PyPI · npm
pydantic/logfire
AI observability platform for production LLM and agent systems.
MIT2026年8月27日 · 指标 2.10.0
全部标签
目录标签
#llm-observability
公开记录中带有此标签的全部仓库——标签来自其 GitHub 主题或软件包注册表发布的关键词。健康度量遵循与记录其余部分相同的版本化方法论。
20 条记录
Go · npm
maximhq/bifrost
Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
Apache-2.02026年8月28日 · 指标 2.10.0
npm · PyPI
comet-ml/opik
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Apache-2.02026年8月5日 · 指标 2.10.0
npm
langfuse/langfuse
🪢 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
自定义许可证2026年8月5日 · 指标 2.10.0
npm
latitude-dev/latitude-llm
Latitude is the open-source AI monitoring platform.
MIT2026年8月28日 · 指标 2.10.0
PyPI
JudgmentLabs/judgeval
The Continuous-Improvement Stack for Agents. Our environment data and evals power agent improvement and monitoring.
Apache-2.02026年8月13日 · 指标 2.10.0
PyPI · npm
douglasmonsky/codex-usage-tracker
Local-first MCP tools and dashboard for investigating Codex token usage, credits, costs, caching, and thread patterns.
MIT2026年7月25日 · 指标 2.10.0
PyPI
Mandark-droid/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
Apache-2.02026年9月5日 · 指标 2.10.0
PyPI · npm
ShekharBhardwaj/AgenticLedger
Local-first flight recorder for AI agents: every LLM call, tool call, cost, and loop captured by a transparent proxy. Zero code changes.
MIT2026年8月23日 · 指标 2.10.0
Go
nudgebee/node-agent
Per-node observability agent for Kubernetes and Linux hosts. Gathers container and host metrics, logs, and L7 traffic via eBPF; exports to Prometheus and OpenTelemetry. Includes LLM API observability.
Apache-2.02026年7月22日 · 指标 2.10.0
PyPI
alizahidraja/isnad
Grade every agent, scraper and model in a claim's chain — provenance, trust scoring and audit evidence for LLM pipelines
Apache-2.02026年8月29日 · 指标 2.10.0
PyPI
phierceweb/pf-core
Python foundation for LLM apps whose prompts and spend you can actually see — versioned prompts, every call recorded and replayable, budgets, evals, jobs.
MIT2026年9月5日 · 指标 2.10.0
npm
cendorhq/cendor-sdk-js
A governed agent SDK for TypeScript - cost budgets, tamper-evident audit, and PII redaction built into the loop.
Apache-2.02026年8月29日 · 指标 2.10.0
PyPI
dunetrace/dunetrace
Real-time monitoring of production AI agents.
自定义许可证2026年7月16日 · 指标 2.10.0
Go
fgn/go-langfuse
Langfuse client for Go, built on OpenTelemetry
Apache-2.02026年7月22日 · 指标 2.10.0
npm
Medhovarsh/forkmind
🧠 Local-first LLM state branching & debugging. Capture, visualize, branch, and regression-test LLM calls as a DAG. Free & local via Ollama, any OpenAI-compatible API, MCP for agents. Zero config.
MIT2026年7月24日 · 指标 2.10.0
npm
TaewoooPark/Agent-Blackbox
Local-first flight recorder for coding agents : replay every run as a live session map, score the context bill, and write the fix back into AGENTS.md — no API key, one npx command.
MIT2026年7月21日 · 指标 2.10.0
Go · npm
marmutapp/superbased-observer
Local-first cost & token tracking for Claude Code, Cursor, Codex & 23 more AI coding agents — proxy-accurate per-model spend, an MCP server your agent can query, and an opt-in team rollup. 100% local, no telemetry.
自定义许可证2026年7月19日 · 指标 2.10.0
npm
inferock/inferock-bench
Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini, and pinned OpenRouter calls with token usage, failure, and billing-integrity receipts.
自定义许可证2026年7月29日 · 指标 2.10.0
npm
PunkTechnologies/punk-sdk
Public TypeScript SDK and integration examples for Punk, the adaptive runtime for production AI agents.
Apache-2.02026年9月3日 · 指标 2.10.0