PyPI Stats
  • Insights
  • PyPI
  • GitHub
  • Search
  • Compare
  • Advisories
  • Ecosystem
  • About
Home

Search Packages

Find Python packages by name, description, GitHub topic, or filter by metrics
Helicone
helicone-helpers

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

10K 6K 560
kalibr-ai
kalibr

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

8K 30 3
helicone
helicone-async

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

3K 6K 560
helicone
helicone

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

3K 6K 560
ranajoy-dutta
claude-code-cost-explorer

Local-first observability for Claude Code - drill into costs, prompts, and tool calls turn by turn. Zero instrumentation.

2K 3 0
smigolsmigol
llmkit-sdk

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

1K 10 3
saileshr
aimeter

Your AI agents are burning money. AImeter shows you exactly how much.

986 2 0
buildwithabid
llm-spend-profiler

Track, visualize, and optimize LLM API spending. Monitor OpenAI & Anthropic costs per feature, detect waste, suggest savings. Zero-config Python profiler.

609 5 1
margindash
ai-cost-calc

AI cost calculator and usage tracker. Calculate LLM API costs for 400+ models (OpenAI, Anthropic, Google). No API key required for cost lookups.

337 2 0
FardinHash
tokencal

Token Price Estimation for LLMs

139 0 0
kalibr-ai
llm-cost-reduction

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

137 30 3
kalibr-ai
llm-cost-optimizer

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

136 30 3
doramirdor
nadir-llm

Nadir is a Python package designed to dynamically choose the best llm for your prompt by balancing complexity and cost and response time.

117 68 3
    • Data from PyPI, GitHub, ClickHouse, and BigQuery