Lists (2)
Starred repositories
HTML is the new markdown. Lavish is the new editor for your HTML artifacts.
Native macOS menu-bar recorder: captures system audio (L) + mic (R) into one stereo file, with Gemini transcription
AI-Driven Life Cycle (AI-DLC) adaptive workflow steering rules for AI coding agents
This workshop teaches systematic approaches to evaluating Generative AI workloads for production use. You'll learn to build evaluation frameworks that go beyond basic metrics to ensure reliable mod…
FHIRPath-QA: Executable Question Answering over FHIR Electronic Health Records
The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
Agentic RL on Any Harness at Scale
Super simple group chat, without a subscription
Toolkit for Seamlessly Enabling RL Training on Any Agent with Bedrock AgentCore.
agent first cli with full schwab api parity
Hermes WebUI: The best way to use Hermes Agent from the web or from your phone!
Rust CLI that converts EPUBs into a single YAML-headed Markdown file with per-chapter byte and line offsets, giving LLM agents a navigation API for token-efficient reading.
Drop agents inside running marimo notebook sessions
Skills for Real Engineers. Straight from my .claude directory.
A Bun CLI that ingests Claude Code and Codex session transcripts, generates LLM-powered daily summaries, and serves a browsable web UI for your engineering journal.
Causal Judge Evaluation: calibrate LLM-as-judge scores against oracle labels with valid uncertainty.
Tangle is a web app that allows the users to build and run Machine Learning pipelines without having to set up development environment.
🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models
A drop-in code interpreter using the Monty Python emulator for DSPy's RLM module.
Autonomous experiment loop extension for pi
Using Python and DSpy’s Recursive Language Model implementation to handle unbounded context lengths.
Continuous background code review database for agents, work faster and smarter with accountability for every line of generated code.
The agent that grows with you
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
Adaptive Test-time Learning and Autonomous Specialization
Terminal UI for browsing, searching, and resuming Claude Code sessions