Ryan Shea shea256
- New York, NY
- https://www.shea.io
- @ryaneshea
- in/ryaneshea
- ryaneshea
Highlights
Lists (1)
Sort Name ascending (A-Z)
Stars
Lean Algorithmic Trading Engine by QuantConnect (Python, C#)
Evaluation dataset for AI systems intended to benchmark capabilities foundational to scientific research in biology
Cheap, hard, model-distinguishing capability evals (IFEval + more) for the Chinese open-weight models via TrustedRouter.
Cadence is a distributed, scalable, durable, and highly available orchestration engine to execute asynchronous long-running business logic in a scalable and resilient way.
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
A local dashboard for tracking your Claude Code token usage, costs, and session history. Pro and Max subscribers get a progress bar. This gives you the full picture.
The open source AI research agent.
Enchanted is iOS and macOS app for chatting with private self hosted language models such as Llama2, Mistral or Vicuna using Ollama.
On-device meeting capture, dictation, and vault-native knowledge layer for macOS. Nothing leaves your Mac.
Autonomous experiment loop skill for Claude Code β port of pi-autoresearch
Collaborator is a place to create with agents.
A CLI tool that automates the provisioning of GPU's across cloud providers and the running of AI experiments across them
A terminal workspace with batteries included
AI agents running research on single-GPU nanochat training automatically
Control Ableton Live via Open Sound Control (OSC)
π The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence...
Agent harness to publish your agent chat history as Huggingface datasets.
Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig
IronClaw is an Agent OS focused on privacy, security and extensibility
An agentic skills framework & software development methodology that works.
SGLang is a high-performance serving framework for large language models and multimodal models.
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Neural Networks: Zero to Hero
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI