Gm Drop the stock of the day

A 27B uncensored model just got squeezed from 54.7 GB down to 15.7 GB, small enough for a single consumer GPU. > OrcaSAQ2 compresses Qwen3.8-27B with a mixed-precision quantization method > 71% smaller, only +0.80% perplexity versus the original > 94.4% token-level agreement, 262K context, thinking mode and tool calling intact Runs locally through llama.cpp, Ollama and LM Studio It's positioned for coding, vulnerability research and authorized security testing, with no guardrails baked in. Open Weights: huggingface.co/orcarouter/Or…

Anthropic is spending like it’s already worth $2 trillion — because it plans to be. H1 2026 numbers from the draft S-1: •⁠ ⁠$80.7B net loss (mostly non-cash from Amazon & Google notes) •⁠ ⁠Real loss closer to $8.7B •⁠ ⁠Revenue jumped 15x to $16.3B •⁠ ⁠Compute spend nearly $9B in six months (more than all of 2025) Still on the hook for $600B+ in future infrastructure deals, possibly $750B. IPO targeted for November.

Underdog just released Bark 3.0, a speech model small enough to run on your phone. >⁠163 MB, as accurate as NVIDIA Parakeet (15x bigger) and ahead of OpenAI Whisper large-v3 (57x bigger) >⁠Transcribes 1 minute of audio in under 0.25 seconds on a MacBook >⁠7.82% word error rate on meetings vs 13.63% for Whisper Runs fully on-device, free and open source x.com/UnderdogAI/status/2112…

Someone just open sourced the framework for Intelligent UI, and it's already #5 trending on GitHub. >⁠Works with any LLM and any agent framework >⁠Plug in your own components and design system >⁠Supports every kind of generative UI •⁠ ⁠No lock-in, built by CopilotKit The pitch is that every app ships with this by 2027. WILL EVERY APP HAVE AN AGENT BUILT INTO ITS INTERFACE BY THEN? github.com/CopilotKit/OpenIn…

Your AI agent can code. Now it can do your marketing too. 55.9K stars. Marketing Skills is a free library from marketer Corey Haines that turns Claude Code, Codex or Cursor into a growth team: → copywriting for homepages, landing pages and pricing pages → SEO audits and SEO pages built at scale from templates and data → cold email sequences that get replies → competitor profiles built from their websites → launch plans, ad creative, A/B tests and conversion tracking → churn prevention: cancellation flows, save offers, failed-payment recovery → a "marketing council" that gives you several expert opinions on one question Install all of them: npx skills add coreyhaines31/marketingskills Or just the ones you need: npx skills add coreyhaines31/marketingskills --skill cro copywriting MIT. github.com/coreyhaines31/mar…

Turn your AI coding assistant into a full video production studio. 70.7K stars. Describe the video in plain words, and OpenMontage handles the research, script, visuals, narration, music, captions and final edit. → 12 pipelines: animated explainers, cinematic trailers, documentaries, product films, short-form clips cut from one long video, dubbing and more → a real-footage mode that cuts actual clips from free archives like Pexels, Archive.org, NASA and Wikimedia, with no paid AI video needed → checks its own work before you see it: video and audio levels, sampled frames, subtitles → asks your approval on creative decisions → works with Claude Code, Cursor, Codex, Copilot and Windsurf One of their demos, a 60-second Pixar-style short about a lonely banana, cost $1.33 to make. Install: git clone github.com/calesthio/OpenMon… cd OpenMontage make setup Then try: "Make a 45-second animated explainer about why the sky is blue" AGPL-3.0.

You read a great book once. Three months later you can't remember chapter 7 even existed. book-to-skill turns any book, PDF or folder of docs into a skill your AI agent can use while you work. 35.7K stars. 1.⁠ ⁠Point it at a file: /book-to-skill ./my-book.pdf 2.⁠ ⁠It pulls out the frameworks, decision rules, mistakes to avoid and one file per chapter. It's built from the book's structure, not a summary. 3.⁠ ⁠Ask your agent about a topic and it reads the right chapter and answers from the actual text. → uses 24 to 51 times fewer tokens than pasting the whole book into the chat → also works on your own runbooks, brand guidelines, onboarding docs and research papers → works with Claude Code, Codex, GitHub Copilot CLI, OpenCode and more Install: npx skills add virgiliojr94/book-to-skill Use it on books and documents you own. MIT. github.com/virgiliojr94/book…

Shopify CEO Tobi Lütke built a search engine for your own notes, and it runs entirely on your computer. 30.5K stars. QMD indexes your markdown notes, meeting transcripts and docs, then finds what you need: → fast keyword search → semantic search that matches what you mean, not just the words you type → a hybrid mode that re-ranks results with a local AI model → everything stays on your machine, with no cloud → your coding agent can use it to search your notes too Install: npm install -g @tobilu/qmd qmd collection add ~/notes --name notes qmd embed qmd query "quarterly planning process" MIT. github.com/tobi/qmd

Your AI writes three paragraphs before it tells you what to do. This skill fixes that. 58K stars. i-have-adhd makes your coding assistant lead with the answer: → the next action comes first → steps are numbered → it ends with one concrete next step → lists are capped at 5 items → no "Great question!", no recap, no "Hope this helps!" Before: a long paragraph about your auth flow, "one approach would be…", "let me know if you want to dig deeper." After: "Edit src/auth.ts:42", three numbered steps, and what to do if a test fails. To install, paste this into Claude Code or your coding agent: "Install the i-have-adhd skill/plugin from github.com/ayghri/i-have-adh…, refer to the repo's AGENTS.md for instructions." No diagnosis needed. MIT.

