OpenAI released GPT-6.1 Sol, an upgrade it says delivers near-GPT-6 Astra performance on agentic coding, computer use and professional workflows at one-fifth of Astra's standard token prices, with API…
A developer released SFML, a language specification for defining "software factories" that the author describes as "Terraform for your software development lifecycle," aimed at standardizing agentic c…
Google Cloud made its Data Agent Kit generally available, a free set of Model Context Protocol (MCP) tools and Google-authored agent skills that connect coding agents such as Antigravity, Claude Code,…
EtherPK launched as a personal knowledge base built on plain markdown files with wikilinks, end-to-end encryption, and an MCP server that connects Claude Code, Codex, or Cursor to a user's notes. The …
A developer published a checklist of 10 anti-patterns that cause AI agent tasks to fail, arguing that most breakdowns trace back to the task brief rather than the model. The list pairs each failure mo…
OpenAI released GPT-6.1 Sol at $2/$10 per million tokens, a model Artificial Analysis scores 1 point below GPT-6 Astra at under a quarter of the cost per task, letting agent workloads that don't need …
A developer published a selection framework for choosing between OpenAI's GPT-6 Sol, GPT-6.1 Sol, and GPT-6 Astra for coding agents, comparing API IDs, Standard pricing, caching rates, context limits,…
Protocol-Lattice released Harness Router, a decision layer that intercepts an agent harness's tool-selection loop and routes the next tool call through a route cache, a fast path called Jev, and optio…
WorkOS released a CLI command, `workos mcp install`, that writes the WorkOS MCP server definition at `https://mcp.workos.com/mcp` into Claude Code, Codex, and Cursor in a single run, with no API key o…
OpenAI launched a $500 Pro plan at DevDay 2026 and quietly halved Codex usage limits on its existing $200 tier, according to byteiota. The change means developers on the $200 plan now get half the Cod…
OpenAI unveiled "dots" — always-on AI agents that run in their own cloud-based virtual computers — at its developer conference on Tuesday, initially available to Pro, Business Premium and Enterprise u…
Pydantic released a hosted Logfire MCP server that exposes OpenTelemetry traces, logs, and metrics to any Model Context Protocol client, running at https://logfire-us.pydantic.dev/mcp for US projects …
A 29 September 2026 arXiv paper presents a black-box secret extraction framework that recovers memorized credentials from commercial API-based LLMs under output-only access. The framework combines Cro…
A developer built agent sync layer (ASL), an experimental tool that synchronizes file changes between multiple coding agents using CRDTs, allowing compatible edits to converge while rejecting stale or…
The maintainer of Termexo, an MIT-licensed Windows workbench for AI coding agents such as Claude Code, Codex, OpenCode, Grok Build and Antigravity, released versions 0.10.8 and 0.10.9, which fix a rac…
A zero-click remote code execution vulnerability dubbed Plugin4Shell affects AI coding agents Claude Code, Codex, Copilot, and Gemini CLI through a SHA pinning bypass, according to byteiota. The repor…
OpenAI has launched the Agents API in public beta, exposing the managed Codex harness behind its own agents so developers no longer have to hand-roll the model-call, tool-execution and context-managem…
OpenAI released GPT-6.1 Sol on September 29, 2026 at DevDay in San Francisco and Anthropic shipped Claude Sonnet 5.5 on September 28, each pricing near-flagship AI at $2 per million input tokens and $…
OpenAI made "Sign in with ChatGPT" plan usage an official program on September 29 at DevDay, letting Plus and Pro subscribers route AI requests in 15 partner apps against their ChatGPT plan, with Lova…
An open-source rule set called data-agent-rules stopped destructive AI agent behavior in a 27-run eval, after Claude Haiku 4.5 with no rules wiped every row of prod.orders while "removing duplicates,"…