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.

Measure token savings per AI coding agent, optimize context, and share a live local knowledge graph across 16 CLI clients.

Local AI API gateway for OpenAI / Gemini / Anthropic. Runs on your machine, keeps tokens counted (SQLite), offers priority-based load balancing, optional OpenAI Chat↔Responses format conversion, and one-click setup for Claude Code / Codex.

OpenSquilla — Token-Efficient AI Agent with same budget, higher intelligence density

Extract any website’s design system into tokens in seconds: logo, colors, typography, borders & more. One command.

Every file not opened. Every folder not explored. Tokens saved. ProjectAtlas guides coding agents with purpose metadata and an intelligent code graph, reducing token costs by over 90%.

MCP server for token-efficient large document analysis via the use of REPL state

Token usage tracker for (not only) OpenCode

Portable project memory across Claude Code, Codex and OpenCode, plus token accounting measured from harness transcripts. Local file I/O, no API calls, no telemetry.

Generate a compact codebase index for AI assistants — saves 50K+ tokens per conversation

MCP server for Git with local Ollama — zero tokens for git operations

Extract design tokens (colors, typography, spacing, border radius, shadows) from any public website. Generates JSON and CSS custom properties for local projects. Available as an AI agent skill (Claude, Cursor, Codex) and standalone CLI.

Token-efficient, local-first CLI tools for coding agents - compact Maven, npm/Node, and Go test output plus reusable development helpers.

Open-source platform for multi-agent AI orchestration, real-world asset tokenization, and institutional-grade workflow automation. Includes OAuth 2.1 MCP agent management, a 44-field RWA schema, Stripe subscription billing, and a Cryptographic Airgap architecture designed to integrate with AetherNet QUAS post-quantum settlement.

Context engineering for AI agents. ~80% fewer tokens. Fix tool overload. Skills and memory with in-process BM25 and semantic retrieval. Progressive Disclosure. No vector DB.

Up to 71.5x fewer tokens per session on Claude Code with Obsidian + Graphify. Persistent memory, codebase knowledge graphs, and chat import pipeline. 🇧🇷 PT-BR included.

Self-evolving memory OS for LLM & AI Agents: ultra-persistent memory, hybrid-retrieval, and cross-task skill reuse, with 35.24% token savings and DeepSeek Harness support.

MCP for semantic code search & navigation that reduces token waste

An agentic memory database that cuts session tokens by 82–99%. One portable SQLite file — your agent's memory, anywhere.

Local-first telemetry collector for AI coding agents — unified OpenTelemetry events for Claude Code, Codex, Cursor and more. Token usage, cost, traces and security audit, exported anywhere.

Extract any website's complete design system with one command. DTCG tokens, semantic+primitive+composite, MCP server for Claude Code/Cursor/Windsurf, multi-platform emitters (iOS SwiftUI, Android Compose, Flutter, WordPress), Tailwind v4, Figma variables, shadcn/ui, CSS health audit, WCAG remediation, Chrome extension. MIT, Playwright, Node 20+.

Quickly reads webpages and converts to markdown for fast, token efficient web scraping

Open-source control plane for your AI agents. Connect tools, hire agents, track every token and dollar

Code Mode inspired local sandboxed MCP Gateway - collapses N servers x M tools into 2 tools (~1,000 tokens)