Model Context Protocol (MCP) server for floating-point conversions. Encode, decode, and convert numbers across FP32, FP16, BF16, TF32, FP8, FP6, FP4, and integer formats, with binary/hex breakdowns and precision-loss analysis.

Google Cloud Logger destination for [jlog-facade](https://github.com/fp8/jlog-facade)

Simple Config Reader

Cross-platform command-line tool for floating-point conversions. Encode, decode, and convert numbers across FP32, FP16, BF16, TF32, FP8, FP6, FP4, and integer formats, with binary/hex breakdowns and precision-loss analysis.

Google Cloud Helpers

Makora provider extension for pi - Access DeepSeek V4, GLM 5.2, Kimi K2.7 Code, Llama 3.3, Qwen 3.6, and more through the Makora inference API

Run Claude Code with NeuroSpark and other OpenAI-compatible providers.

Sogni SDK - AI image, video & audio generation plus LLM chat with vision via the Sogni Supernet (Stable Diffusion, Flux, WAN 2.2, LTX-2, Seedance, HappyHorse, Qwen VLM)

Installer for configuring agents to use the Tropass remote MCP gateway.

Logger façade that focusing on creating a JSON output for typescript projects

MCP server for Volt HQ — the compute price oracle for AI agents

xInfer — a high-performance LLM inference engine in Rust with CUDA/Metal acceleration

Cloudflare Playwright Tools for MCP

Makora provider plugin for OMP — Access DeepSeek V4, GLM 5.1, Kimi K2.6, Llama 3.3, Qwen 3.6, and more through the Makora inference API

First-party NEAR AI Cloud TEE inference provider plugin for elizaOS.

Framework-agnostic core for tinytipy: grapheme diff, Korean IME composition frames, and a pure morph planner.


Reference client for the mtok.market non-custodial token spot market: manages agent identity + wallet and pays on-chain however the market asks.

HyperCharm provider extension for pi - Access DeepSeek, GLM, Kimi, Qwen, MiniMax, Gemma, and GPT-OSS models through the Charm Hyper API

GMI Cloud provider for the Vercel AI SDK.