Top Picks

arXiv paper describing QUEST, an open family of deep research agents from 2B to 35B parameters, plus a synthetic-task training recipe and released models, data, and scripts.

A Claude Code skill pack with 171 structured reasoning methods drawn from historical thinkers, designed to route different problem types to specific procedures.

An experimental programming language and compiler built for agent workflows, with CLI commands for parsing, checking, graphing, repair planning, and JSON-based inspection output.

Rust TUI for browsing local Codex and Claude Code session logs, searching past chats, and estimating API-equivalent cost.

A daily AI intelligence journal for builders, covering notable model, tooling, and release updates in a short sourced digest.

Desktop app for orchestrating crews of local coding agents like Claude Code and Codex in one workspace.

An early-access TypeScript rewrite of Prisma ORM built to be extensible, composable, and AI-agent friendly, with scaffolding, agent skills, and extension support.

PocketWebTools is a collection of browser-based utility tools, including AI features like background removal, image upscaling, OCR, subject cutout, and audio transcription. The site emphasizes local processing, no signup, no tracking, and data staying on device.

Physics AI is a physics homework and study tool that solves problems from photos or typed prompts, with step-by-step explanations, tutor mode, and visual breakdowns for diagrams and vectors.

A tarot reading site with daily draws, common spreads, card meanings, multilingual support, and shareable reading images.

A free browser-based signature font generator for creating handwritten-style name graphics, logo mockups, and email signature assets. The page shows live preview, font style selection, PNG export, and copy-to-clipboard options, with a library of 58 styles.

A field study on AI coding agents showing that a large share of token spend comes from re-reading files, with data from 47 sessions and discussion of memory-layer fixes.

A free browser-based text survival and settlement-building game with incremental progression, turn-based combat, crafting, villagers, and dark fantasy storytelling.

An Android-focused on-device AI agent fork that can automate phone actions, run workflows and schedules, and be controlled locally or through Telegram.

Open-source package manager for AI coding assistants that helps teams share, version, and scope skills, MCP configs, commands, and other AI assets across tools and projects.

A governance plugin for OpenClaw that registers instances with a Recursant registry and intercepts tool calls, LLM prompts, and chat messages for auth, PII redaction, rate limiting, and auditing.

MerryDiv is a dividend tracker that automatically syncs with brokerage accounts through Plaid to consolidate payouts, portfolio diversification, and income analytics across multiple accounts.

A Mac-resident MCP server that lets AI agents access Apple services like Mail, Calendar, iCloud Drive, Voice Memos, Reminders, and Contacts over a Tailscale network with per-token ACLs and audit logging.

HookGuard is a CLI security scanner for AI coding agent configuration files. It looks for malicious hooks, invisible Unicode, credential exfiltration patterns, and prompt-injection text in files like CLAUDE.md, AGENTS.md, Cursor rules, and GitHub Copilot instructions.

Single-binary viewer for HTML reports generated by AI agents, with local browsing, live previews, search, and shareable links.

Free analyzer that reads server logs to identify AI bot traffic, estimate bandwidth cost, and generate block rules for Cloudflare, Nginx, Next.js, or robots.txt.

Modular framework for building trading systems with a C++ core, polyglot strategy bindings, and an MCP server for AI coding agents.

Lowdefy is a config-first web stack that lets AI generate reviewable YAML for full-stack apps and can run AI agents that call existing endpoints as tools.

A multi-lens code review pipeline for Claude Code that runs parallel review passes, validation gates, optional Codex review, an auto-fix loop, and interactive walkthroughs for findings.