Search

3-round adversarial brainstorm between Claude and Gemini. One idea in, one converged decision out. Claude orchestrates, Flash researches, Pro reasons.

Gemini inside Claude Code. Second opinions, web-grounded facts, diagrams, brainstorms — one skill, five capabilities.

The only Telegram skill your AI agent needs. Read messages, parse channels, download voice notes. User API via Telethon.

A powerful AI agent skill that transforms rough ideas, notes, or documents into professional, visually structured slide decks and presentations.

Adaptive decision-making framework for AI agents. Think before you build. Quick / Standard / Scientific modes.

A Claude skill that writes the accurate prompts for any AI tool. Zero tokens or credits wasted. Full context and memory retention

Train small LLMs and deploy them for fast structured extraction on CPU

OpenAI-compatible AI chat pane + FIM completion for Spyder 6

A universal multi-model AI extension — interact with OpenAI, Gemini, and Claude through a single interface.

OpenAI & Ollama compatible API powered by your ChatGPT account

Semantic grep for codebases - local-first, SQLite-backed, with local or cloud embeddings

Semantic file search powered by Google Gemini embeddings

A lightweight Python library for calling LLMs through a unified interface with built-in caching, retry policies, and session management

Multi-LLM debate engine for architectural decisions

Convert a code repository into a single text file for LLM prompting.

CLI tool for TokTab LLM pricing data

Measure cost, quality, and performance of LLM API interactions

LangChain tools for the Unbrowse CLI — reverse-engineer any website into reusable API skills.

A unified benchmarking framework for local LLM inference backends

Python SDK for fin (badboy) - track LLM usage events; import as fin_sdk