MCP servers and skills: search, filter by where they run, and compare.
Context compression plugin for Claude Code. Automatically trims large tool output—JSON, YAML, stack traces, and logs—before it enters the context window.
Node.jsMIT★ 67No key
transparent TOON re-encoding for AI coding agent tool-call context
SkillAGPL-3.0★ 2Few starsNo key
MCP server for transparent TOON format optimization. Automatically converts data files to 30-60% more token-efficient format for coding agents with smart analysis and caching.
SkillMIT★ 5No key
TOON-MCP is a Model Context Protocol server that automatically converts verbose JSON structures into Token-Optimized Object Notation (TOON), reducing token consumption in AI-assisted development workf
SkillMIT★ 7No key
Token-Oriented Object Notation (TOON) & Semantic HTML standard for AI agents. 55-80% token reduction vs JSON/HTML with zero-build browser rendering.
SkillMITFew starsNo key
MCP server giving AI coding agents offline, token-efficient persistent memory — recall decisions, patterns, and bugs across sessions with 68.5% fewer tokens than re-reading context. No LLM, no server;
Node.jsMIT★ 12No key
Fast directory structure generator with LLM context support. Built for developers and AI agents.
Node.jsMIT★ 7No key
The AI-native wire format for structured data. 100% comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ lossless round-trips across 17 formats. Spec v3.5.1 Stable.
SkillApache-2.0★ 60No key
GCF Go implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
GoApache-2.0★ 7No key
GCF Rust implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
SkillApache-2.0★ 5No key
🥈 2nd Place @ MariaDB Hackathon Malaysia 2026 — TOON-Native Auto-Embedding & RAG Toolkit for MariaDB | Docs & Judges' Guide: https://mariadb-hackathon-my-2026.github.io/seamless-rag/
SkillApache-2.0★ 2Few starsNo key
GCF Kotlin implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
SkillApache-2.0★ 1Few starsNo key
GCF .NET implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
SkillApache-2.0Few starsNo key
MCP server that lets AI assistants animate in OpenToonz: editable vector levels, xsheet timing, real keyframes, anatomy-accurate character rigs with walk and run cycles, physics, and studio looks buil
PythonMITFew starsNo key
⚜️ An MCP server for context compaction and recycling in Claude Code
Node.jsMIT★ 11No key
MCP to provide harmony API and tool context
SkillMIT★ 1Few starsNo key
Observability and predictive memory tooling for LLM agents on Markdown vaults — predictive context-rot scoring, Ed25519-signed hash-chained journal, hierarchical tiering. 100% local. MCP server + Obsi
Node.jsApache-2.0★ 1Few starsNo key
An agentic memory database that cuts session tokens by 82–99%. One portable SQLite file — your agent's memory, anywhere.
GoMIT★ 129No key
Rust library and MCP server for crate API docs
SkillApache-2.0Few starsNo key
MCP server for Your Spotify analytics with TOON format support
SkillApache-2.0Few starsNo key
Smartest context aware Token Optimizer for mcp tools.
Node.jsApache-2.0★ 1Few starsNo key
Shrinks your AI agent's tool output so it burns fewer tokens, without changing what the agent reads. Lossless by default, no decode step.
PythonMIT★ 2Few starsNo key
A Model Context Protocol (MCP) server for accessing Fathom AI API endpoints (meetings, recordings, transcripts, summaries, teams, team members) via GET operations.
PythonMIT★ 2Few starsNo key
Who stands behind it
