Token Optimization

Fast Rust launcher for DeepSeek Harness, with clear Claude Code/Codex migration, model setup and lightweight local tools

CLI proxy that reduces LLM token usage by 60-90%. Declarative YAML filters for Claude Code, Cursor, Copilot, Gemini. rtk alternative in Go.

Independent research on Claude Code internals, Claude Agent SDK, and related tooling.

Delta MCP is a free app that sits between your AI apps and their MCP servers: any server, every tool. It checks each task before it runs, applies it all or nothing, reads back what it changed and lets you undo it. Far fewer tokens on multi-step tasks, and shortcuts that run on a schedule. Coming soon for macOS, Windows and Linux.

Carves your agent's tool outputs down to what matters. Never cuts what doesn't come back.

CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

Cut your AI coding agent's token bill on three axes: terse prose, YAGNI-first code, and tool-output compression. Claude Code, Pi, Cursor, Codex, Gemini + 4 more. Zero deps, published benchmarks including the runs it loses.

The open source runtime that turns your APIs AI-Native, without rebuilding them

A curated list of tools, benchmarks, papers, and copy-paste configs for AI token costs: what tokens cost, where they get wasted, and how to cut the bill.

Production-ready modular Claude Code framework with 30+ commands, token optimization, and MCP server integration. Achieves 2-10x productivity gains through systematic command organization and hierarchical configuration.

One command gives AI agents instant codebase context. ~250 tokens replaces 50,000+ tokens of exploration. Auto-configures Claude Code, Cursor, Aider.

Stop Claude Code from burning through your quota in 20 minutes. Auto-rotates oversized sessions and preserves context.

Three hooks that fix Claude Code's attention drift. Cited research, one-line install.

Working memory for Claude Code - persistent context and multi-instance coordination

Your agent pays twice for output it has already seen. OMNI returns a handle instead: 97.2% off a file read twice. Nothing deleted, nothing invented.

Enhanced fork of OpenWolf — a token-conscious second brain for Claude Code, with bounded storage, self-maintenance (openwolf doctor), .wolfignore scoping, and tunable retention. AGPL-3.0.

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.

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

Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.

Stop paying the multimodal tax. Your AI agent keeps every image it has seen but only sends the ones it needs: lighter chats, no endless reconnecting, no starting over. Works with Codex, Claude Code, Cline, Gemini CLI, OpenCode, WorkBuddy and more. Install once, forget it.

面向 AI Agent 的高并发、低延迟上下文治理与 Prompt Cache 守护网关 (Tree-sitter AST / Tool Delta / 50%~80% Token 削减)

An MCP server that executes Python code in isolated rootless containers with optional MCP server proxying. Implementation of Anthropic's and Cloudflare's ideas for reducing MCP tool definitions context bloat.

98-patent AI stack. Haiku reaches 93% of Fable 5 quality at 125x lower cost. Auto-activates from natural language.

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。