Top Picks

An iPhone app that tests how much judgment you may be handing over to LLMs. It runs offline, keeps data on device, and gives users a calibration score plus a shareable result card.

Windows desktop chat client for OpenRouter with streaming completions, model browsing, multi-session history, local storage, and PySide6 UI.

An open-source desktop client for editing LLM context with a separate AI model, context maps, compression tools, and revision rollback.

An Apple Silicon–optimized inference build of Bonsai 1.7B with custom Metal kernels, benchmark results, quick-start instructions, and a bundled OpenAI-compatible server.

Chrome extension that exports ChatGPT conversations to PDF, Word, Google Docs, or Notion, with partial exports, formatting controls, and local processing in the browser.

Trama is a VS Code tool for agentic coding that puts a map of the app next to the code and makes AI-generated changes go through approved Proposals before anything is built.

Model Salt is a web tool for rerunning the same prompt across multiple runs to surface varied LLM outputs by adding external randomness. The page shows example prompts, side-by-side generations from several models, and a simple workflow for exploring answer diversity.

A technical write-up on packing hundreds of AI agent sandboxes onto limited hardware, covering VM booting, idle killing, snapshots, and routing lighter tasks outside the VM.

A technical Ubicloud blog post about improving tool-call schema accuracy in vLLM for open-weight models, especially Kimi and DeepSeek, using constrained decoding.

Bellman is an MCP-based system for cross-session, cross-provider agent collaboration. The repository describes rooms, role-based join codes, peer confirmation, message passing, room surfaces, and support for MCP plus A2A integration.

An interactive map of AI companies, models, products, people, hardware, and ideas that are drawing attention across English-language news and developer communities over the last 7 days.

A pay-per-crawl system that lets site owners charge AI crawlers per page across WordPress, Next.js, Laravel, Cloudflare, nginx, Python, Go, and more. The page says payments settle in USDC on Base, with no custody, and that each edition includes crawler discovery files and support for x402/MPP-style access control.

ArtCraft is an open-source creative software suite that uses AI to recreate Adobe-style apps like Photoshop, Premiere, and Lightroom for macOS, Windows, and Linux.

An open-source Pac-Man benchmark where AI decision models compete in real time against scripted ghosts, with a public leaderboard, replayable games, and instructions for benchmarking your own endpoint.

A weekly curated index of AI research papers from DAIR.AI Academy, with searchable archives, topic filters, and an MCP setup for use with Claude Code or Codex.

Graphite’s Five Percent research article analyzes writing-style differences in Claude Opus 5.5, compares it with prior Claude versions and GPT-6 Astra, and includes charts, tell counts, and downloadable data.

A Claude Code plugin that delegates subtasks to Codex, Antigravity, opencode, or a local model, each running in its own tmux session, then returns only the final report.

A Chrome extension that acts like a floating AI sidekick for browsing, with voice commands, page interaction, and local AI/Ollama support.

A React-based package for adding lip-synced Gaussian-splat avatars to AI voice agents, with support for OpenAI Realtime, GPT-Live, Qwen Realtime, ElevenLabs, Vapi, and LiveKit Agents.

A Julia-based projectional editor for structured data with multiple editable views and an AI assistant that edits the same underlying data.

Drawgent is a coding agent that works on a live Excalidraw canvas, aimed at turning sketches and diagrams into code. The page shows a real project with a README-driven quick start, demo section, setup command, and detailed notes on how the agent interacts with diagrams and code.

An interactive site that maps your AI worldview and compares it with public figures and simulated users on how AI may change the future.

arXiv paper on constraining LLM decoding with incremental parsing to reduce invalid SQL and improve text-to-SQL results.

MineTrials is a benchmark-style writeup exploring how far AI agents can get in one hour of Minecraft, comparing models and harnesses and highlighting performance, cost, and a best run.