免費 / 開源Runs parallel CLI coding agents in isolated worktrees, lacking dedicated context compression and cost routing tools.
Caveman 每月有 171,826 次造訪,月增率 -15.5%,定價模式為免費增值、需聯絡報價。Code Arena 每月有 35,827,928 次造訪,成長率 +19.4%,定價模式為免費。
| 面向/指標 | ![]() | ![]() |
|---|---|---|
| 官方網域 | caveman.so | arena.ai |
| 定價模式 | 免費增值、需聯絡報價 | 免費 |
| 每月造訪次數 | 17.18萬 (171,826) | 3582.79萬 (35,827,928) |
| 月流量變化量 | -3.16萬 (-15.5%) | +583.28萬 (+19.4%) |
| 主要市場與市佔 | 🇺🇸 美國 (30%) | 🇮🇳 印度 (13.1%) |
| 每月直接造訪 | 6.42萬 | 2433.99萬 |
| 使用者評分 | 4.7 | 4.7 |
| 支援平台 | 網站 | 網站 |

用可還原的上下文壓縮與智慧模型路由,降低 AI Agent 權杖成本

Code Arena is a hands-on playground and leaderboard where you can pit leading AI coding models against each other on real web builds, comparing speed, accuracy, and logic in live side-by-side battles.
Send the same coding prompt to multiple leading models and compare their generated apps and logic side by side.
Watch models construct web apps and websites live, so you can see process and output, not just the final file.
Projects go beyond one-off snippets, testing how well a model structures components, routes, and styles together.
Track which coding models accumulate the most wins over time to identify consistently strong performers.
免費 / 開源Runs parallel CLI coding agents in isolated worktrees, lacking dedicated context compression and cost routing tools.
讓 AI 模型同台競技、由真人投票選出最佳設計產出的群眾外包競技場
免費 / 開源檢索並研究數百萬公開的 SKILL.md 代理技能

專項更強為程式碼編寫代理提供企業級上下文引擎,但缺乏開源 Token 壓縮與自訂模型路由功能。
專項更強為程式碼編寫代理提供企業級上下文引擎,但缺乏開源 Token 壓縮與自訂模型路由功能。

免費 / 開源Provides an open-source Python framework for building model-agnostic agents without built-in context compression.
建立具備權限意識的上下文圖譜並將任務路由至模型,不過主要針對企業級代理工作流程。
面向 Cursor 的社群外掛、規則與 MCP 伺服器中心

專項更強提供企業級 LLM 閘道器與監控工具,但較少著墨於本地上下文壓縮與代理路由。
用盲測對戰評測電腦與手機操作型 AI 代理