open-codex-computer-use 是一个「skill」类 AI agent,解决:在本地运行AI代理执行代码任务，提升开发效率并保护代码隐私。定价:产品页未标明。截至 2026-10-27,KanonAgent 记录到 10 票。本站首次收录于 2026-07-08。
开源替代GitHub Copilot的计算机使用能力项目，允许用户在本地运行AI代理执行代码任务，提升开发效率并保护代码隐私。
10 票
Kanon 于 2026 年 7 月 8 日 收录
状态依据:daily change -4026.3 is -3.9 standard deviations from this entity's own prior mean (59.5±1060.7, baseline excludes this point) — unusual, not necessarily adoption
📈 时间线什么时候变了什么
- 异常 daily change -4026.3 is -3.9 standard deviations from this entity's own prior mean (59.5±1060.7, baseline excludes this point) — unusual, not necessarily adoption
- 异常 daily change -4026.3 is -3.9 standard deviations from this entity's own prior mean (59.5±1060.7, baseline excludes this point) — unusual, not necessarily adoption
- 降温 npm_downloads_7d momentum fell to -542 per 3d from 1419 (<= 40% of the prior window)
- 降温 npm_downloads_7d momentum fell to 0 per 3d from 1419 (<= 40% of the prior window)
- 降温 npm_downloads_7d momentum fell to -5055 per 3d from 1682 (<= 40% of the prior window)
- 降温 npm_downloads_7d momentum fell to -5055 per 3d from 2019 (<= 40% of the prior window)
- 降温 npm_downloads_7d momentum fell to 0 per 3d from 2572 (<= 40% of the prior window)
- 降温 npm_downloads_7d momentum fell to 1682 per 3d from 5556 (<= 40% of the prior window)
- 降温 npm_downloads_7d momentum fell to 2019 per 3d from 10520 (<= 40% of the prior window)
- 降温 npm_downloads_7d momentum fell to 2572 per 3d from 9967 (<= 40% of the prior window)
- 降温 npm_downloads_7d momentum fell to 890 per 3d from 9967 (<= 40% of the prior window)
- 加速 npm_downloads_7d gained 10520 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- 加速 npm_downloads_7d gained 9967 in the last 3d vs 1283 in the 3d before (ratio 7.8x, threshold 1.5x)
- 异常 daily change 2333.0 is 3.7 standard deviations from this entity's own prior mean (261.3±561.9, baseline excludes this point) — unusual, not necessarily adoption
- 加速 npm_downloads_7d gained 5301 in the last 3d vs 1019 in the 3d before (ratio 5.2x, threshold 1.5x)
- 异常 daily change 2898.0 is 5.8 standard deviations from this entity's own prior mean (209.6±462.2, baseline excludes this point) — unusual, not necessarily adoption
- 降温 npm_downloads_7d momentum fell to 0 per 3d from 1609 (<= 40% of the prior window)
- 异常 daily change 1283.0 is 5.9 standard deviations from this entity's own prior mean (51.4±209.6, baseline excludes this point) — unusual, not necessarily adoption
- 加速 npm_downloads_7d gained 5301 in the last 3d vs 1019 in the 3d before (ratio 5.2x, threshold 1.5x)
- 加速 npm_downloads_7d gained 1283 in the last 3d vs 398 in the 3d before (ratio 3.2x, threshold 1.5x)
- 异常 daily change 1283.0 is 5.9 standard deviations from this entity's own prior mean (51.4±209.6, baseline excludes this point) — unusual, not necessarily adoption
- 降温 npm_downloads_7d momentum fell to 0 per 3d from 1609 (<= 40% of the prior window)
- 异常 daily change 1283.0 is 5.9 standard deviations from this entity's own prior mean (51.4±209.6, baseline excludes this point) — unusual, not necessarily adoption
- 加速 npm_downloads_7d gained 1019 in the last 3d vs 662 in the 3d before (ratio 1.5x, threshold 1.5x)
🔎 已知 / 未知
23 个字段里 12 个未知
| 可机器调用 | — | 未知 | — |
| 开源 | 1 | 已核实 | 1 条引文 |
| 可自托管 | 1 | 推断 | 1 条引文 |
| 需自带 key | — | 未知 | — |
| 自主度 | 2 | 推断 | 1 条引文 |
| 计费模式 | — | 未知 | — |
| 集成面 | mcp | 推断 | 1 条引文 |
「未知」= 我们没核实过,**不等于「否」**。硬性筛选永远不会把未知当成否。
🤖 Agent 拆解 · skill
解决什么场景在本地运行AI代理执行代码任务，提升开发效率并保护代码隐私
自主度L2 · 有工具调用(引文: "run Computer Use on macOS, Linux, and Windows…")
目标市场开发者
前置条件开源 · 可自托管
集成面mcp
为什么值得关注
在AI编程助手泛滥的背景下，本地化、可自托管的开源替代方案具有隐私和可控性优势，是开发者关注的热点。
证据引文判定所依据的原文 · 逐字引用
“public GitHub repository (README fetched)”— structural
“npm i -g open-computer-use”— readme
“run Computer Use on macOS, Linux, and Windows”— readme
“wrapped as `MCP`”— readme
信号来源: GitHub
访问官网 →
📛 官方徽章挂到官网 / README
你是 open-codex-computer-use 的作者?上面选样式,嵌入代码实时更新;要贴合站点配色可在 URL 上加 bg= / fg= / accent=(十六进制色)。徽章链回本页。
手机端点「分享」直达微信/朋友圈/小红书;桌面端用「复制文案」后到 App 内粘贴发布
常见问题
open-codex-computer-use 是什么?
开源替代GitHub Copilot的计算机使用能力项目，允许用户在本地运行AI代理执行代码任务，提升开发效率并保护代码隐私。
open-codex-computer-use 解决什么问题?
在本地运行AI代理执行代码任务，提升开发效率并保护代码隐私
open-codex-computer-use 为什么值得关注?
在AI编程助手泛滥的背景下，本地化、可自托管的开源替代方案具有隐私和可控性优势，是开发者关注的热点。
open-codex-computer-use 是开源的吗?
是。open-codex-computer-use 为开源项目。
open-codex-computer-use 能自托管吗?
可以。open-codex-computer-use 支持自托管部署。
open-codex-computer-use 能接哪些工具?
mcp
open-codex-computer-use 有多少人在用?
KanonAgent 记录到:10 票(本站首次收录于 2026-07-08)。
open-codex-computer-use 有什么替代品?
KanonAgent 库内的同类 agent:Stealth Venture、taste-skill、archify、open-design、deer-flow、ruflo。