Python SDK for dataset generation on LightningRod platform ⚡
-
Updated
Apr 17, 2026 - Jupyter Notebook
Python SDK for dataset generation on LightningRod platform ⚡
Template-aware development workflow plugin for Claude Code.
A powerful Model Context Protocol (MCP) server and Omni-AST engine. It empowers AI agents to seamlessly parse complex codebases, execute secure cross-project operations, and dynamically fetch token-optimized rules.
finasys: Fast financial data processing, feature engineering & AI agent toolkit
AI agent skills library built by OpenSite AI. A single git repo that keeps Claude, Codex, Cursor, Copilot, and Perplexity Computer in perfect skill sync, with persistent cross-session memory and automated cloud upload via Playwright.
Fast BPE tokenizer with guaranteed perfect text reconstruction. 2x faster than tiktoken at encoding/decoding while preserving all whitespace and formatting.
CLI for DeadLibrary.
Context composition engine for AI systems. Builds structured prompt payloads from Markdown artifacts and renders them for OpenAI, Anthropic, and agent frameworks.
A reasoning framework plugin for Claude Code that helps LLMs catch distributed system bugs before they reach production.
A Claude Code agent harness — 6-gate workflow + Ralph loop + 9 stack tracks. Lean by design.
Local-first AI shorthand interpreter and Codex habit pipeline for turning repeated user phrases into structured, reviewable intent hints.
Zero-dependency, deterministic MCP server implementation. Rejects "magic" decorators for rigid Pydantic enforcement and explicit architectural control.
Python toolkit and JSON-first CLI to fetch YouTube channel top videos and transcripts via YouTube Data API v3.
Bounded multi-agent coding CLI with guided owner path and experimental QueenBee beta support.
Conduct AI agents like a CEO — orchestrate, delegate, ship.
Safety-first self-improvement loop for AI agents — auto-rollback on regression, pure stdlib, MIT
CLI tool to transplant MTP weights between Hugging Face models by extracting and merging safetensors.
Five functional scars and four Claude Code hooks I use in production. Companion code to 'The Lucy Syndrome and AI' — an essay on why LLMs forget every morning and what an operator can do about it.
VibeCode creates cryptographically verified Digital Twin snapshots—immutable PDFs that serialize entire codebases with full restoration. Powered by large-context LLMs, it combines multi-agent workflows (file selection, context generation, tool orchestration) with semantic RAG, security quarantine, and bidirectional MCP integration. Code as data.
Session state persistence for AI systems. MCP server providing crash recovery, decision registry, and context compression — so AI assistants pick up exactly where they left off.
Add a description, image, and links to the llm-tooling topic page so that developers can more easily learn about it.
To associate your repository with the llm-tooling topic, visit your repo's landing page and select "manage topics."