lacausecrypto

MCP Sophon — AI skill for Claude Code

AI community

Deterministic context compressor for MCP agents.

How to install MCP Sophon

This entry records only its repository, not the path inside it, so there is no exact command to give. Open lacausecrypto/mcp-sophon and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What MCP Sophon does

Deterministic context compressor for MCP agents. Slots in front of prompt caching, mem0, Letta, or Claude Code. Single Rust binary, zero ML at query time.

Alternatives in AI

Sentrux — Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improveme 2.9k ★
Agenvoy — Self-hosted AI agent harness in a single Go binary — writes, sandbox-tests and repairs its own tools, and lets 474 ★
Octocode — Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in o 464 ★

README

Sophon

**Deterministic context compression for MCP agents.** One Rust binary. Zero ML at query time. Reproducible benchmarks, real-data measurements.

[![npm version](https://img.shields.io/npm/v/mcp-sophon.svg?color=blue)](https://www.npmjs.com/package/mcp-sophon) [![npm total downloads](https://img.shields.io/npm/dt/mcp-sophon.svg)](https://www.npmjs.com/package/mcp-sophon) [![GitHub release](https://img.shields.io/github/v/release/lacausecrypto/mcp-sophon?sort=semver)](https://github.com/lacausecrypto/mcp-sophon/releases) [![CI](https://github.com/lacausecrypto/mcp-sophon/actions/workflows/ci.yml/badge.svg)](https://github.com/lacausecrypto/mcp-sophon/actions/workflows/ci.yml) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](./LICENSE) [![Rust 1.75+](https://img.shields.io/badge/rust-1.75%2B-orange.svg)](https://www.rust-lang.org) [![MCP](https://img.shields.io/badge/MCP-2025--06--18-purple.svg)](https://modelcontextprotocol.io) [![Tests](https://img.shields.io/badge/tests-405%20Rust%20%2B%204%20Python-brightgreen.svg)](./BENCHMARK.md)

Sophon is a deterministic context layer for agents speaking the Model Context Protocol. It compresses prompts, conversation memory, code digests, file deltas, and shell output — without an embedding model at query time, without a GPU, and without API keys.

**Single 5.2 MB Rust binary.** MCP-native. `cl100k_base`-accurate. Default build pulls no Python, no ML weights, no network.

What it does, in 30 seconds

Tool	What it solves
`compress_prompt`	Long structured prompt → keep only sections relevant to the query
`compress_history`	Growing conversation → summary + facts + recent window + optional retrieval
`compress_output`	Shell stdout/stderr → 21 domain-aware filters (git, cargo, docker, kubectl, JSON, …)
`read_file_delta` / `write_file_delta`	Re-reads + edits → diffs only, never the whole file
`encode_fragments`	Repeated boilerplate → single token refe