A C++, header-only library for constructing JSON and JSON-like data formats, with JSON Pointer, JSON Patch, JSON Schema, JSONPath, JMESPath, CSV, MessagePack, CBOR, BSON, UBJSON, toon-format

Context compression plugin for Claude Code. Trims large JSON, logs, stack traces, and source files before they enter the context window.

toon4s: Token-Oriented Object Notation for JVM

Turning messy repos into weapons of mass structured context.

⚜️ An MCP server for context compaction and recycling in Claude Code

hight performance .NET implementation of TOON (Token-Oriented Object Notation), delivering compact, human-readable serialization with encoder/decoder APIs, multi-target support (.NET Standard 2.0, .NET 6–10), and advanced features like key folding, path expansion, and Tabular list handling tailored for LLM-friendly logging.

The missing Middleware for reducing LLM API costs through TOON format by converting JSON to TOON automatically with 30-60% token savings with no code changes.

Production-ready RustAPI framework examples: REST APIs, GraphQL, microservices, JWT auth, real-time WebSockets, TOON format, MCP servers, and serverless. Complete with learning paths and comprehensive documentation.

A Zig implementation of the TOON (Token-Oriented Object Notation) format.

Toon Plus format

TOON format parser for Julia

Nim implementation of TOON (Token-Oriented Object Notation): compact, human-readable JSON serialization and parsing for AI and LLM prompt workflows.

High-performance .NET serialization library for TOON format - 40% fewer tokens for AI/LLM, expression tree-based (10-100x faster)

A lightweight GitHub code search CLI for AI agents, outputting in a token-efficient TOON format.

Zig implementation of TOON (Token-Oriented Object Notation).

Lucee toon-format ext

Structural analysis for codebases. Produces dependency graphs, class hierarchies, and cross-boundary coupling maps via language plugins -- compressed into token-efficient formats for LLM context windows. Multi-format output including TOON.

Experiments chain of thought prompting for pH regression in a cold start setting

Architecture, vision, and design docs for Agentic Forge

CodeGraphX is a local, token-efficient indexing engine that maps codebase dependencies for AI agents. By storing data in a high-density TOON format and serving it via MCP, it eliminates expensive file re-scanning and cuts token usage. It features O(1) symbol lookups and a real-time dashboard, agent with persistent, low-latency architectural context