aiagent.club
中文

Observability & evals

Tracing, evaluation, monitoring, cost control, and agent quality systems.

Rule-inferred category · a project may appear in more than one

Observability & evals · 2

Ranked projects have at least two current score dimensions across two source types. Score = observed adoption (45%) + momentum (30%) + attention (25%); stale or missing signals receive no weight.

  1. 2
    litellm GHPyPI

    The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

    341.6M observed/mo 58.5k ▲ 450 ★/wk 3/3 current signals

    93
  2. 42
    agentops GHPyPI

    Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

    183.5k observed/mo 5.8k ▲ 7 ★/wk 3/3 current signals

    27