AI on 22 Oct 2026
Everything new on the trackers that day: official announcements, model uploads from the big labs, tool releases, papers, AI rules and outages. Each item links to its source.
On 22 Oct 2026 the Machine Notes trackers recorded 7 announcements, 3 tool releases, 5 papers and 2 outages (announcements from Hugging Face and NVIDIA). The most upvoted paper was "StreamEval: Evaluating Interactive Streaming Video Generation Models". The fastest-rising AI repo was yetone/magpie.
Updated 22 Oct 2026, 11:25 UTC
Official announcements
WireTool releases
Releases that dayPapers people are reading
Research that day| Paper | Upvotes |
|---|---|
| StreamEval: Evaluating Interactive Streaming Video Generation ModelsStreamEval Team | 83 |
| SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?Zhaoxi Zhang, Hao Liang, Linxuan Wu and others | 82 |
| Cache Engineering for AgentsTianyu Fu, Ruoxi Wang, Zihan Min and others | 75 |
| Looking Ahead: Modeling Future Evolution in Autoregressive Video GenerationRuopeng Gao, Yukun Huang, Jiarui Hu and others | 73 |
| Agent World Model in the Wild: Computer-Use Agent Environment SynthesisZhaoyang Wang, Qianhui Wu, Haorui Wang and others | 59 |
Outages
Outage log| Service | Incident | Impact | Started | Lasted |
|---|---|---|---|---|
| Anthropic | Elevated errors affecting Connectorsclaude.ai · Claude Cowork | Minor | 03:50 UTC | 4 h 17 min |
| OpenAI | Elevated ChatGPT conversation and Responses API errors | Minor | 02:18 UTC | 6 h 32 min |
Rising AI repos
Repos that day| Repository | Description | Stars gained |
|---|---|---|
| magpieyetone | Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar. | +598 |
| coucouLouis-CFM | A tiny friend in your Mac's notch and on your iPhone that keeps an eye on your AI coding agents: Claude Code, Codex, Cursor, Gemini CLI, Antigravity and more. Approve from the notch or your Lock Screen. | +486 |
| nanoMusenano-muse | nanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that does things, keeps working while the app is closed, remembers you, and asks before anything you cannot undo. On Android, iPhone and iPad, Windows / macOS / Linux and in the browser; your phone's screen and your computer as its hands. | +159 |
| project-mayamw00 | Project Maya - run GLM-5.3-Flash (321B MoE) and DeepSeek-V4.1-Flash-1017 (748B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant tools. | +78 |
| StartLux-DecisionStartLuxLabs | Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine for vLLM, llama.cpp and MLX. | +71 |