Search

Interoperate between AI providers using the OpenAI Responses API as a common interface.

Deterministic, training-free lexical compression for LLM prompts.

Flat-rate cloud LLM inference service. Same CLI as Ollama, predictable pricing.

```js const pkg = require("agentic-os");

Agentic AI for SDLC

Agentic Payment CLI — agents own money

Admin UI for Dineway Agentic Web builder

RAG AI client using GroundX + GitHub Models

None

Unstable experiments with pycord.

Durable, explainable long-term memory for the llm CLI, powered by Engram (Lumetra)

Embeddable AI engine for inference, embeddings, vector search, and fine-tuning

RAG AI client using GroundX + GitHub Models

A Tiny VM for LLM-Powered Programs

A private, local LLM-powered data dictionary parser and entity mapper with automated cleaning.

SUAVE: Sparse Uncertainty-Aware Vector Encoding — A novel LLM algorithm that solves hallucination at the architectural level

A tool to generate and apply git diffs using LLMs

The AI video skill for Claude Code that learns — end-to-end generation across 6 models (Seedance 2.0, Kling, Wan, Veo, OmniHuman) with a self-improving quality-control loop

Claude Code skill: generate images from markdown prompts via Gemini, upload to Cloudinary, return optimized URLs

Multi-agent code audit skill for Claude Code — Opus orchestrator + parallel Sonnet specialists + Haiku baseline. Modes: full, differential, targeted.