PyPI · npm94Exceptionalhealth index
jgravelle/jcodemunch-mcpCut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.
Python★ 2,675↓ 85.3K/moSep 9, 2026
npm89Excellenthealth index
Dave-London/PareDev tools, optimized for agents. Structured, token-efficient MCP servers for git, test runners, npm, Docker, and more.
TypeScript★ 138↓ 4,687/moSep 10, 2026
npm89Excellenthealth index
toon-format/toon🎒 Token-Oriented Object Notation (TOON) – compact, human-readable serialization of JSON data for LLM prompts. TypeScript SDK, CLI, benchmarks.
TypeScript★ 25.4K↓ 4.7M/moSep 16, 2026
PyPI83Excellenthealth index
JingbiaoMei/TokdashAgent Dashboard: Visualization and analytics for Sessions and Quota Usage. Track, analyze, and optimize token usage across providers with heatmaps, cost tracking, token counting and quota resets..
Python · HTML★ 84↓ 3,402/moOct 3, 2026
npm83Excellenthealth index
raymondchins/agentmapStop your coding agent reading the wrong files. Compiler-grade TS/JS repo map — 100% precision on blast radius vs grep's 60%, measured on public repos. CLI + MCP server, fully local, no vector DB.
JavaScript★ 48↓ 1,106/moSep 13, 2026
PyPI · crates.io · npm +180Excellenthealth index
ISON-format/ison🔥 Token-efficient JSON alternative for LLMs & agentic AI — same data, fewer tokens. Python · JS/TS · Rust · Go · C++
Python · Rust★ 127↓ 1,198/moSep 30, 2026
TypeScript★ 4↓ 4,865/moSep 6, 2026
toon-format/specOfficial specification for Token-Oriented Object Notation (TOON)
JavaScript★ 324↓ 722/moSep 14, 2026
PyPI · npm67Goodhealth index
CorvinLabs/CorvinOSSelf-hosted agentic OS — a Vibe-Engineering platform for Builders. Connect Claude Code, Codex or Hermes Agent to Discord, Telegram, WhatsApp, Slack & Email. EU AI Act 2026 & GDPR compliance by architecture.
Python★ 10↓ 1,020/moSep 13, 2026
kompassdev/kompassNavigate your way - manual steering, steered autonomy, or autonomously. Kompass keeps AI coding agents on course with token-efficient, composable workflows.
TypeScript · Astro · MDX★ 9↓ 4,456/moSep 14, 2026
Go · npm63Moderatehealth index
prasenjeet-symon/ogcodeThe token-efficient agentic coding workbench. Built for a future where every token counts — it optimizes token usage at the agent-loop level, saving 70%+ on long sessions, while planning, remembering your codebase, and shipping features in parallel from a single self-hosted binary.
Go · TypeScript★ 136Sep 10, 2026
Go · PyPI60Moderatehealth index
Clawdlinux/agent-native-formatToken-minimal system views for AI agents. Translate Kubernetes and live state into compact Agent Native Format with Go tooling and governed execution primitives.
Go · Python★ 1Sep 13, 2026
npm60Moderatehealth index
TaewoooPark/Agent-BlackboxLocal-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.
TypeScript★ 74↓ 130/moSep 12, 2026
blackwell-systems/gcf-goGCF Go implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
Go★ 7Oct 20, 2026
crates.io · Go60Moderatehealth index
dweve-ai/hedlToken-efficient data serialization for LLM/AI. 50% fewer tokens than JSON, 93% better value/token. Rust, schema validation, LSP.
Rust★ 77↓ 78/moSep 19, 2026
PyPI57Moderatehealth index
blackwell-systems/gcf-pythonGCF Python implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
Python★ 5↓ 11.4K/moOct 3, 2026
nawodyaishan/pdf2md-tuiHigh-speed PDF → Markdown ingestion engine for multimodal RAG pipelines. Extracts structured text + isolated images so downstream chunkers, LlamaIndex, and VLM agents get context that actually works
Go★ 4Sep 19, 2026
NuGet54Moderatehealth index
C#★ 8Sep 15, 2026
npm54Moderatehealth index
LuiggiVal08/toon-memoryMCP 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; works with 15+ agents.
TypeScript · MDX★ 11↓ 1,500/moSep 10, 2026
derinbarutcu17/costmaxxShrinks what agents read: 60.6% fewer model-visible tokens, full evidence kept lossless, savings self-measured.
Go · Python★ 1Oct 19, 2026
npm51Moderatehealth index
blackwell-systems/gcf-typescriptGCF TypeScript implementation. 100% LLM comprehension on every frontier model. 50-92% fewer tokens than JSON. 43B+ round-trips verified. Zero dependencies.
TypeScript★ 4↓ 187.4K/moSep 18, 2026
PyPI · Go50Moderatehealth index
blackwell-systems/gcf-proxyMCP proxy: zero-code GCF adoption. Wraps any MCP server, converts JSON to GCF mid-flight. 53-71% fewer tokens. Works with any structured data.
Go★ 11↓ 248/moOct 20, 2026
npm50Moderatehealth index
TypeScript · JavaScript★ 4↓ 2,461/moSep 9, 2026