Skip to content
Agents tracked: 501 Releases (7d): 777 Agent status: no reported issuesSince last limit reset: Claude 10d · Codex 8d For AI agents: Markdown Updated Nov 21, 2026

AI Agent News: Releases, Launches and Usage Jumps, Live · page 27

  1. Release GitHub Releases

    Junie 3874.1 released

    (+2 more releases that day)

  2. Release GitHub Releases

    Langfuse 4.66.0 released

    feat(topics): one gate for Topics visibility; fix(sessions): Don't allow expanding empty reasoning messages; fix(web): disable Owner role selection without ownership permission (+1 more release that day)

  3. Hacker News research.poh.org

    Benchmarking Bot Detection Systems Against Modern AI Agents in 2026

    Study benchmarking bot detection systems against modern AI agents in 2026.

  4. Official AWS Machine Learning

    Discover tools at runtime with AWS Agent Registry

    AWS Agent Registry enables agents to discover and instantiate tools at runtime through semantic search rather than hardcoding, scaling from dozens to hundreds of tools.

  5. Official GitHub Blog

    How 3 Java Champions are using GitHub Copilot for increased productivity

    Three Java Champions describe their use of GitHub Copilot for development acceleration and problem-solving.

  6. Official AWS Machine Learning

    Securing AI agent identity with X.509 PKI on AWS

    Reference architecture for securing multi-agent AI systems using X.509 PKI, cryptographic identity, and MCP tool calls on AWS.

  7. Official AWS Machine Learning

    How Eon built multi-cloud investigation with an MCP Gateway on Amazon Bedrock AgentCore

    Eon replaced per-tool credentials with Amazon Bedrock AgentCore MCP Gateway across AWS, GCP, and Azure, reducing onboarding from two days to two minutes for over 100 developers.

  8. Official AWS Machine Learning

    Build a semantic layer for agentic AI on AWS with Strategy Mosaic and Amazon Bedrock AgentCore

    AWS post describes building a semantic layer for agentic AI on Bedrock AgentCore using Strategy Mosaic, Redshift, Aurora, and an MCP server to expose customer data to Strands agents with row and column security.

  9. Official AWS Machine Learning

    Build a semantic layer for agentic AI on AWS with AtScale and Amazon Bedrock AgentCore

    AWS post describes building a semantic layer for agentic AI on Bedrock AgentCore using AtScale and Redshift, exposing governed customer data to Strands agents through an MCP server with identity propagation and audit.

  10. Release GitHub Releases

    Cloudflare Agents SDK 0.29.0 released

    #2560 8c720d3 Thanks @mattzcarey! - Agent Skills read and write a @cloudflare/computer Workspace, for both projection and skills.runner(). See Upgrading to a Computer workspace.; #2584 3b3a88e Thanks @ben-reitz! - Browser creates and closes its Browser Run…

  11. Release GitHub Releases

    Chatwoot Captain 4.19.0 released

    Automatic conversation translation with Captain or Google Translate. [Enterprise]; Conversation monitors, AI automation conditions, and label and priority suggestions. [Enterprise]; Refreshed Captain reports, Copilot chat history, and low-credit alerts…

  12. Official OpenAI

    Franchisee reconciles cash in 94% less time with ChatGPT Work

    A Schlotzsky's and Cinnabon franchisee used ChatGPT Work to reduce cash reconciliation time by 94% and menu repricing time by 95%, potentially freeing up $100K in cash flow.

  13. Incident Status page

    Legora: Increased errors in loading Legora owned Skills in EU

    Major impact; resolved after 50 min.

  14. Limit reset @thsottiaux on X

    OpenAI Codex: usage limits reset

    Reset usage limits, announced as day 15 of an ongoing series, with the post saying the team is still working on something.

  15. Official Vercel

    DeepSeek V4.1 Flash is now available in Token Pass

    DeepSeek V4.1 Flash model is now available through Vercel's Token Pass subscription alongside other models, accessible to coding agents via AI Gateway.

  16. Official Cursor Changelog

    Agent SDK

    Define an agent as a folder of code, test it with evals, and deploy it to Cursor or your own infrastructure.

