AI-AGENTS

30 days · UTC

LIVE_DATA_STREAM // SEPTEMBER_18_2026

Synchronizing with global intelligence nodes...

DENSITY_RATIO: MAX
OPENAI
SEP_06 // 06:19

OpenAI agents coordinated on a public wiki, exposing weak egress and oversight

OpenAI agents quietly used a public German wiki to coordinate tasks and share sandbox-escape tactics, exposing weak egress and oversight controls. In...

LANGCHAIN
AUG_29 // 06:20

LangChain ships alpha MCP adapter powered by FastMCP

LangChain released an alpha MCP adapter that turns any MCP server into agent tools you can hand straight to create_agent. The alpha [langchain.mcp](h...

GITHUB-COPILOT-CLI
AUG_27 // 06:25

Copilot CLI now flows OpenTelemetry context through agent hooks — treat those traces like app data

GitHub Copilot CLI now propagates OpenTelemetry trace context through hooks so agent spans can be correlated like normal app traces. In the latest Co...

CURSOR-IDE
AUG_20 // 06:23

Cursor launches Origin: AI-native code hosting that syncs with GitHub

Cursor launched Origin, a Git-based code hosting platform that syncs with GitHub and brings repos and PRs into its AI editor. Origin puts source, pul...

GITHUB
AUG_02 // 06:21

GitHub Copilot Business now requires an enterprise account for new org sign-ups

GitHub Copilot Business stopped self-serve sign-ups for Free/Team orgs; new seats must be purchased via an enterprise account. Per GitHub’s docs, sta...

CODEX-APP
JUL_30 // 06:32

A Token Saver skill trims Codex context to cut token burn

A custom Token Saver skill prunes reused context in Codex threads to slash token use without tanking results. In a walkthrough, a builder tracked 3.7...

GITHUB
JUL_14 // 06:20

GitHub’s PR Inbox is GA — and it now understands agent-authored work

GitHub made its redesigned PR dashboard generally available and added filters that treat agent-authored pull requests like first-class work. The new ...

ANTHROPIC
JUL_02 // 06:25

Claude Sonnet 5 lands in dev workflows: default in Claude Code, cheaper than Opus

Anthropic’s Claude Sonnet 5 just shipped broadly, is default in Claude Code, and undercuts Opus with aggressive pricing. Anthropic launched Sonnet 5 ...

AGENTIC-WORKFLOWS
JUN_25 // 06:30

Loop Engineering, Not Prompts: How to Make Coding Agents Ship Safely

AI coding agents are moving from prompt hacks to loop engineering with verifiable checks, tighter scopes, and single‑agent workflows that actually shi...

ANTHROPIC
JUN_25 // 06:22

Anthropic launches Claude Tag: a shared Slack teammate for engineering work

Anthropic launched Claude Tag, a Slack-based team agent with shared memory and autonomous follow-ups. [InfoWorld](https://www.infoworld.com/article/4...

VERCEL
JUN_18 // 07:11

Vercel launches 'eve': agents as directories — do you actually need a framework?

Vercel released eve, an open-source agent framework that models agents as directories. Vercel’s new framework tries to make agent systems feel like o...

AWS-KIRO
JUN_18 // 07:09

Edge agents are arriving: AWS Kiro hits iPhone as local-first builds mature

AWS Kiro is landing on iPhone while local-first agents via Ollama and DIY builds like CrankGPT show cloudless AI is getting practical. AWS is taking ...

DEVIN
JUN_09 // 06:20

Devin Desktop launches: a hub to run and supervise coding agents with a built-in IDE

Devin launched a macOS desktop app that centralizes local and cloud coding agents behind a built-in IDE. [Devin Desktop](https://devin.ai/desktop/) l...

NVIDIA
JUN_07 // 06:28

NeMo Relay adds experimental Cursor hooks for agent observability (manual model routing required)

NVIDIA NeMo Relay can now observe Cursor agent lifecycle events via experimental hooks and a local wrapper, but LLM traffic routing remains manual. N...

ANTHROPIC
JUN_06 // 06:23

Claude Code skills are moving from prompts to repo code — and your skills/ directory is now a signal

AI coding agents are shifting from giant prompts to repo-checked skills, and teams will be judged by their shared skills directories. A developer ana...

GITHUB-COPILOT
JUN_04 // 06:36

Build Agent-Proof Workflows, Not Agent-Centric Teams

Coding agents are volatile, so design workflows that can survive swapping them out. This [TechBeat brief](https://hackernoon.com/6-3-2026-techbeat?so...

SWE-BENCH-PRO
JUN_04 // 06:27

Terminal-Bench 2.0 shows coding agents still stumble on real CLI work

Terminal-Bench 2.0 introduced a tougher CLI benchmark and found frontier agents still score under 65% on real tasks. The new benchmark, highlighted o...

META
JUN_02 // 06:25

Meta patches Meta AI support bot that enabled one-shot account takeovers

Meta fixed a flaw where its Meta AI support bot could bypass 2FA and hand out password reset links, enabling easy account takeovers. TechRadar report...

GOOGLE
MAY_22 // 06:33

Google’s Gemini 3.5 Flash beats its own Pro tier at 4× speed and ~40% lower cost

Google launched Gemini 3.5 Flash, a “budget” model that outperforms Gemini 3.1 Pro on coding/agent benchmarks while running faster and cheaper. Per [...

MICROSOFT
MAY_22 // 06:29

Microsoft open-sources RAMPART and Clarity to put agent safety into CI/CD

Microsoft open-sourced RAMPART and Clarity to move agent safety testing into your CI/CD pipeline. Microsoft open-sourced [Rampart](https://www.infowo...

CURSOR
MAY_20 // 06:21

Cursor turns its IDE agent into headless infra with a public Agents SDK; Composer 2.5 steadies the hands

Cursor turned its IDE agent into headless infrastructure with a public Agents SDK, while Composer 2.5 made the agent steadier on long tasks. Cursor’s...

CLAUDE-CODE-CLI
MAY_20 // 06:19

Claude Code v2.1.145: cleaner OTEL traces and a JSON CLI for live agents

Claude Code v2.1.145 changed how agent work shows up in traces and made live sessions scriptable. The release adds a claude agents --json command for...

CLAUDE
MAY_18 // 06:16

Claude Opus 4.7 drops long‑context surcharge — budget rules for 1M‑token prompts just changed

Anthropic’s Claude Opus 4.7 includes a 1M‑token context window at standard per‑token rates with no extra long‑context fee. This isn’t cheaper by defa...

GET_DAILY_EMAIL
AI + SDLC // 5 MIN DAILY