追踪、评测、监控、成本控制与 Agent 质量系统。
规则推断分类 · 同一项目可属于多个分类
主榜项目至少要有两个当前有效的评分维度，且覆盖两种数据源。综合分 = 可观测采用度（45%）+动量（30%）+关注度（25%）；过期或缺失信号不计分。
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]
92.2M 可观测/月 62.9k ★ ▲ 451 ★/周 3/3 当前信号
Free, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in context. Works with Claude Code, Codex, Pi, OpenCode, Gemini CLI, Copilot CLI and 4 more agents. Zero telemetry.
288.8k 可观测/月 33.7k ★ ▲ 597 ★/周 3/3 当前信号
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
94.7k 可观测/月 5.9k ★ ▲ 14 ★/周 3/3 当前信号
Symbol-level code retrieval for AI agents: fetch the function you need, not the whole file. Runs locally. 96.2% fewer tokens per lookup on average than grep-and-read on our 15-lookup benchmark. Works with Claude Code, Cursor, Codex and any MCP client. Free for non-commercial use; commercial use needs a one-time license.
29.4k 可观测/月 2.8k ★ ▲ 8 ★/周 3/3 当前信号