Cost Tracking Python Packages

voicegateway

Drop-in observability and cost-control layer for LiveKit voice agents

caliper-ai

See what your AI coding cost and produced, from the logs already on your disk. Offline, no account.

tokenpak

Drop-in HTTP proxy that compresses LLM context, optimizes cache hits, routes smart, and tracks every dollar. Zero SDK changes required.

agentburn

See where your AI assistant burns money — and pay less. Local profiler for OpenClaw, Hermes Agent & Claude Code: who spends (cron/chats/helpers), the overnight bill, why (loops, retries, idle wake-ups), ready fixes, world model trends, community efficiency benchmark. Zero deps, nothing leaves your machine.

vibe-coding-tracker

Track AI coding costs in real-time — a lightweight Rust CLI/TUI for Claude Code, Codex, Copilot & Gemini usage and cost analytics

genai-otel-instrument

GenAI OpenTelemetry Auto-Instrumentation Library A comprehensive wrapper for automatic instrumentation of LLM/GenAI applications Supports all major LLM providers and MCP (Model Context Protocol) tool calls

pf-core

Dependency-light Python foundation for LLM apps, built for AI-assisted development.

modelmux

Model multiplexer — unified MCP server for cross-platform multi-model AI collaboration

agent-roi-tracker

Track the cost, usage, and ROI of your AI coding agents across every tool — local-first, model-free, cross-tool.

plutus-agent

Greek god of wealth — LLM provider credit & spend monitor for Hermes Agent that auto-balances model routing by runway.

cc-monitor

Real-time Claude Code token usage and cost monitor in your terminal

sandcastle-ai

Describe what you want. Go home. Sandcastle ships it. 6 AI providers, EU data residency, smart failover, cost intelligence, 20 step types, 236 templates. European-built, open source. pip install sandcastle-ai

ai-spend-tracker

Track AI coding agent token usage and spending across multiple platforms (Hermes, Codex, Copilot, OpenCode, Claude Code, OpenClaw, Kimi)

burndown

Local, real-time fuel gauge for your Claude credit burn — burn rate, runway forecast, budget check. Zero deps.

spanlens

Spanlens SDK for Python. Agent tracing, LLM usage capture, and cost observability.

codex-proxy

🚀 Lightweight LLM gateway — use any AI provider (Z.AI, Groq, Ollama, Anthropic, Gemini...) with Codex CLI, Cursor, or any OpenAI-compatible tool. Smart routing, cost tracking, JWT auth, document pipeline.

cost-katana

Cost Katana Python

shekel

LLM budget control and cost governance for AI agents. Python library for token budgets, usage limits and guardrails for OpenAI, Anthropic, LangChain, LangGraph and agentic systems.

last9-genai

OpenTelemetry extension for LLM observability - track conversations, workflows, and costs in Python AI applications

openclaw-cost-tracker-mcp

MCP server for AI agent token-cost telemetry across Anthropic, OpenAI, Gemini, Ollama — per-agent attribution, anomaly detection, model-routing recs with savings estimates, monthly forecast.

studiomeyer-aishield

Python LLM security middleware: prompt-injection, PII, tool-policy, cost-budget, audit. Port of ai-shield-core (TS).

llmkit-sdk

Know what your AI agents cost. API gateway with budget enforcement, session tracking, and MCP tools.

burnlens

Open-source LLM FinOps proxy — track OpenAI, Anthropic (Claude), and Google Gemini costs by feature, team, and customer. Zero code changes. pip install burnlens.

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.