@Octid-io
Basic information
Agentic AI instruction encoding. 86.8% smaller than JSON. Inference-free decode by table lookup. 342 opcodes, 26 namespaces, three conformant SDKs. Confirmed over LoRa mesh radio. Apache 2.0 with express patent grant.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"osmp": {
"command": "osmp-mcp"
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Osmp is an MCP server providing tools for the Octid Semantic Mesh Protocol (OSMP), an open encoding standard for agentic AI instruction exchange that works across any channel — from LoRa radio packets to cloud pipelines — using the same grammar, dictionary, and decode logic. It is designed for developers building multi-agent systems that need efficient, inference-free instruction encoding with no cloud dependency.
Install the server with pip install osmp-mcp and run osmp-mcp. Connect from any MCP-compatible client such as Claude Code (claude mcp add osmp -- osmp-mcp), Claude Desktop, or Cursor. The server exposes 9 tools: encode, decode, compound_decode, lookup, validate, discover, resolve, batch_resolve, and benchmark.
OSMP is an encoding‑layer protocol, not a framework. It operates beneath any framework protocol and works over any channel. It offers 86.8% compression vs JSON and inference‑free decode, features no other protocol provides.
The Python SDK has no dependencies beyond the Python standard library. The MCP server also requires only Python. TypeScript and Go SDKs have minimal dependencies (TypeScript uses fzstd; Go uses klauspost/compress/zstd).
Three domain corpora are shipped: ICD‑10‑CM (74,719 clinical codes), ISO 20022 (47,835 financial definitions), and MITRE ATT&CK Enterprise v18.1 (1,661 entries). All are resolvable by all three SDKs without network access.
Yes. No cloud access is required. The ASD dictionary and all shipped domain corpora are compiled into each SDK, enabling full offline operation. The protocol explicitly prohibits inference at the decode layer.
Measured benchmarks show 86.8% byte reduction vs JSON, 70.5% vs protobuf, and 76% fewer GPT‑4 tokens (cl100k_base). The BAEL floor ensures encoding never exceeds natural language length.
Open-source Python SDK & MCP interface for Priostack Agent Context Network (ACN). Zero-setup, autonomous memory orchestration for AI agents.
The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs
Shared memory for AI coding agents. Claude Code, Cursor and Codex read your project's decisions, lessons and tasks before they act.
Mess in, magic out: pour in your D&D and TTRPG notes and LoreKeeper keeps them as a private store for your world. Ask Claude or ChatGPT about it, or build a sourcebook.
Groundwork: company memory for your AI tools. Docs public. Source closed. Public proof needs no account.
Comments