Highlights
- Pro
Stars
Agentic clinical research environment, built on T3 Code
A FHIR® Extraction Tool for structured, consent-compliant data extraction
Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (N…
Orchestrate sandboxed coding agents in TypeScript with sandcastle.run()
CLI security is broken. The packaging layer is where we fix it.
An organizable, terminal-first agentic workspace with plugins
Skills for Real Engineers. Straight from my .agents directory.
TrialMatchAI leverages large language models to streamline clinical trial matching by evaluating patient-specific clinical characteristics against trial eligibility criteria and generating relevant…
The open-source AI workbench for scientific research
Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.
Open-source foundation of the user-sponsored PyMOL molecular visualization system.
Your GitHub stats, turned into a World-Cup-style player card
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
The best way to control Claude Code, Codex and more from any computer or phone
Learn how to design large-scale systems. Prep for the system design interview. Includes Anki flashcards.
🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
MCP servers for Apple apps (Notes, etc.) on macOS via AppleScript
Self-hosted platform to unify wearable health data through one AI-ready API.
A unified framework to detect, benchmark, and mitigate shortcut learning in machine learning models across medical imaging and beyond.
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
Run agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference
A package for autoencoders/tokenizers also applyable for 3d medical data.
The MEDS Decentralized Extensible Validation (MEDS-DEV) Benchmark: Establishing Reproducibility and Comparability in ML for Health
AI agents running research on single-GPU nanochat training automatically
Self-hosted MCP proxy that gives AI agents fine-grained access to your accounts (e.g. GMail, GCal, Outlook) – without giving away the keys.
GitNexus: The Zero-Server Code Intelligence Engine