Agenta: Serves as an open-source workspace for evaluating and deploying AI agents, bridging theory and production. Agenta 每月有 45,760 次造訪，月增率 +29.5%，定價模式為免費增值。ApX Machine Learning 每月有 252,389 次造訪，成長率 -6.5%，定價模式為免費增值。
面向開源權重 LLM 部署的 VRAM、吞吐與 GPU 成本計算器與課程平台
| 面向／指標 |  | |
|---|---|---|
| 官方網域 | agenta.ai | apxml.com |
| 定價模式 | 免費增值 | 免費增值 |
| 每月造訪次數 | 4.58萬 (45,760) | 25.24萬 (252,389) |
| 月流量變化量 | +1.04萬 (+29.5%) | -1.74萬 (-6.5%) |
| 主要市場與市佔 | 🇺🇸 美國 (23.1%) | 🇺🇸 美國 (14.2%) |
| 每月直接造訪 | 1.72萬 | 6.76萬 |
| 使用者評分 | 4.4 | 4.2 |
| 支援平台 | 網站 | 網站 |
用於建構、評估與部署 AI Agent 的開源工作空間
從範本或空白開始建立 Agent，為其配置模型、技能與工具，並在聊天介面、Slack 或 Telegram 中執行。
透過 MCP 接入 Notion、GitHub、HubSpot、Slack、Linear、Drive 等，可在不重寫 Agent 的前提下更換工具或技能。
為 Agent 輸出評分、收集回饋，並檢視每次執行的耗時、Token 用量與成本紀錄，讓改進可被衡量。
自行決定哪些動作可無人值守執行、哪些需要審批，憑證則保存在 Agent 可用但不可讀的保險庫中。
面向開源權重 LLM 部署的 VRAM、吞吐與 GPU 成本計算器與課程平台
依模型版本、上下文長度、批次大小與量化精度估算權重與 KV 快取佔用，判斷某張 GPU 是否真的裝得下。
依硬體組態推算首字延遲與每秒 token 吞吐，協助你按實際流量規劃容量。
把記憶體與效能估算換算為每小時成本與單位 token 成本，方便橫向比較硬體方案。
收錄 500 多個模型版本與有據可查的硬體基準，讓選型輸入集中在一處。
免費 / 開源簡化在自有硬體上本地運行開源權重 LLM 的流程，但缺乏 ApX 明確的 VRAM 計算器與課程。
免費 / 開源讓多個程式智能體在各自獨立的 worktree 中並行運作
專項更強Focuses on production LLM observability and evaluation rather than foundational deployment courses or hardware cost calculators.
專項更強Focuses on production LLM observability and evaluation rather than foundational deployment courses or hardware cost calculators.
免費 / 開源Sim is the open-source AI workspace for building, deploying and governing AI agents. Create agents visually, in Chat or in code, ground them in a synced knowledge base, connect 270+ integrations, and control access, spend and deployment from one place — on Sim Cloud or self-hosted.
免費 / 開源Sim is the open-source AI workspace for building, deploying and governing AI agents. Create agents visually, in Chat or in code, ground them in a synced knowledge base, connect 270+ integrations, and control access, spend and deployment from one place — on Sim Cloud or self-hosted.
專項更強Provides testing and monitoring tools for AI applications, helping developers optimize model performance in production.
專項更強Streamlines prompt management and LLM application tracing, complementing open-weight deployment workflows.
專項更強Streamlines prompt management and LLM application tracing, complementing open-weight deployment workflows.
免費 / 開源OpenAgents is an open-source platform for building, connecting and orchestrating AI agent workflows inside a shared team workspace. It pairs a browser-based Workspace with a desktop Launcher so agents running on your own machine or a remote server can join the same threads, files and tasks as your teammates.
免費 / 開源OpenAgents is an open-source platform for building, connecting and orchestrating AI agent workflows inside a shared team workspace. It pairs a browser-based Workspace with a desktop Launcher so agents running on your own machine or a remote server can join the same threads, files and tasks as your teammates.
