One zero-dependency CLI for every MCP server and agent skill. Token optimization, tool discovery and context compression: 71,929 -> 581 tokens (-99.2%, measured), schemas stay out of context. One config for Claude Code, Codex, Cursor, every agent. 341KB, pure Python. | 零依赖 CLI：管所有 MCP 工具与技能，工具发现省 99.2% token。

Scene-aware storyboard for DeepSeek Harness: 9-16 numbered cells with timestamps + transcript + an audio envelope, packed into ONE image (384 tokens). Two tools: video_storyboard and video_zoom.

A live, local-first dashboard for Claude Code sessions: project graph of agents, tokens, tool feed, replay, alerts. Plugin + terminal UI + MCP server. Includes the AOS-1 agent orchestration spec.

Framework-aware code intelligence MCP server — 91 framework integrations, 81 languages, 72.7% fewer input tokens to review a pull request, comprehension at parity

One memory for your AI agents: scoped, expiring, revocable per-agent tokens and an audit log.

Craft is a Claude Code plugin that asks you the product questions and works out the technical ones. Features get planned, built, and tested, with your codebase read-only until you approve the work. Point at a live page to change it. The calls you make - decisions, design tokens, the tweaks you loved - carry into every build after.

Run efficiency for coding agents: share of paid tokens that became output, not context re-reading.

Fast and Accurate Code Search for Agents. Uses 99% fewer tokens than grep+read

Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.

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.

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.

Use when the user mentions wallet connect/sign in/sign out, check balance, send/transfer tokens, swap/buy/sell tokens, DEX trade, limit/market order, cancel order, get a quote, transaction history, wallet settings, daily limit, slippage, MEV protection, supported chains, send to ENS domain, send to

A single MCP gateway that lets every agent and login on your machines reach services like Notion, Sentry, Cloudflare, Gmail and Google Calendar after signing in once, with per-agent tokens. Calls that reach other people or can't be undone wait for approval first, and every call is logged.

Enables MCP-compatible AI agents to interact with Discord through a local Vencord plugin inside the native desktop client, providing over 30 tools for messaging, server management, roles, moderation, and invites without bot or user tokens in config files.

Enables Claude Code users to inventory the MCP servers, skills, commands, agents and plugins installed on their machine, estimate how many tokens each one adds to every request, and switch them off per project or globally, including across other AI coding tools. It also monitors live sessions to report real token usage and the savings achieved from disabled items.

Enables an LLM to orchestrate multiple downstream MCP tools inside one isolated sandbox in a single turn, filtering intermediate results in memory and returning only the final output to cut context tokens.

Enables AI agents to run free, no-signup Ethereum on-chain lookups over a remote HTTP endpoint: wallet ETH balance, contract/EOA detection, outbound transaction counts and simple risk heuristics, plus NFT metadata (name, description, image URLs, IPFS gateway links and raw tokenURI/uri JSON) for ERC-721 and ERC-1155 tokens. Reads only, with cached results and no key, account, or wallet connection required.

Enables AI agents to read and write a local-first Markdown/Obsidian notebook via a single capture call that routes text into the right notebook, board, or daily journal entry and returns related notes, alongside search, note and card management, and numeric metric series. Access is governed by per-agent tokens with read/write/admin scopes, optional folder restrictions, and an audit log of every action.

Run your real agent with and without your skills, MCPs, and rules. See which ones actually help, and what they cost in tokens. Supports Claude Code, Codex, Pi, and Hermes.

Enables an LLM to triage hard-to-extract Vue components by feeding it structured coupling analysis, dependency graphs, and design tokens, then generating decoupling suggestions with before/after code, composable wrappers for store-bound components, and full rewrite-and-extract operations.

Code intelligence for agents: find the code that matters and keep your context window and tokens lean.

Token Bank — the local LLM gateway that sits between your AI agents and every provider. Know where tokens go · Spend less with smart routing to Ollama, Groq, GitHub Models · Earn by sharing idle quota on a community P2P network. One-click onboarding for Cursor, Claude Code, Codex CLI, Gemini CLI — no agent changes. Full trace, seamless model swap

Enables AI agents to list and compare LLM API prices per million tokens, rank the cheapest models by context and keyword, look up GPU rental rates per hour by provider, and estimate self-hosting cost per million tokens against API pricing. Pricing data comes from OpenRouter's public models endpoint plus a dated GPU price CSV, with source URLs and explicit notes when data is missing.

Use Agent Pulse to inspect local AI-agent activity across Hermes, Claude Code, Codex, DeepSeek, OpenClaw, Copilot, Aider, Qwen, OpenCode, Goose, Cursor, Antigravity, and Amp logs. Use when the user asks about AI-agent sessions, tokens, tool/search calls, model usage, estimated cost, budgets, forecas