Sandbox
14 repos for tokens · Gemini CLI · DocsClear
FreePeak/
LeanKG
FreePeak/LeanKGConnectors

LeanKG: Stop Burning Tokens. Start Coding Lean.

217
activeing123/
mcptoon

MCP tool lists eat 71,929 tokens at 255 tools — more than half a 128K window before you ask anything. mcptoon reads the same tools back at 581 (-99.2%, measured). 128KB CLI, zero deps. Compute your own: activeing123.github.io/mcptoon/tools/token-tax

195
edouard-claude/
snip

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

440

Save 94% on AI coding tokens. Index your codebase, agents search instead of reading files. Works with Claude Code, Codex, Copilot, Cursor, Gemini CLI. Local MCP server, free, open source.

413
claudioemmanuel/
squeez

Hook-based token compressor for 5 AI CLI hosts (Claude Code, Copilot CLI, OpenCode, Gemini CLI, Codex CLI). Up to 95% bash compression, signature-mode for code reads, cross-call dedup, MCP server, self-teaching protocol. Zero runtime deps.

200
jgravelle/
jdocmunch-mcp

The leading, most token-efficient MCP server for documentation exploration and retrieval via structured section indexing

203

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

125

A headless browser for AI agents that fetches modern web pages, runs JavaScript, manages sessions, and returns token-efficient Markdown.

86

30 sec to give your AI agents persistent memory. Reduce 90% token consumption while also maintaining quality.

466
CodeAlive-AI/
codealive-mcp

Context engine for large codebases, exposed through MCP. Gives AI coding agents precise repository context; benchmarked at frontier-agent quality with ~25x lower model cost and 45% fewer tokens with semantic search.

90

Make your agents talk human. ADHD-friendly output styles for Claude Code, Codex, and others. So you can pay attention, not tokens.

1k
atlassian/
atlassian-mcp-server

Official remote MCP server for Atlassian. Securely connect Jira, Confluence, Jira Service Management, Bitbucket, and Compass to Claude, ChatGPT, Cursor, VS Code, and other AI tools using OAuth 2.1 or API tokens.

1k
fajarhide/
omni

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.

369

HEDGEHOG codes Cleaner, Faster and with Fewer Tokens. Hedgehog's AI-driven development builds a task dependency graph from your spec-driven, BMAD-METHOD plan, so Claude Code, Cursor & Gemini CLI stay locked to it. A CLI-enforced state machine for agentic coding. Now builds DeepSeek DSH Plugins. DeepSeek Harness、DSH 插件、AI 编程、BMAD 方法. AI Copywriting

38