heatdrop.ai

Garry Tan open-sourced the exact Claude Code prompts he uses to ship 810× faster while running Y Combinator full-time.

Claude Code skill makes the agent talk like a caveman and claims ~65% fewer output tokens, with benchmarks to back it up.

An AI agent that edits, trains, and evaluates LLM code overnight so you don't have to.

A developer turned months of manual applications into an AI agent pipeline that evaluates, scores, and tailors CVs for each listing.

Paperclip is an open-source control plane that turns a swarm of AI agents into something resembling an actual company.

Hermes Agent is a self-improving AI assistant that creates skills from experience, persists knowledge across sessions, and runs anywhere from a $5 VPS to serverless cloud.

rtk sits between your AI agent and the shell, compressing command output before it ever hits context.

A free, from-scratch curriculum that makes you build backprop before you touch PyTorch, then ships every lesson as a reusable prompt or agent.

A single TypeScript codebase that turns 500+ news feeds and 65+ data APIs into a geopolitical intelligence dashboard with local AI.

Desktop app that corrals Claude Code, Codex, Gemini CLI and half a dozen other AI agents into one switchboard.

Claude Code skills that run your research through a full academic pipeline—research, writing, staged integrity checks, and multi-perspective review—while keeping a human in the driver's seat.

A Python system that scrapes market data, asks an LLM for a verdict, and pushes buy/sell/emoji dashboards to Slack or WeChat on a cron job.

A hybrid CLI tool that uses deterministic pipelines to keep LLM agents from drifting off-target during code review.

A reference stack that cages always-on agents like Hermes and OpenClaw inside hardened OpenShell sandboxes with managed inference and network policy.

A Rust TUI that scores hundreds of models against your actual hardware so you stop downloading 70B weights onto a laptop.

A skill that turns Claude, Cursor, or any agent host into a social-native research analyst, scoring signals by upvotes, likes, and actual money wagered.

A crowdsourced library of copy-paste academic writing prompts, gathered from researchers at MSRA, ByteDance Seed, and top Chinese universities.

OpenMAIC turns any topic into a multi-agent classroom where AI teachers lecture, peers debate, and everyone draws on the whiteboard.

Datawhale's open-source curriculum wants to turn LLM users into agent builders, not just prompt engineers.

Microsoft's SkillOpt treats a markdown skill document as the trainable parameter of a frozen LLM agent, complete with epochs, batching, and validation gates.