Search

gemini drawing MCP & skill through browser, can be used in openclaw or any agent that supports MCP.

Compress embeddings 8x instantly with TurboQuant. No training needed. Up to +8pp recall vs FAISS PQ at matched storage.

Terminal-based Claude Code usage limit visualizer with real-time burn-up charts

Think-block filter for LLM streams

Interface between LLMs and your data

The cLLM (chat-optimized Large Language Model, 'clem') framework tests such models' ability to engage in games, that is, rule-constituted activities played using language.

Claude AI skill for cinematic Higgsfield AI prompts — 18 sub-skills, MCSLA formula, Soul ID, Cinema Studio 2.0

Deep strategy analysis for any Polymarket wallet. Paste a profile link → get EV signals, market focus, trading style, and the strategy core. Claude Skill / CLI.

No description available

Git for humans: Innovation architecture for the AI age. Capture your work, protect your progress, travel through time — no coding required.

OntoGPT is a Python package for extracting structured information from text with large language models (LLMs), instruction prompts, and ontology-based grounding.

CLI for unattended AI-driven development with multi-backend support (Codex, Claude, Gemini, OpenCode)

Universal, infinite-memory proxy for LLM APIs.

A unified library for creating, representing, and storing speculative decoding algorithms for LLM serving such as in vLLM.

Use Composio to get an array of tools with your OpenAI Function Call.

Use Composio to get an array of tools with your Anthropic LLMs.

A dependency free prompts (not the LLM prompts) library built for CLI.

Shared LLM calling and event-sourced storage primitive for benchmark systems.

The pytest of LLMs — build, version, and run LLM eval suites from the terminal

CLI for running LLMs on Apple Silicon via MLX