All posts in the series

Post 5 of 8Live

AI agents: news from primary sources

A live digest: releases of Claude Code, Codex, Cursor, the MCP specification and agent frameworks. Collected from official blogs, changelogs and GitHub releases, every note links to the primary source.

Alexandr Mihalkevich · Fact-checked October 5, 2026

AI agents: what’s new
Where the news comes from: Primary sources → Checked every 15 minutes → A short note
Why agent governance starts with observability
OpenAI Codex CLI 0.171.0
Use Kimi Code CLI with models on Amazon Bedrock
Enable AI agents to pay for AWS Marketplace x402 products with Amazon Bedrock AgentCore payments
Amazon Bedrock AgentCore harness adds Strands harness defaults, built-in tools, and lifecycle hooks
How to read agent news: Open the source, check the date and version; Preview, beta or generally available?; Do the defaults change?; Are permissions, model or limits affected?; Try it on your task before adopting
The full feed is on the site
Slide 1 of 9

Agent tools change every week: new permission modes, configuration formats, protocol versions. This page is a live digest. Below are the latest notes on releases and changes in agent tooling. They are collected by our news feed: it checks primary sources every 15 minutes and writes a short note with a link to the original.

What goes into the digest

Notes from the “Agents” and “Developer tools” topics:

How to read agent news

A piece of tool news matters not in itself but for what it changes in your work. Before you upgrade or rebuild your process:

  1. Open the primary source. Check the date, the version number and the exact wording. Retellings lose the caveats.
  2. Tell the statuses apart. “Research preview,” “beta,” “experimental, off by default” and “generally available” are different things. For example, agent teams in Claude Code are marked experimental and are off by default.
  3. Look for changes to default behavior. The most important news is what changes the starting permission mode, the default model, limits or the configuration format. It is easy to miss, and the consequences show up immediately.
  4. Test it on your own task. Run the updated agent through your task set before changing the process for the whole team. How to build such a set is covered in the first post.

Where to follow it yourself

If you want to get changes directly, subscribe to repository releases on GitHub (Watch → Custom → Releases) and to the official changelogs. Our feed collects the same things in one place and writes a short summary in Russian.

Latest news

  1. Why agent governance starts with observability

    A strong AI agent governance strategy

    LangChain · November 20

  2. OpenAI Codex CLI 0.171.0

    New Features Added GPT-6.2 Sol and Astra to model catalogs, with Sol as the default catalog selection. ( #62106 ) Enabled the TUI workspace by default, with searchable document previews, image previews, and subagent transcripts alongside the main conversation.

    OpenAI Codex CLI · November 20

  3. Use Kimi Code CLI with models on Amazon Bedrock

    Kimi Code CLI v2.7.0 adds a native Amazon Bedrock provider, so you can connect the open source coding agent to models like Kimi K3.1 Pro using your standard AWS credential chain (named profiles or SSO) instead of a separate API key.

    AWS Machine Learning · November 20

  4. Enable AI agents to pay for AWS Marketplace x402 products with Amazon Bedrock AgentCore payments

    Amazon Bedrock AgentCore payments now supports AWS Marketplace, so agents can discover and buy x402-enabled products, APIs, data, and content and pay in USD on the developer's AWS bill, with no stablecoin wallets or API keys.

    AWS Machine Learning · November 19

  5. Amazon Bedrock AgentCore harness adds Strands harness defaults, built-in tools, and lifecycle hooks

    Amazon Bedrock AgentCore harness now runs on the open-source Strands harness, bringing a recommended model, task-oriented defaults, automatic prompt caching, proactive context management, and new built-in tools.

    AWS Machine Learning · November 19

  6. Introducing Tool Retrieval in the Gemini API

    Give your agents access to hundreds of tools while using fewer tokens with Tool Retrieval, now in preview in the Gemini API.

    Google AI · November 19

  7. Let Gemini tackle repetitive chores on your Mac

    The Gemini app for Mac now has computer use to help you with repetitive tasks.

    Google Gemini · November 19

  8. Build Tool-Calling Parsers in Rust with AI Agents

    A tool call can arrive in pieces, an argument can be cut short, or model-specific markup can leak into the answer. A frontend parser turns that output, received...

    NVIDIA Developer · November 19

Terms in this post

Sources

  1. Claude Code — релизы на GitHub
  2. OpenAI Codex CLI — релизы на GitHub
  3. Cursor — Changelog
  4. Model Context Protocol — блог
  5. MCP specification — релизы
ShareTelegramXLinkedIn

Practise this for real

In the school's simulators an agent does the task, and you learn to set it, check it and never trust it blindly.

Open simulators