v0.16.305 · MIT
Bring SynthesisUI design systems into any project - tokens, typed components, whole pages and an agent-ready CLAUDE.md manifest.
— · GPL-3.0
The Design Tokens Multitool. CLI and go library; LSP and MCP; Generator and converter
v0.2.9 · MIT
Desktop cockpit for DeepSeek Harness (dsh): token usage & cost tracking, budget alerts, runtime auto-update with rollback, Quick Ask hotkey, scheduled tasks, session search. Win+macOS. DeepSeek Harness 桌面驾驶舱:成本/用量监控 · 自动更新 · 定时任务
v0.1.1 · MIT
Shorter replies with Claude Code. Save output token spend.
v1.3.6 · BSD-3-Clause
DeepSeek / OpenCode Go / OpenAI 额度悬浮窗:输入框上方显示,支持 DSH 模型列表同步、自定义额度接口、可拖动、主题适配;内置 DSH 会话 token 用量统计(按 日/月/模型)与官方峰谷价费用估算。
— · Apache-2.0
ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.
v1.1.0 · MIT
Tech-lead orchestration for Claude Code — the top-tier model (Fable) keeps architecture & decisions, cheap subagents (Sonnet/Opus) do the routine and the digging. Save tokens without losing quality.
— · Apache-2.0
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.
v1.5.1 · MIT
Claude Code plugin: Fable 5 as a token-frugal orchestrator with tiered Opus/Sonnet/Haiku agents
— · MIT
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.
— · Apache-2.0
Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they touch, and proves what they save. 60–90% fewer tokens as the receipt. 76 MCP tools, 30+ agents, local-first.
— · Apache-2.0
High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, based on graph, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local. Discord: https://discord.gg/39MFHu3J5d
v0.9.12 · MIT
Claude Cup — worldwide building contest. Track your Value/Token Ratio, climb the real-time leaderboard, and fill a live trophy in your terminal.
v3.0.0 · MIT
MCP server that lets Claude Code delegate heavy-token tasks to DeepSeek, Kimi, GLM, Qwen, Grok, or any OpenAI-compatible model. Claude orchestrates; the delegate does the heavy lifting. Zero dependencies.
v0.1.0 · MIT
Figma to design.md — Convert Figma design tokens into structured design.md for AI-assisted coding (Cursor, Claude Code, Copilot)
— · no license
Token-efficient Claude Code workspace with parallel agents and persistent memory. Research → Plan → Implement → Validate workflow.
— · MIT
Agent 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..
v0.2.17 · Apache-2.0
Usage statistics for DeepSeek Harness: aggregated token and cost metering per session, per day, per week, per month and over custom date ranges, with per-model breakdown, peak-hour pricing, durable daily history, a Settings usage panel and the /usage comm
— · MIT
Agent 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..
v0.31.1 · Apache-2.0
The best DeepSeek Harness plugin for context insight and management, with context dashboard / browser and context command, for context statistics, composition, breakdown, evolution details, understanding how the context is made of, and how it evolves. 一站式 DeepSeek Harness 上下文可视化插件,Context 面板及浏览器与 Context 命令,透视上下文组成、演进、压缩、剪枝等事件与动作。
v0.9.21 · MIT
See where your AI spend goes - by task, tool, model, and project
v1.1.2 · MIT
Image generation (gpt-image-2) and GPT-5 subagents for Claude Code — through the Codex CLI login you already have. No OpenAI API key.
v1.4.0 · MIT
Context-as-image compression proxy for LLMs: renders bulky context (system prompt, tool docs, history) as dense PNG pages with exact per-provider billing math (Anthropic/OpenAI/Gemini). Node and Cloudflare Workers. Part of the OmniRoute family.
v1.2.1 · MIT
Claude Code skills for the work that keeps a design system alive