the Vercel update.
Developers evaluating Vercel SDK can compare compatibility and migration impact before updating integrations.
- Watch next
- Watch the Vercel release for patch notes and rollout issues.
10Updates
Muse-Glimmer-30B and Qwen 3.8-27B models now available on Amazon SageMaker JumpStart
Meta's Muse-Glimmer-30B and Alibaba's Qwen 3.8-27B models are now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers.
The AWS What's New release records 3.8 for Qwen.
Teams evaluating Qwen 3.8-27B can compare its documented input scope, limits, and deployment fit.
- Watch next
- Watch supported plans, rollout notes, rate limits.
11Updates
arXiv updates WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution
arXiv updates WikiSkill: Compiling Agent Experience into Persistent Knowledge for Skill Evolution.
The arXiv Coding-Agent Research page documents the arXiv update.
arXiv pushed arXiv updates WikiSkill: Compiling Agent Experience into Persistent deeper into agent workflows; the watch is whether it reduces manual handoff or creates new supervision needs.
- Watch next
- Watch the arXiv release for patch notes and rollout issues.
12Updates
Gemini CLI publishes Release v0.59.0-nightly.20260828.g3c311beac
Gemini CLI publishes Release v0.59.0-nightly.20260828.g3c311beac.
The Gemini CLI release records v0.59.0 for Gemini CLI.
Developers can test Gemini CLI Nightly nightly.20260828 against their current workflow before rollout.
- Watch next
- Check Gemini CLI nightly comparison and release notes.
13Updates
Introducing OpenAI models on Amazon Bedrock for in-country inferencing in India
Amazon Bedrock now supports the OpenAI GPT-5.6 models, Terra and Luna, in India with India geographic cross-Region inference. If you have local data processing requirements.
The source records 5.6 / GPT-5.
Teams evaluating OpenAI 5.6 can compare its documented input scope, limits, and deployment fit.
- Watch next
- Watch access tiers, latency, pricing, benchmark updates.
14Updates
LangChain releases 1.3.18
The pypi registry records LangChain version 1.3.18.
The PYPI LangChain release records 1.3.18 for LangChain.
Developers evaluating LangChain 1.3.18 can compare compatibility and migration impact before updating integrations.
- Watch next
- Watch the LangChain release for patch notes and rollout issues.
15Updates
vLLM updates v0.28.1rc0
[Tools][Recipes] Improve sweep recommendations and short alias parsin.
The vLLM Releases release records v0.28 for vLLM.
Teams evaluating vLLM v0.28.1rc0 can test how vLLM updates v0.28.1rc0 changes the documented workflow.
- Watch next
- Watch the vLLM release for patch notes and rollout issues.
16Updates
Remotion Renderer releases 4.0.518
The npm registry records Remotion Renderer version 4.0.518.
The NPM Remotion Renderer release records 4.0.518 for Remotion.
Developers evaluating Remotion 4.0.518 can compare compatibility and migration impact before updating integrations.
- Watch next
- Watch the Remotion release for patch notes and rollout issues.
17Updates
Cosmos3-Edge, Cosmos3-Nano, and Cosmos3-Super models now available on Amazon SageMaker JumpStart
NVIDIA's Cosmos3-Edge, Cosmos3-Nano, and Cosmos3-Super models are now available on Amazon SageMaker JumpStart.
The AWS What's New release records now available for AWS.
Teams evaluating AWS now available can compare its documented input scope, limits, and deployment fit.
- Watch next
- Watch supported plans, rollout notes, rate limits.
18Updates
Ollama updates v0.33.2
app: restore system dark mode by @hoyyeva in 18049 proxy: continue requests when the model catalog changes by @ParthSareen in 18058 app: synchronize macOS app handoff.
The Ollama Releases release records v0.33.2 for Ollama.
Teams evaluating Ollama v0.33.2 can compare its documented input scope, limits, and deployment fit.
- Watch next
- Watch access tiers, latency, pricing, benchmark updates.
19Updates
OpenHands updates v1.16.0
1.16.0 (2026 08 27) Changed: Features feat(settings): select supported LLM providers by @keeltrace in 16772 feat: add linux desktop installer build (CI and deb maintainer fix).
The OpenHands Releases release records v1.16.0 / 1.16.0 for OpenHands.
Teams evaluating OpenHands v1.16.0 can test how OpenHands updates v1.16.0 changes the documented workflow.
- Watch next
- Watch the OpenHands release for patch notes and rollout issues.
20Updates
arXiv updates SWE-Prime: Fewer Trajectories, Better Performance
To improve large language models' ability to resolve real world software issues, prior work has focused on constructing large scale agent trajectory datasets and performing.
The arXiv Coding-Agent Research page documents the arXiv update.
Teams evaluating arXiv agent can compare its documented input scope, limits, and deployment fit.
- Watch next
- Watch access tiers, latency, pricing, benchmark updates.
21Updates
OpenAI Codex publishes 0.151.0-alpha.8
OpenAI Codex publishes 0.151.0-alpha.8.
The OpenAI Codex release records 0.151.0 for OpenAI Codex.
developers should test it against a stable repository workflow before rollout. Metric cue: 0.151.0.
- Watch next
- Watch the OpenAI Codex release for patch notes and rollout issues.
22Updates
Vercel updates Hy4 Preview now available on AI Gateway
Hy4 Preview from Tencent is now available on AI Gateway.
The Vercel Changelog release records Preview for Vercel.
the source details the configuration and rollout limits that determine who can use it.
- Watch next
- Watch supported plans, rollout notes, rate limits.
23Updates
Anthropic Python SDK publishes v1.2.0
1.2.0 (2026 08 27) Changelog: v1.1.0.v1.2.0 Features api: beta files/skills namespaces use GA shapes; drop dated beta header pins (9df4565) Bug Fixes aws.
The Anthropic Python SDK release records v1.2.0 / 1.2.0 for Anthropic Python SDK.
Developers evaluating Anthropic Python SDK v1.2.0 can compare compatibility and migration impact before updating integrations.
- Watch next
- Watch supported plans, rollout notes, rate limits.