AI Agent News: Releases, Launches and Usage Jumps, Live · page 7
-
Day Trader Skill gained 1,845 GitHub stars in a week
Now at 7,657 stars.
-
Learnharness gained 3,456 GitHub stars in a week
Now at 9,297 stars.
-
Oh My Pi 18.20.0 released
prepareCompaction() runs as the compaction.prepare loop phase, so a ui.loop-blocked stall from a cold token walk over a long branch names compaction instead of "unknown"; Added the google-decisions judgment API for Google's Gemini Decisions API…
-
agent-browser 0.43.0 released
Added snapshot hints for controls whose accessible name is empty or shared with another ref in the same snapshot.; Added a Modern Web Guidance skill that retrieves Chrome's guidance for a task and checks the built page in agent-browser; Fixed commands on…
-
Build once, run on any agent: A practical guide to agent skills
GitHub published guidance on agent skills as reusable, reviewable code that can run across different agent platforms while keeping tools and permissions host-specific.
-
Strands Agents 0.4.0 released
feat(site): add /frogs page (9b38e2e9c); feat(context)!: offload conditions decide granularity (typescript) (50a391e05); feat(mcp): add find_integrations tool backed by the catalog feed (085d4de61) (+2 more releases that day)
-
OpenAI Codex: a usage-limit reset to apply yourself
Activated a banked reset that was expected to land in everyone's accounts soon, after shipping some updates to dots.
-
How Natera designed an agentic AI system for lab ops with Amazon Bedrock AgentCore
Natera built SWARM, an agentic AI system on Amazon Bedrock AgentCore for lab operations, achieving 130x faster first response and 96.2% automated coverage on support tickets.
-
Fin: Delays in outbound email delivery
Major impact; resolved after 21 h 19 min.
-
Kimi K3.1 Pro is now available in Token Pass
Kimi K3.1 Pro, a model for coding and agentic workflows with vision and tool use, is now available in Vercel's Token Pass subscription at $30 per month for $80 in credits.
-
Cursor: Elevated errors for some requests
Major impact; resolved after 1 h 31 min.
-
Optimizing cost per task and proving agent ROI on Amazon Bedrock
AWS post explains how to calculate true cost per task for agents on Bedrock and reduce it through caching, routing, and output constraints.
-
Building a self-service LLM gateway with Amazon Bedrock and LiteLLM
Guide to building an OpenAI-compatible LLM gateway using LiteLLM on AWS Fargate with Amazon Bedrock foundation models, including cost controls and quota management.
-
Qualified Piper: Degraded Performance: Microsoft Calendar Integrations
Major impact; resolved after 51 h 3 min.
-
Show HN: AgentRun – open-source, Self-improving Managed Agents
AgentRun is an open-source platform for managed agents with self-improving capabilities.
-
Run agents securely and efficiently with the next generation AgentCore runtime
Amazon Bedrock's next-generation AgentCore runtime now offers hardware-isolated sessions, faster starts, more compute capacity, and usage-based billing for running multi-step AI agent workloads.
-
Claude Cowork: Elevated errors affecting the Microsoft 365 connector
Major impact; resolved after 27 h 56 min.
-
Claude Design: Elevated errors affecting the Microsoft 365 connector
Major impact; resolved after 27 h 56 min.
-
Claude in Chrome: Elevated errors affecting the Microsoft 365 connector
Major impact; resolved after 27 h 56 min.
-
Hebbia: Increase error rates for some single tenants
Major impact; resolved after 15 min.
-
Migrate to Amazon Bedrock Managed Knowledge Base with your coding agent
AWS published a migration guide for moving customer-managed Amazon Bedrock knowledge bases to Managed Knowledge Base, with a coding agent automating discovery, creation, and validation steps.
-
Build composable, interoperable multi-agent systems with A2A on AWS
AWS demonstrates a multi-agent system using the Agent-to-Agent (A2A) protocol, with a LangChain orchestrator on ECS communicating with a Strands agent on Bedrock AgentCore via OAuth-authenticated calls.
-
From prototype to production: Engineering agents with Agent DLC
AWS introduces Agent DLC, a framework addressing measurement and evaluation challenges in moving agents from prototype to production, using a standardized lifecycle and explicit metrics for judging changes.
-
Langfuse 4.79.0 released
feat(ai-gateway): add OpenRouter as a pre-release gateway provider; feat: add SUBSTITUTE_OK no-data mode for monitors; feat(ai-gateway): add xAI as a pre-release gateway provider
-
Context7 4.7.0 released
MCP Bundle for @upstash/context7-mcp@4.7.0 (+4 more releases that day)
-
Rea 6.9.0 released
Build and test desktop tasks from recorded application state, including downloaded Linux apps, reusable build computers and multiple tasks per capture.; Inspect more shipped artifacts offline: standalone application bundles, embedded firmware, NTFS…
-
WTF are evals? How to test agents and the software they use
Article explains evaluation frameworks for testing AI agents and the software they interact with, covering discovery, selection and access patterns.
-
Build autonomous AI agents with Amazon Bedrock and Spring AI
AWS blog post on building autonomous AI agents with Amazon Bedrock and Spring AI, covering tool calling, memory, resilience, and multi-agent orchestration for Java developers.
-
Gemini 4 Hydrogen now available on AI Gateway
Google Gemini 4 Hydrogen model is now available on Vercel's AI Gateway, improving agentic coding, tool use and handling longer tasks in fewer steps.
-
Inkling 2 Small now available on AI Gateway
Inkling 2 Small from Thinking Machines is now available on AI Gateway. The multimodal reasoning model supports coding agents, visual understanding, and professional knowledge work, with text and…
-
agent-browser passes 50K GitHub stars
-
AgentScope downloads up 83% in a week
141K PyPI downloads in the 7 days to Nov 12, against 77.3K the week before.
-
Andee gained 2,410 GitHub stars in a week
Now at 6,028 stars, against about 904 a week over the month before.
-
bb downloads up 70% in a week
20.5K npm downloads in the 7 days to Nov 12, against 12K the week before.
-
Browser Use downloads up 26% in a week
2.2M npm and PyPI downloads in the 7 days to Nov 12, against 1.7M the week before.
-
Corsair downloads up 29% in a week
42.8K npm downloads in the 7 days to Nov 12, against 33.2K the week before.
-
Mistral Vibe downloads down 69% in a week
168K PyPI downloads in the 7 days to Nov 12, against 541K the week before.
-
nanobot passes 50K GitHub stars
-
OpenClaw downloads up 26% in a week
3.1M npm downloads in the 7 days to Nov 12, against 2.5M the week before.
-
OpenHands downloads up 146% in a week
86.6K PyPI downloads in the 7 days to Nov 12, against 35.2K 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.