Tag
Self-hosted AI gateway for 100+ LLMs in OpenAI format
Text-to-animation for any rigged skeleton, no per-rig retraining
Multilingual decision engine for typed answers without text generation
Self-hosted memory that makes AI agents smarter over time
Visual desktop companion for OpenAI Codex configuration
The minimal, self-extensible coding agent for the terminal
Lossless context compression for Claude Code and OpenCode
Drop-in LLM token compression. Code stays verbatim; prose compresses.
Token savings and persistent knowledge graphs for AI coding agents
352-provider AI gateway with automatic fallback and token compression
ADHD-friendly output rules for Claude Code. Action first, no filler.
Cuts LLM context use by up to 98% per session via local MCP sandbox
