Headless Angular components from the 4SH Design System: signals + Angular CDK, styled exclusively through design tokens. Ships a companion MCP server exposing the kit catalog and doc to AI coding agents.

Shorter replies with Claude Code. Save output token spend.

PostMCP core engine - OpenAPI parser, Token Diet, JIT router, and MCP protocol server

Local dashboard auditing Claude Code's per-turn token context (skills, agents, commands, CLAUDE.md, MEMORY.md, hooks, MCP) with toggle-based disable and session analytics.

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..

Figma to design.md — Convert Figma design tokens into structured design.md for AI-assisted coding (Cursor, Claude Code, Copilot)

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..

Context compression for AI coding agents: compresses tool output before it enters the model, dedups repeats to 13-token refs. Claude Code, Cursor, Codex, Kiro, Zed, any MCP client. Rust, zero LLM calls.

Image generation (gpt-image-2) and GPT-5 subagents for Claude Code — through the Codex CLI login you already have. No OpenAI API key.

Claude Code usage governor: compact professional output, context slimming, tool-output filtering, telemetry, and drift guardrails.

You say it. AutoCode ships it. 48 skills. Code to deployment in one session. iLang v5.0 judgment + secret-safe deploys. Free forever.

Usage billing dashboard plugin for DeepSeek Harness: sidebar cost metrics, real usage aggregation from session logs, current multi-provider pricing catalog

Your AI can write the UI. This makes sure it writes your UI. A deterministic scanner scores your design system 0-100 against 112 public repos, reads React and web components (Stencil, Lit), hands you a copy-paste fix prompt for each top finding, writes ru

Cut context bloat in your AI-agent stack: find and safely prune unused skills, MCP servers and subagents from real transcript evidence

Production-ready prompt library for Claude coding agents. APEI methodology, ~35 specialist prompts, current Claude Code coverage, plus a /find-prompt skill that routes any task to the right prompt.

DeepSeek Harness control center for balance, usage, peak/off-peak pricing, encrypted multi-account switching, health checks, reminders, recharge, and session controls. / 余额、用量、峰谷计费、加密多账户、健康检查、提醒、充值与会话控制

Quieter sessions for Claude Code: less narration, shorter tool output and concise answers focused on the result.

Pith is the hook that makes Claude Code sessions last 3x longer.

Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.

LeanCTX — Context Gateway for AI systems.

Your AI can write the UI. This makes sure it writes your UI. A deterministic scanner scores your design system 0-100 against 112 public repos, reads React and web components (Stencil, Lit), hands you a copy-paste fix prompt for each top finding, writes ru

Real-time execution trace and cost intelligence for Claude Code

Claude Code plugin that offloads large outputs to filesystem and retrieves when required.

Give your Claude Code Agent Teams a memory. Auto-injects role-specific context into every new teammate — your team never starts blind again.