AI Agent News: Releases, Launches and Usage Jumps, Live · page 2
-
ARTEX passes 10K GitHub stars
-
bb downloads up 72% in a week
35.1K npm downloads in the 7 days to Nov 19, against 20.5K the week before.
-
Claude Code downloads up 26% in a week
21.7M npm downloads in the 7 days to Nov 19, against 17.2M the week before.
-
Corsair downloads up 33% in a week
56.8K npm downloads in the 7 days to Nov 19, against 42.8K the week before.
-
Graphiti downloads up 33% in a week
241K PyPI downloads in the 7 days to Nov 19, against 181K the week before.
-
Haystack downloads up 26% in a week
196K PyPI downloads in the 7 days to Nov 19, against 156K the week before.
-
Linger gained 2,069 GitHub stars in a week
Now at 2,207 stars.
-
Maven AGI downloads up 56% in a week
20.1K npm and PyPI downloads in the 7 days to Nov 19, against 12.8K the week before.
-
Mistral Vibe downloads up 50% in a week
251K PyPI downloads in the 7 days to Nov 19, against 168K the week before.
-
nanobot downloads up 28% in a week
23K PyPI downloads in the 7 days to Nov 19, against 18K the week before.
-
Noetic downloads up 28% in a week
90.7K npm downloads in the 7 days to Nov 19, against 70.9K the week before.
-
Repomix downloads up 26% in a week
157K npm downloads in the 7 days to Nov 19, against 125K the week before.
-
UI gained 3,777 GitHub stars in a week
Now at 6,188 stars.
-
Paperclip 2026.1117.0 released
The built-in Google Workspace connector is off by default. While Paperclip's Google app verification is pending, the unified Google Workspace connection introduced in v2026.1106.0 is gated behind…; Every subtask gets its own execution workspace. Child tasks…
-
Gemini 4 Neon in GitHub Copilot
Google's Gemini 4 Neon model is now generally available in GitHub Copilot, designed for agentic coding and multistep tool use.
-
How Airbnb uses cost per task to operate coding agents on Amazon Bedrock
Airbnb describes how it uses cost per task metrics on Amazon Bedrock to select models for coding agents and control production spending.
-
How Stretto built an AI voice agent with Amazon Nova 2 Sonic
Stretto built Tara, an AI voice agent using Amazon Nova 2 Sonic, to conduct bankruptcy intake interviews and qualify leads over the phone.
-
Launch HN: Maritime (YC F26) – A managed cloud for production AI agents
Maritime, a Y Combinator F26 company, launched a managed cloud platform for production AI agents.
-
Hosted agents in Foundry Agent Service at Ignite 2026: from pilot to production inside your enterprise boundaries
Microsoft Foundry Agent Service adds enterprise deployment features including shared subnet IPs, private CA trust, network egress controls, AKS cluster deployment, resilient execution, memory snapshots, and A2A passthrough.
-
The Foundry Dev Pack is here: build Foundry agents your way
Microsoft Foundry Dev Pack is now generally available, providing developer tools for building Foundry agents in editors, terminals, or with coding agents.
-
What’s new in Foundry Agent Service at Ignite 2026
Microsoft Foundry Agent Service announces updates focused on production execution, context management, tools integration, and runtime reliability at Ignite 2026.
-
Build once, reuse across your agent fleet: Tools and Toolboxes in Foundry
Microsoft Foundry introduces Tools and Toolboxes feature to manage and reuse tools and capabilities across multiple production agents at scale.
-
Show HN: Mastra Factory, the open-source software factory we use to build Mastra
Mastra released an open-source software factory tool used to build the Mastra agent framework.
-
Customize GitHub Copilot for your team
GitHub Copilot now allows sharing team-customized plugins across organization teams without requiring individual setup.
-
AI agents ask better questions than KPMG accountants in audit trial
AI agents outperformed KPMG accountants in questioning during an audit trial, suggesting potential applications in financial analysis.
-
Meta Welcomes Loblaw as First Canadian Retail Partner to Muse
Loblaw becomes the first Canadian retailer to integrate with Meta's Muse personal AI agent through a partner connector.
-
GitHub's agents ported the Copilot runtime to 800,000 lines of Rust for about $120,000 in tokens
GitHub rewrote the agent runtime behind the Copilot CLI, app and SDK from TypeScript on Node.js to Rust, using Copilot's own agents. One engineer steered the work, and the agents wrote most of the code.
-
Mastra 1.84.0 released
Knowledge alpha scope matching changed: $param now matches exactly one segment; raw : is no longer allowed inside a scope segment, requiring canonical encoding via encodeKnowledgeScopeId /…; @mastra/factory: newestOpenPullRequestNumber is no longer exported…
-
[AINews] GPT-6.2 Astra, the #2 Frontier Model is better and 20%-600% cheaper, but has mixed reviews; 6.2 Sol likely main workhorse
OpenAI released GPT-6.2 Astra and Sol models with lower benchmark costs and pricing. Early testers reported mixed experiences with Astra.
-
Dify 1.20.0 released
Reach approvers where they work. Configure email and an IM platform—Slack, Feishu/Lark, Microsoft Teams, DingTalk, or WeCom—to deliver workflow review requests through your team's existing channels.; Manage recipients in Contacts. Sync IM directories and…
-
Inside the Codex sandbox
OpenAI describes how Codex executes commands on machines while enforcing configurable filesystem and network restrictions across macOS, Linux, and Windows.
-
Parallel web search is free on AI Gateway and eve through January 31
Parallel web search is free on AI Gateway through January 31, 2027, and is now the default web search tool for eve agents.
-
LiteLLM 1.110.0 released
fix(gemini)!: answer 400 for an unsupported chat audio format, drop it under drop_params; fix(router): keep encrypted reasoning when a fallback hops between same-key deployments with no api_base; fix(anthropic)!: sync the beta header allowlist with what…
-
OpenAI Agents SDK 0.25.0 released
Migrate Runloop workloads to another supported sandbox provider, such as Modal, or remain on 0.24.0 while migrating. Provider-specific sessions and snapshots require a separate data migration.; Resume nested agent-tool approvals with output guardrails using…
-
Gemini 4 Neon now available on AI Gateway
Gemini 4 Neon is now available on Vercel's AI Gateway, offering improved output quality and speed for coding, agent workflows, and multi-step tasks with a 1M-token context window.
-
AI downloads up 40% in a week
129K npm downloads in the 7 days to Nov 18, against 91.9K the week before.
-
Billion Context downloads up 36% in a week
1.1M npm downloads in the 7 days to Nov 18, against 807K the week before.
-
CLI-Anything passes 60K GitHub stars
-
Context7 downloads up 29% in a week
1.4M npm downloads in the 7 days to Nov 18, against 1.1M the week before.
-
Crawl4AI downloads up 25% in a week
468K PyPI downloads in the 7 days to Nov 18, against 373K the week before.
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.