免費 / 開源在本機或雲端執行與打造開源 AI 模型

Voker is analytics for AI agents. Its SDK wraps your existing OpenAI, Anthropic, Gemini or Vercel AI SDK calls so every agent session is instrumented, letting you see how agents behave, where they get confused, and how to improve them.
| 面向/指標 | ![]() | ![]() |
|---|---|---|
| 官方網域 | openlit.io | voker.ai |
| 定價模式 | 免費 | 免費增值、免費試用、需聯絡報價 |
| 每月造訪次數 | 6028 (6,028) | 3234 (3,234) |
| 月流量變化量 | -1353 (-18.3%) | -1567 (-32.6%) |
| 主要市場與市佔 | 🇺🇸 美國 (53.6%) | 🇺🇸 美國 (96.3%) |
| 每月直接造訪 | 2375 | 1272 |
| 使用者評分 | 4.7 | 4.1 |
| 支援平台 | 網站 | 網站 |

開源、原生 OpenTelemetry 的 AI 代理可觀測性與 Harness 工程平台
為每一次 LLM 呼叫、工具呼叫、檢索與代理步驟擷取 OpenTelemetry 鏈路與指標,並可依使用者、工作階段、成本、延遲或自訂中繼資料篩選。
對生產流量或實驗資料使用 LLM-as-a-judge、啟發式檢查或人工審核評分,持續衡量準確率、相關性與安全性。
在 Prompt Hub 集中管理與版本化提示詞,無需發布新的應用程式碼即可部署、回滾與更新提示詞。
將 OpenAI、Anthropic 及其他 LLM API 金鑰存放在程式庫之外的加密保險庫中,並支援輪換。

Voker is analytics for AI agents. Its SDK wraps your existing OpenAI, Anthropic, Gemini or Vercel AI SDK calls so every agent session is instrumented, letting you see how agents behave, where they get confused, and how to improve them.
Wrap your existing OpenAI, Anthropic, Gemini or Vercel AI SDK client and every call is instrumented automatically with agent and session context.
Voker organizes activity by agent and by session, so you can follow a single conversation end to end and see how it developed.
Understand which intents users bring to your agent and how well the agent handles them, revealing where prompts or flows need work.
If you need more control, create custom events through the SDK or REST API to capture exactly the behavior you care about.
免費 / 開源在本機或雲端執行與打造開源 AI 模型

免費 / 開源面向生產級 AI 的代理可觀測性、評估與持續改進平台
免費 / 開源打造、模擬、評估並監控能自我改進的 AI 代理

免費 / 開源Maxim AI is a platform for evaluating, testing, and monitoring AI applications, and the home of Bifrost, an open-source LLM gateway. It helps teams ship reliable AI features with tracing, evaluation, agent simulation, and production observability.
免費 / 開源Maxim AI is a platform for evaluating, testing, and monitoring AI applications, and the home of Bifrost, an open-source LLM gateway. It helps teams ship reliable AI features with tracing, evaluation, agent simulation, and production observability.
AI 工程團隊的協作層
在整個組織內統一 LLM 評估、可觀測性與紅隊測試標準