IFTTT switched to credit-based pricing on October 28, 2026: unlimited Applets on every plan, 1,000 free credits a month, and a new $2.99 Starter plan. Here is what each plan costs, how credits are counted, and how IFTTT now compares with Zapier.
Framer MCP, released October 22, 2026, lets the Claude app, ChatGPT, Codex, Cursor and Grok Bot build pages and fill the CMS of your Framer site. It is free on every Framer plan during the preview.
Anthropic launched Claude Duet on October 21, 2026: a proactive agent app that briefs you each morning, works in its own cloud computer and asks before it sends, pays, signs or deletes. Here is how it compares with OpenAI dots, Meta Muse and Grok Bot.
Notion now gives every Business and Enterprise seat 1,500 Standard and 500 Select AI credits a month, and existing workspaces switch on November 2, 2026. Here is what that buys, and how to stretch it.
OpenAI opened the Decisions API to every developer on 6 October 2026: gpt-6-luna returns probabilities, choices and rubric scores at $0.10 per 1M input tokens, with no output charge. We compared it with the Responses API, Cloudflare Clef and TypeSafe Jev.
Meta open-sourced Muse Gadgets on October 2: ESP32 firmware, a Linux SDK and 42 device skills. The Linux SDK lets Muse run any command as the account you choose. We tested the runner, found what the log and the sudo warning miss, and wrote a safe Pi setup.
On October 2, 2026, Apple said it will make macOS Full Disk Access harder to grant because of AI agents. No date yet, but if your terminal already has the permission, every agent you launch from it can read your Messages, Mail and Safari data. Here is how to audit it.
Cloudflare launched a Web Search API on October 2, 2026: one endpoint that lets an AI agent search the web through Ceramic.ai at $0.25 per 1,000 requests, Linkup at $5 or Exa at $7, with no markup. Here is how it prices against Brave, Tavily and Claude's search tool.
Comfy Agent launched October 1 on Comfy Cloud and bills Claude Opus 4.8 tokens at exactly Anthropic's list price. Priced from the agent's own recorded turns, a build-and-run turn costs $0.86 before GPU time, and local ComfyUI builds compile the agent out.
Cloudflare's open Clef decision models would top the Decision Index at 61.2 on Cloudflare's own numbers, but cost 5.7 times Jev per token, Clef-flash fails hallucination checks, and 5,354 downloads went to GGUF files missing the decision head.
Shopify Canvas, launched October 1, builds a store theme by chatting with Sidekick in about 20 minutes. The catch: a theme edited in Canvas can't be downloaded and stops receiving theme updates.
OpenAI launched dots, always-on agents on GPT-6 Astra with their own cloud computer, for Pro and Business Premium. We checked six official pages: four launch claims differ from the setup docs, and you cannot delete a single dot memory.
Meta's Muse for Small Business promises nothing publishes, sends or spends without your approval. We read the 12 official pages behind that line: purchases always ask, but publishing and sending are a setting, and a sent email cannot be reversed.
Shopify opened checkout to browser AI agents on September 28. We tested 8 stores in Chrome 154: every storefront exposed 11 tools, but no checkout did until WebMCP was switched on, and one partial update wiped a buyer's address.
AI scrapers fill missing fields with real text from the wrong line of the page. We rebuilt the "Do not guess" twin-page test on a CPU: quote checks caught 0 of 7 decoys, and a 4B checker model caught them all.
Manus 2.0 adds a timeline Video Editor and a Game Dev tool with multiplayer. We checked 10 official Manus pages: none gives a credit cost for either, and the server behind a multiplayer game starts at $30 a month.
H Company's Holo4 ships two open-weight computer-use models. The 27B wins on long workflows at $2.94 per completed task but is research-only; the Apache 2.0 35B-A3B is the one you can self-host commercially.
Ollaya, the open-source runtime that serves Jev-style decision models locally, hit the Hacker News front page on 25 September. We ran three of its models on a CPU against 300 labelled examples: Laya is fastest and most overconfident, decider:0.8b the most accurate.
Placeholder domains like yoursite.com appear in 349 AI agent skills and anyone can own them. We scanned 658 popular skills, found 20 hits, and wrote a 10-minute audit.
CLM-8B, an open decision model from Stanford and NVIDIA released on 23 September, scores candidate actions up to 9x faster than Jev. Its 81.6% DeepSWE result is 31 of 38 tasks. Here is how to run it as a verifier for your coding agent.
Google's Antigravity SDK now runs agents on local models: Gemma 4 26B A4B through LiteRT-LM, or any OpenAI-compatible server such as Ollama, LM Studio or vLLM. We read the SDK source and the demo code behind its 97.2% local-token headline.
StepFun's Step Code claims 80.9% on Terminal-Bench 2.1. That is 72 of 89 tasks, run once, on a model StepFun has not named, and it is not on the official leaderboard.
OpenClaw shipped v2026.9.5 on 19 September with atomic updates and plugin hot reload. The continuity promise is thinnest in two places: an open hot-reload regression, and an extended-stable channel that published nothing.
Meta opened the Muse Connector Platform to developers on 18 September 2026, with a three-step review and a Stripe Link payment rail. It governs one of the two ways a service reaches Muse. Custom connectors, which Muse writes itself against any public API, are not reviewed at all.