- Redmond, WA
- http://www.iunknown.com
- @john_lam
Stars
Multi-backend CLI for executable markdown prompts. Run .md files against Claude, Codex, Gemini, or Copilot.
View your beads (Steve Yegge's task management system for coding agents) like a king.
💫 Toolkit to help you get started with Spec-Driven Development
Ruby gems for general-purpose AI agent systems: automation, research, data processing, customer support, content creation. SwarmSDK provides single-process orchestration, persistent memory with sem…
Xterm/VT100 Terminal emulator in Swift
TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM gateway, observability, optimization, evaluation, and experimentation.
A benchmark for LLMs on complicated tasks in the terminal
Use Claude Code with any LLM provider - GLM-4.5, Kimi-K2, Qwen3-Coder, DeepSeek, etc.
A community-driven knowledge base of practical patterns for Effect-TS.
LuLu is the free open-source macOS firewall
A CLI tool for analyzing Claude Code/Codex CLI usage from local JSONL files.
Convenient CLI tool for generating shareable transcripts of Claude Code sessions
A Model Context Protocol server for converting almost anything to Markdown
Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports local and cloud LLMs (Ollama, Google, Anthropic, ...). Searches 10+ sources - arXiv, PubMed, web, and yo…
A Conversational Speech Generation Model
🕷️ An undetectable, powerful, flexible, high-performance Python library to make Web Scraping Easy and Effortless as it should be!
aider is AI pair programming in your terminal
Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/CPU ONNX and NVIDIA GPU PyTorch support, handling, and auto-stitching
My go-to rules for using Cursor and LLMs in software development.
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
Recipes to scale inference-time compute of open models