01 / Agent runtime
term2
An open terminal agent runtime for local and SSH workflows, with provider-flexible models, guarded execution, durable conversations, and delegated work.
First-party runtime · 5 modes · SSH · Sandbox · Background agents
Work / selected systems
Building across the intelligent software stack.
From agent runtimes and code context to complete AI products and browser-native machine learning. The technologies change; the work stays focused on clear boundaries and useful systems.
Core work / 01—04
Systems with enough depth to teach me something.
02 / AI application
ChatForge
A full-stack AI workspace for tool orchestration, model comparison, conversation branching, memory, and browser automation.
Next.js · Node.js · SQLite · Electron
03 / Code intelligence
code-rag
Semantic code search that turns syntax-aware code chunks into useful context for developers and coding agents.
Tree-sitter · Embeddings · Vector search · MCP
04 / Applied machine learning
easyocr.js
A TypeScript implementation of the EasyOCR pipeline designed to run in Node.js and browsers without Python at runtime.
TypeScript · ONNX Runtime · Node.js · Browser
Smaller tools / 05—07
Focused experiments and useful edges.
- 05 OCRAn OCR application that runs the recognition pipeline directly in the browser. Browser ML
- 06 ink-promptA focused prompt toolkit for interactive terminal applications built with Ink. Developer utility
- 07 Advisor Skills for Claude CodeA set of advisor skills for consulting specialized models during complex engineering work. Agent workflow