AI Agent News: Releases, Launches and Usage Jumps, Live · page 19
-
OpenCode downloads up 30% in a week
5M npm downloads in the 7 days to Oct 29, against 3.8M the week before.
-
OpenHands downloads up 88% in a week
83.5K PyPI downloads in the 7 days to Oct 29, against 44.5K the week before.
-
PI Mcp Extension downloads up 127% in a week
460K npm downloads in the 7 days to Oct 29, against 203K the week before.
-
Qwen Code downloads up 37% in a week
115K npm downloads in the 7 days to Oct 29, against 84.2K the week before.
-
TesterArmy e2e downloads up 26% in a week
587K npm downloads in the 7 days to Oct 29, against 466K the week before.
-
VoltAgent downloads up 29% in a week
48.6K npm downloads in the 7 days to Oct 29, against 37.7K the week before.
-
MemPalace passes 60K GitHub stars
-
Ruflo passes 80K GitHub stars
-
Anatomy gained 3,449 GitHub stars in a week
Now at 22.7K stars.
-
AutoSwarm-Shadow-Adapter gained 1,737 GitHub stars in a week
Now at 4,502 stars, against about 661 a week over the month before.
-
OpenMausBot gained 2,246 GitHub stars in a week
Now at 7,664 stars, against about 481 a week over the month before.
-
Solidcraft gained 2,727 GitHub stars in a week
Now at 12.1K stars.
-
Cursor: Multiple services degraded
Major impact; resolved after 1 h 58 min.
-
Lyro: Webhook events not being delivered
Major impact; not marked resolved yet.
-
Why Agents Love Supabase
Podcast episode discussing Supabase as a backend platform for AI agents.
-
Botpress: Botpress platform is unavailable
Critical impact; resolved after 34 min.
-
Building an Agentic AI Platform on Amazon Bedrock AgentCore
AWS publishes architecture guide and open-source blueprint for building multi-account agentic AI platforms on Amazon Bedrock AgentCore, including control plane and CI/CD evaluation pipeline.
-
Accelerating software delivery with agentic QA automation using Amazon Nova Act – Part 3
Part 3 of QA automation series using Amazon Nova Act adds test organization tools and team-based access controls for managing agentic QA across organizations.
-
Junie 3893.6 released
GPT 6.1 Terra support (+8 more releases that day)
-
Introducing the Microsoft Copilot harness in Foundry Agent Service
Microsoft introduces a Copilot harness in Foundry Agent Service, providing a unified execution foundation for agents with context, tools, and control management.
-
Bits AI SRE: Metrics query are disrupted
Major impact; resolved after 2 h 29 min.
-
Octoverse: Commits, pushes, reach new highs in 2026 as developers build with agents
GitHub's 2026 Octoverse report shows record growth in commits and pushes as developers build with agents.
-
Route and orchestrate models with GitHub Copilot Fusion
GitHub Copilot Fusion is now generally available and intelligently routes and orchestrates models for different tasks.
-
GitHub Copilot app, Universe releases
GitHub Copilot app and Universe releases enable cross-repository work and access to specs, designs, and assets.
-
GitHub Enterprise now includes access to GitHub Copilot
GitHub Enterprise now includes GitHub Copilot access for all licensed users through GitHub or Microsoft accounts.
-
Dayjob: Tax – evaluating AI agents on 50 professional tax assignments
Dayjob releases a benchmark evaluating AI agents on 50 professional tax assignments.
-
GitHub Copilot in VS Code, Universe releases
GitHub Copilot in VS Code now offers expanded model choice and control over where agents run.
-
GitHub Agentic Workflows generally available
GitHub Agentic Workflows is now generally available for automating reasoning-based tasks like issue triage and CI failure analysis.
-
Mastra 1.80.0 released
queryTraceThreads() thread rows no longer include model or provider, and page.limit is now capped at 100 (default 25); larger limits fail validation.; @mastra/connect connect-session creation response changed: POST /connect/:provider/sessions now returns…
-
Legora: Increase in error rates and latencies in the EU Region
Major impact; resolved after 6 min.
-
GitHub Copilot CLI: Disruption with some Copilot services
Critical impact; resolved after 1 h 15 min.
-
GitHub Copilot: Disruption with some Copilot services
Critical impact; resolved after 1 h 15 min.
-
The Agent SDK
-
CopilotKit 0.12.0 released
Includes security fixes for Teams and other Channels integrations.; Render static JSX as images in managed Slack and Teams messages.; Combine rendered cards with native buttons and carousel layouts. (+1 more release that day)
-
OpenAI and ServiceNow expand partnership across enterprise workflows
OpenAI and ServiceNow expanded their partnership to integrate OpenAI models and agents into ServiceNow, and ServiceNow workflows into ChatGPT and Codex.
-
Dia pricing changed: Free + $20/mo → Free + $10/mo
Free 'Better Browser' tier with profiles, tab groups, ad blocker, and sync; Better Answers $10/month (includes Morning Brief and AI features); Better Days $100/month (20x more tasks and chats, reports and decks). All new users get a 14-day free trial of Better
-
Elicit pricing changed: Free + $11/mo → Free + $39/mo
Free plan with limited research agent and report usage. Plus $39/month billed annually ($468/year). Pro $49/month billed annually ($588/year). Scale $89/month billed annually ($1,068/year). Enterprise custom.
-
Google Antigravity pricing changed: Free + $19.99/mo → Free + $30/mo
Individual use is free with unlimited Tab completions and Command requests plus basic weekly rate limits. Paid tiers include Google AI Pro and Google AI Ultra with flexible AI credit pools. Business access via Google Cloud offers Standard/Plus plans starting a
-
OpenHands pricing changed: Free + $499/mo → Free + $500/mo
OpenHands is free for local open-source deployment. Cloud plans: Teams at $500/month (up to 10 seats, $50/mo per additional seat, capped at 5,000 sessions/month, 30-day trial). Enterprise custom pricing available. All paid tiers include self-hosted deployment,
-
Legora is building the agentic operating system for legal work
Legora uses OpenAI models and ChatGPT to accelerate legal workflows and contract analysis.
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.