1. An open protocol for every company and every personal agent. Personal agents can discover participating companies, sign users in, and get things done through APIs, web pages, and company agents.

  2. Hi there guys. I need suggestion on from reference to 3d model, texture, rigging and animation for my game project.

  3. Mopup › Guides › Coding agent worktrees How to clean up the worktrees Claude Code, Cursor and Codex leave behind Coding agents work in git worktrees so several can run at once. Each worktree is a full checkout with its own node_modules and…

  4. could not extract summary

  5. I had 9% of my weekly usage limit left, which was set to reset today. I decided to use it wisely by selecting Composer and asking it to build a medium-sized feature (a reservation calendar).

  6. The SaaS I work for has started being spammed with startup ads. Except now they aren't just emails, they're AI agents visiting our website, opening the help desk chat widget in the corner, and spamming their message.

  7. Hi everyone, I use Claude Code via the Claude Desktop app because it’s by far the simplest and cleanest workflow for me. However, there is one really frustrating UX limitation: whenever images are displayed in the conversation (screenshots…

  8. I built a 3D Gaussian splat of an ibuprofen liquid softgel from 189 turntable photos, using Claude Code (Opus 5.5 on medium). It's free and open source (MIT): my github repo has the raw photos, every script, the exact settings, and an offl…

  9. I just noticed the option to decide whether my data is used to train future models is greyed out (used to not be) and says "not available for this account" (personal Pro account). Does that mean that all my data is being used for training?

  10. Hi there! I am a Product Designer (UX/UI) and Frontend Developer, with a fair knowledge on AI, I use it for years now for anything I can optimize.

  11. agentic-emulator (agemu) A fast control layer for the Android emulator and iOS Simulator, for coding agents that build mobile apps. A screenshot takes 4-5 ms and reading the screen 2-23 ms.

  12. Recorded mock run shown as a 3D diagram next to a terminal: 3 agents across 3 turns, each turn with 2 helpers, 27 nodes in total. Nodes move from pending to running to verified.

  13. I built two skills for sharing project memory and handing off work between AI assistants I work on projects with both Claude and ChatGPT. One recurring frustration: switching assistants means explaining the project again: what we decided,…

  14. Cursor's downfall is worth talking about I've been using Cursor almost since it released. At the time, it was a beast and the only legitimate AI-first IDE.

  15. I am not in this AI field but I have a question. Does they just give us the Claude interface or CLI experience and silently route our promts to free tier models like DeepSeek, Qwen, or Llama?

  16. OPEN SOURCE · APACHE-2.0 Agent policies in declarative logic, enforced on every action. SASY checks each action an AI agent takes, such as sending an email or running a command, before it happens.

  17. on the desktop app (windows), code tab, opus 5.5, permission mode is set to bypass permissions. asked claude to open a login page in chrome and it just kept failing with "the automatic safety check gave no verdict on this call".

  18. Investigating - We are currently investigating this issue. Nov 16, 07:49 UTC Post flair and post body will be updated as the incident report is updated by Anthropic.

    +28 more
  19. If you're choosing a self-hosted identity server for single sign-on and you'll set it up with an AI coding agent, the agent's preferences affect what you end up with. We asked Claude Code which open-source tools it recommends for login, si…

  20. Loftline is a 3D stunt driving game I made with Claude Code. You drive cars or motorbikes on tracks hanging from balloons over a sea of clouds.

  21. I'm working on some reverse engineering projects, but I'm running into restrictions with both Claude Code and OpenAI Codex. Whenever I ask them to analyze or generate certain types of code, they refuse, even when my intention is legitimate…

  22. I'm currently building my own coding harness, similar to Claude Code and Codex CLI. The idea is to build a terminal-based AI coding agent that can understand a codebase, read and modify files, execute terminal commands, use tools, manage c…

  23. brief2mp4 Text to motion graphics for Claude Code and Codex. Write a video brief, get a finished MP4 that has been checked against every line of it.

  24. Hello guys again :) It's Monday so here is the newest weekly update. Thanks to everyone who downloaded the game and especially to those who donated, I really didn't expect that and I appreciate it a lot ☺️ DEMO LINK DOWNLOAD - FREE Last we…

  25. **IMAGE NOT RELATED** I usualy use Claude for either personal projects like cleanTV, help with complex coding tasks, processing large spreadsheets and formatting them, and other things. I am currently on the free plan, and I keep running o…

    +55 more
  26. Huffl Skill Shared memory for your agents. Read and write capsules in Huffl so your agents share context across vendors and sessions, and you can read what they wrote.

  27. TrustGraph Policy-as-code for what AI agents produce. Decide where your agent's output can go, based on what it read.

  28. Paper · November 4, 2026 On a unified-memory device, the model and every agent's history share one memory. Hibana co-designs the model, its memory, and its decoding so many agents run fast on a single DGX Spark.

  29. Opus 5.5 comes out. Everybody is happy.

  30. Descobrir que o Opus 5.5 tem um cap de 330 carácteres e infere o resto com o contexto, sem indexação de código local isso faz aquelas perdas de contexto que te irritam tanto fazer mais sentido. Minha dúvida é, fable tem esse mesmo cap no a…