A curated list on AI token economics: what tokens cost, where they get wasted, and how to cut the bill. Tools, benchmarks, papers, and copy-paste configs for the token economy of LLMs and coding agents.

A Lisp with first-class LLM primitives, implemented in Rust

MCE: Clone Human Souls with LLM Native Agent Skills | 基于 LLM Agent Skills 的心智克隆工程 | Agent Skills | Mind Skills | Mind Clone

Lightweight Long-Term Memory for LLM Agents.

Config-driven CLI tool that compresses command output before it reaches an LLM context

Control Ableton Live with any LLM: create tracks, arrange clips & compose music via MCP

Python sandboxes for llms

Clean up Claude's token vomit with a separate LLM. Save your tokens, Opus is hopeless

🏆 Curated, ranked list of AI agent harnesses (100+) — plus an MCP server, llms.txt & JSON so agents can recommend them too. Rescored weekly.

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

LLM-powered OpenFOAM MCP server for intelligent CFD education with Socratic questioning and expert error resolution

Go web crawler to scrape documentation sites and convert content to clean Markdown for LLM ingestion (RAG, training data).

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

⏰ Time MCP Server: Giving LLMs Time Awareness Capabilities

An MCP server implementation enabling LLMs to work with new APIs and frameworks

docx ↔ LLM translator. Projects .docx office files to Markdown for editing. Projects edits back to OOXML as tracked changes (redlines). Python and Node.js implementations.

Memory server for llms that can be easily integrated to any client.

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.

An MCP server for Google Tag Manager. Connect it to your LLM, authenticate once, and start managing GTM through natural language.

Build mods for Claude Code: Hook any request, modify any response, /model "with-your-custom-model", intelligent model routing using your logic or ours

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

An agent skill to evolve the quality of LLM-Wiki (Graphify) at test time.

Agent-first local harness for OKF-compatible LLM Wikis.

Governance standard and reference toolset for LLM-maintained knowledge corpora