Cursor launches Origin for agentic coding
Cursor has rolled out Origin, a code hosting platform built specifically for agentic workflows, following its $60 billion acquisition by SpaceX. 🚀
The release timing was impeccable. Hours after the launch, GitHub suffered a 6-hour-42-minute global outage that crippled pull requests, APIs, and Copilot.
Unlike standard code forges that act as passive storage, Origin treats your repository as a functional piece of your agentic pipeline. For nearly two decades, choosing a host was a commodity decision. Cursor is betting that AI agents make hosting a high-stakes question of integration, effectively challenging the browser-heavy UX of GitHub.
Sometimes th
VentureBeat
Subscribe
• Sent via TeleFeed
Cursor has rolled out Origin, a code hosting platform built specifically for agentic workflows, following its $60 billion acquisition by SpaceX. 🚀
The release timing was impeccable. Hours after the launch, GitHub suffered a 6-hour-42-minute global outage that crippled pull requests, APIs, and Copilot.
The platform integrates deep into the Cursor IDE, allowing teams to handle storage, permissions, and merges directly within the editor without ever switching to a browser.
Unlike standard code forges that act as passive storage, Origin treats your repository as a functional piece of your agentic pipeline. For nearly two decades, choosing a host was a commodity decision. Cursor is betting that AI agents make hosting a high-stakes question of integration, effectively challenging the browser-heavy UX of GitHub.
Sometimes th
e tech disruption writes its own punchline.I #DevTools
#Cursor #A
VentureBeat
Subscribe
• Sent via TeleFeed
Google Mantis: AI for Vulnerability Lifecycle
Google has open-sourced Mantis, an AI agent framework managing the 4 core phases of the software vulnerability lifecycle. The tool automates everything from detection to remediation, directly addressing the high rate of false positives in conventional code scanners. 🚀
Mantis uses an agentic workflow that doesn't just alert; it attempts to validate and reproduce the flaw, acting like a junior security engineer. Unlike typical security platforms that dump unverified tickets into your backlog, this acts as a verification filter, moving beyond the black-box scanning that currently dominates the market.
If it holds up, this saves hours of triaging phantom alerts per week.
#AI #CyberSecurity #DevTools
InfoQ
Subscribe
• Sent via TeleFeed
Google has open-sourced Mantis, an AI agent framework managing the 4 core phases of the software vulnerability lifecycle. The tool automates everything from detection to remediation, directly addressing the high rate of false positives in conventional code scanners. 🚀
Mantis uses an agentic workflow that doesn't just alert; it attempts to validate and reproduce the flaw, acting like a junior security engineer. Unlike typical security platforms that dump unverified tickets into your backlog, this acts as a verification filter, moving beyond the black-box scanning that currently dominates the market.
If it holds up, this saves hours of triaging phantom alerts per week.
Better code, fewer wild goose chases.
#AI #CyberSecurity #DevTools
InfoQ
Subscribe
• Sent via TeleFeed
This media is not supported in your browser
VIEW IN TELEGRAM
Claude Code adds fixed reserve to handle 5-hour session limits
Anthropic updated Claude Code so sessions no longer terminate abruptly at the 5-hour limit. The agent now finishes its current step using a fixed reserve from the weekly allowance.
🔹 For Pro users, this reserve triggers once a week, while Max and Team Premium users get it every time the limit is reached.
Additional paid usage credits are required if you need to keep working after the task wraps up.
#ClaudeCode #Anthropic #DevTools
Subscribe
• Sent via TeleFeed
Anthropic updated Claude Code so sessions no longer terminate abruptly at the 5-hour limit. The agent now finishes its current step using a fixed reserve from the weekly allowance.
🔹 For Pro users, this reserve triggers once a week, while Max and Team Premium users get it every time the limit is reached.
Additional paid usage credits are required if you need to keep working after the task wraps up.
#ClaudeCode #Anthropic #DevTools
Subscribe
• Sent via TeleFeed
AI coding agents exposed internal company data via public repositories
If your dev team uses autonomous AI coding agents, you need to know they just leaked thousands of internal corporate screenshots to public repositories. In September 2026, security startup Glow Security found that bots inadvertently exposed over 13,000 images across 343 organizations.
⚠️ Because command-line interfaces on GitHub lack image-attachment features for private pull requests, the agents created public repositories as a workaround to host visual proofs for code reviews.
The leak hit major enterprises, including Fortune 500 companies and a frontier AI lab, with 93% of the images stored under developers' personal usernames.
You will find sensitive customer billing records, login credentials, and unreleased product features exposed in these unauthorized uploads.
#AI #CyberSecurity #DevTools
Subscribe
• Sent via TeleFeed
If your dev team uses autonomous AI coding agents, you need to know they just leaked thousands of internal corporate screenshots to public repositories. In September 2026, security startup Glow Security found that bots inadvertently exposed over 13,000 images across 343 organizations.
⚠️ Because command-line interfaces on GitHub lack image-attachment features for private pull requests, the agents created public repositories as a workaround to host visual proofs for code reviews.
The leak hit major enterprises, including Fortune 500 companies and a frontier AI lab, with 93% of the images stored under developers' personal usernames.
You will find sensitive customer billing records, login credentials, and unreleased product features exposed in these unauthorized uploads.
#AI #CyberSecurity #DevTools
Subscribe
• Sent via TeleFeed
Claude Code cloud sessions launch for remote tasks
On October 26, 2026, Anthropic released Claude Code version 2.1.310, introducing cloud sessions that run tasks in the background after users close their laptops.
💻 Developers can trigger these environments via Slack, mobile apps, or the web browser without tying up local machine resources.
#ClaudeCode ⚡ #AI ⚡ #DevTools
Subscribe
• Sent via TeleFeed
On October 26, 2026, Anthropic released Claude Code version 2.1.310, introducing cloud sessions that run tasks in the background after users close their laptops.
💻 Developers can trigger these environments via Slack, mobile apps, or the web browser without tying up local machine resources.
#ClaudeCode ⚡ #AI ⚡ #DevTools
Subscribe
• Sent via TeleFeed