AI labs have every economic incentive to maximize your token usage. Nobody is pushing back — until now. SuperLeanAI is an independent third party with one job: make sure you spend as few tokens as possible. We only make money when you save money.
Agents like Claude Code sends lots of information (10+ tool definitiones) on every LLM call. The labs have no incentive to make them short.
{ "name": "Bash", "description": "Executes a given bash command with optional timeout. Working directory persists between commands; shell state (everything else) does not. The shell environment is initialized from the user's profile (bash or zsh). IMPORTANT: This tool is for terminal operations like git, npm, docker, etc. DO NOT use it for file operations (reading, writing, editing, searching, finding files) — use the specialized tools for this instead. Before executing the command, please follow these steps: 1. Directory Verification: - If the command will create new directories or files, first use `ls` to verify the parent directory exists ... 2. Command Execution: - Always quote file paths that contain spaces with double quotes ... [... 4,500 more characters of instructions ...]", "input_schema": { "properties": { "command": { ... }, "description": { "description": "Clear, concise description of what this command does in active voice. Never use words like 'complex' or 'risk'... [200 more chars of meta-instructions]" }, "timeout": { ... }, "run_in_background": { ... } } } }
{ "name": "Bash", "description": "Executes bash commands with optional timeout.", "input_schema": { "properties": { "command": { ... }, "description": { "description": "The bash command to execute." }, "timeout": { ... }, } } }
SuperLeanAI is a transparent HTTP proxy. Point your agent's BASE_URL to v1.superleanai.com (e.g. via ANTHROPIC_BASE_URL) and you're done.
Verbose, multi-paragraph tool descriptions are summarized to a single sentence. The model still understands the tool — it just costs 92% less to say so.
Block tools your agent doesn't really need (e.g. NotebookEdit, Grep). Or use agressive bash_only mode: strip everything down to just Bash, Read, and Edit — the minimum set for most coding tasks.
Override the model on the fly — swap Opus for Sonnet during bulk tasks, or route different profiles to cheaper models without touching agent code.
Built as a production-grade proxy with JWT auth, per-session stats, and live savings.
Every session gets live stats: original tool bytes, debloated bytes, total traffic, and percentage saved. Know exactly what you're not paying for.
Route to OpenRouter, Google Gemini (via googleapis), Groq, or Together AI. Configure named profiles — groq, googleapis_minimal — with different strategies per use case.
Every request is saved to disk as JSON. Replay, audit, or analyze your agent's traffic. Tool calls from the response are also captured for future debloating.
Speaks the Anthropic /v1/messages API. Works with Claude Code, custom agents, any client targeting the Anthropic SDK. No code changes required.
Point your agent to the proxy, and start saving. Works with Claude Code, Codex, your own agent, whatever.
For Claude Code, set ANTHROPIC_BASE_URL in your environment or .claude/settings.json to https://v1.superleanai.com/lean.
Our incentives are completely aligned with yours. We take a small cut of the savings — if you don't save, you don't pay. Crystal clear, no subscription traps.
Get started →