A real-time intelligence dashboard for the entire world, free in your browser. 89K stars. World Monitor puts it all on one screen: → news from global and regional feeds, summarized by AI into briefs → markets and prediction markets → conflicts, military flights and cyber incidents → climate and disasters, on a 3D globe or a flat map → live TV Open it at worldmonitor.app, or run it in your terminal with no API key: npx worldmonitor There are also finance, tech, commodity and energy versions, plus desktop apps for Mac, Windows and Linux. AGPL-3.0. github.com/koala73/worldmoni…

Alibaba open-sourced the AI code reviewer its own engineers have used for two years. Open Code Review served tens of thousands of Alibaba developers and caught millions of code defects before it went public. 48K stars. → reads your changes, then the full files and the rest of the codebase for context → puts each comment on the exact line → "ocr scan" audits whole folders, even code with no git history → works with your own model and API key In Alibaba's test on 200 real pull requests, it beat Claude Code on precision with the same model, using about 1/9 of the tokens. It flags fewer issues overall, by design, so you get fewer false alarms. Install: npm install -g @alibaba-group/open-code-review ocr config provider cd your-project && ocr review Apache-2.0. github.com/alibaba/open-code…

Papertrade's revenue has cooled fast → Launch day: $25.24M → 24h revenue: $1.45M down to $183K in one day → TVL: ~$102M peak, ~$46M now (DefiLlama)

geo-sleuth is an open-source agent skill that estimates where a photo was taken and shows its reasoning. → It uses OpenStreetMap geometry, elevation-based skyline matching, sun and shadow angles, satellite tiles and street view → It outputs coordinates with an error radius, camera heading and an evidence image → The author says its examples are not accuracy on unseen photos; a blind-test set is planned → It works with Claude Code, Codex and Cursor; MIT licensed Repo: github.com/Oldcircle/geo-sle…

ECC (Everything Claude Code) is a free, MIT-licensed pack: 70+ subagents, 300+ skills and about 95 commands. The workflow it pushes: → Plan first, and approve it before code → Failing test before the fix → Separate reviewers per language → A security scanner for your agent config (prompts, hooks, MCP, permissions) Don't install everything. Start with the planning agent and the rules pack for your main language, try it on a small repo, then add more. Install only from the official repo or npm packages. The repo warns that re-uploads may contain malware. Some tiers are paid. Repo: github.com/affaan-m/everythi…

Palantir-style world map. Open source. OSIRIS is a free dashboard that puts a dozen public data feeds on one map: → Live flights and ships → Satellites and undersea cables → Earthquakes, wildfires and cyber-threat feeds → 6,000+ public traffic and open-webcam cameras → Optional AI analyst and 20 recon tools Caveats: data quality varies by source, some feeds go stale, and camera coverage differs by country. The README says it's for research and education. MIT licensed. Run it yourself. github.com/carbon-evolution/…

A GitHub repo maps 300+ AI agent projects across 36 categories and saves developers from spending weekends building memory, browsers and agent loops that five open source projects already did better, covering DSPy for code-based prompting, Serena for meaning-based code editing, Stagehand for web interaction, Steel Browser for sandboxed browsing, Cognee for persistent memory and Opik for agent tracing. → DSPy from Stanford lets you write agents as code instead of prompts → Screenpipe records your computer activity so agents have real context → Google’s ADK for building and testing full agent teams with evaluation built in → Free, MIT licensed, available as JSON and YAML to plug into your own tools Repo: github.com/slavakurilyak/awe…

The same Opus 5.5 prompt run 20 days apart produced noticeably different results, raising questions about whether the model has been quietly downgraded between runs.

GM CT ☀️ HOW IS YOUR WEEK GOING SO FAR? ☕

AI shopping agents just got a front door at Walmart. While Amazon blocks agents, Walmart announced an MCP server called Agent Gateway: → Approved agents can search Walmart and Sam's Club inventory and buy for you → You don't have to share personal info or purchase history with the agent → Next month: a separate profile per agent in your account → Require approval per purchase, or pre-approve up to a spending limit The rules: agents can't see payment details, can't act beyond what you asked, and get blocked if they break the terms. Walmart's returns policy still applies if an agent gets it wrong. It already works with Meta's Muse, ChatGPT and Gemini. techcrunch.com/2026/10/21/wh…