Tokens Python Packages

flask-httpauth

Simple extension that provides Basic, Digest and Token HTTP authentication for Flask routes

headroom-ai

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

ypricemagic

Fetch accurate prices for tokens solely using on-chain data.

eth-portfolio-temp

Use eth-portfolio to output information about a wallet or collection of wallets in a streamlined, speed-optimized way.

ape-tokens

Tokens converter plugin for the Ape Framework

eth-portfolio

Use eth-portfolio to output information about a wallet or collection of wallets in a streamlined, speed-optimized way.

runcost-ai

Small polyglot cost ledger for LLM and agent API calls

token-throttle

Simple Multi-Resource Rate Limiting That Saves Unused Tokens. Rate limit API requests across different resources and workers without wasting your quota. Reserve tokens upfront, get refunds for what you don't use, and avoid over-limiting.

leancontext

Trim the redundant tool output your AI agent re-sends every turn. Deterministic, type-aware token reduction with a fidelity score — never breaks the agent.

zon-format

ZON → 35-70% cheaper LLM prompts than JSON/TOON. Zero overhead.

llmprof

pprof for your LLM context - see where every token and dollar goes.

tokenxray

Live cost alerts, hard-stop ceiling, and session analysis for Claude Code. The spending guard Claude Code doesn't ship with.

opentab-ai

📊 Browse your AI coding spend in the terminal — OpenCode, Claude Code, Codex & more

headroom-hardened

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

tokenizerchanger

Library for manipulating the existing tokenizer.

ruleprof

Ablate your CLAUDE.md / AGENTS.md rules to see which ones actually change agent behavior vs. just cost tokens.

sqz

Universal context intelligence layer — compresses LLM context across CLI, MCP, browser, and IDE

contextcram

llm · rag · context-window · tokens · prompt-engineering · token-budget · agents · python

foldback-ai

Lossless context compression for LLM agents — fold it down, fold it back. Compresses tool outputs/logs before the model, prompt-cache-preserving, 39–82% fewer tokens. pip install foldback-ai

tokenhabit

Scan your Claude Code logs and find the habits silently burning your tokens. No LLM calls, no deps, offline.

atlas-map

Fast Rust repo map for AI coding agents: token-budgeted signatures, imports, diff, and MCP.

llmstat

CLI-first, local LLM cost tracker for indie devs — drop it in front of any OpenAI-compatible API and watch token usage and spend in real time. No cloud, no signup.

cursor-usage

Cross-platform CLI for your Cursor (cursor.com) usage, spend & per-event logs — no API key needed.

skim-mcp

Lossless skim-then-expand MCP server: read big files, repos, and command output with far fewer tokens