  17. Data AgentGid data

    AgentScope downloads up 55% in a week

    47.3K npm and PyPI downloads in the 7 days to Oct 20, against 30.6K the week before.

  18. DataHot AgentGid data

    MCP for Blender (formerly BlenderMCP) downloads up 167% in a week

    595K npm and PyPI downloads in the 7 days to Oct 20, against 223K the week before.

  19. DataHot AgentGid data

    Agent-Reach passes 100K GitHub stars

  20. Data AgentGid data

    OpenMontage passes 70K GitHub stars

  21. DataHot AgentGid data

    Anatomy gained 9,169 GitHub stars in a week

    Now at 17.8K stars.

  22. Data AgentGid data

    Andee gained 1,519 GitHub stars in a week

    Now at 1,615 stars, against about 24 a week over the month before.

  23. Data AgentGid data

    PentAGI gained 3,202 GitHub stars in a week

    Now at 31.6K stars, against about 1,019 a week over the month before.

  24. DataHot AgentGid data

    Solidcraft gained 6,460 GitHub stars in a week

    Now at 8,399 stars.

  25. Official GitHub Changelog

    GitHub Copilot models deprecated on October 19, 2026

    GitHub deprecates certain models across Copilot experiences including Chat, inline edits, ask mode, agent mode, and code completions.

  26. Release GitHub Releases

    Junie 3857.1 released

    (+5 more releases that day)

  27. Official GitHub Blog

    How to continue a GitHub Copilot app session in VS Code

    GitHub Copilot now supports continuing agent sessions from the Copilot app into VS Code while preserving conversation history and code changes.

  28. Release GitHub Releases

    Langfuse 4.64.0 released

    feat(trace): Move messages tab and reuse session timeline; feat(api-keys): enable project API key permissions by default; feat: rename Langfuse Assistant to Halo

  29. Incident Status page

    Bland AI: Inbound calls failing to connect

    Major impact; resolved after 8 min.

  30. Official AWS Machine Learning

    Improve TTFT for multi-turn agentic workloads with bi-directional KV transfer in vLLM

    AWS demonstrates bi-directional KV cache transfer in vLLM reducing time-to-first-token by up to 3.3x for multi-turn agentic workloads by reusing computed context across turns.

  31. Hacker News news.ycombinator.com

    Launch HN: Laminar (YC S24) – RL-trained model that finds errors in agent traces

    Laminar, a Y Combinator S24 company, offers an RL-trained model for identifying errors in agent execution traces.

  32. Hacker News theverge.com

    A hacker broke into John Deere and SharkNinja with an army of AI agents

    A hacker used AI agents to break into John Deere and SharkNinja systems.

  33. Official n8n

    Run your n8n AI workflows on NVIDIA DGX Spark, with no cloud API

    n8n announced integration with NVIDIA DGX Spark to run AI workflows locally without cloud APIs, addressing data privacy concerns for small businesses.

  34. Official Vercel

    Making every harness durable

    Vercel discusses moving coding agent harnesses to the cloud to enable continuous operation without requiring local hardware to remain powered on.

  35. Hacker News crystl.dev

    Tmux and Claude Code: Sessions, Send-Keys, and the Ceiling

  36. Data AgentGid data

    OpenHands downloads down 40% in a week

    125K npm and PyPI downloads in the 7 days to Oct 19, against 210K the week before.

  37. DataHot AgentGid data

    Hermes Agent downloads up 121% in a week

    184K npm and PyPI downloads in the 7 days to Oct 19, against 83.3K the week before.

  38. Data AgentGid data

    mini-SWE-agent downloads up 30% in a week

    4.6M npm and PyPI downloads in the 7 days to Oct 19, against 3.5M the week before.

  39. Data AgentGid data

    GenOffice passes 10K GitHub stars

  40. Data AgentGid data

    Octop passes 10K GitHub stars

This list shows notable items; the sections above show everything of their kind, including patch releases of smaller projects and low-impact incidents. Summaries of outside articles are written automatically from the source's own text and may miss nuance, so follow the link before relying on one.