Tokens Python Packages

flask-httpauth

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

2.3M 1K 236

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.

176K 2K 160

jcodemunch-mcp

The leading, most token-efficient MCP server for GitHub source code exploration via tree-sitter AST parsing

149K 2K 288

ypricemagic

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

63K 74 20

eth-portfolio-temp

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

24K 15 6

ape-tokens

Tokens converter plugin for the Ape Framework

22K 11 8

caliper-ai

Per-PR cost for your AI coding tools. Reads local Codex, Claude Code, Cursor, and Aider logs. Offline. No login. No SaaS. No telemetry.

12K 1 0

tokenxray

See where your AI coding tokens actually go.

11K 1 0

eth-portfolio

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

8K 15 6

token-throttle

Multi-resource rate limiting for LLM APIs. Reserve tokens before you call, refund what you don't use, stay under the limit across workers.

6K 18 2

zon-format

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

5K 71 6

sqz

Compress LLM context to save tokens and reduce costs

2K 269 11

tokenizerchanger

Library for manipulating the existing tokenizer.

743 21 1

lattice-transport

A complete transport layer for LLM traffic

536 0 0

openai-function-tokens

A package to estimate token counts for messages AND functions in openai's chat completion API.

492 19 1

costfuse

A fuse box for your AI bill. Drop-in budget guardrails and runaway-loop kill switch for AI agents.

458 0 0

ethtoken

Ethereum EIP20 Token Interface

434 43 20

parsimony-cli

Know where your Claude Code tokens go - usage tracking for subscribers

408 0 0

caveman-mcp

MCP server that cuts 65% of tokens by compressing markdown files and activating caveman speak.A thinner and simpler option for Brussee's Caveman — no file distribution, no sync. No API key. Works everywhere.

393 0 0

trackly

Zero-overhead AI cost and usage tracking for Python. Import the library, wrap your LangChain model, and every LLM call is automatically logged - tokens, cost, latency, and your own metadata.

318 4 0