Ktx – Open-source executable context layer for data agents 是一个「skill」类 AI agent,解决:为数据代理提供安全可复用的运行时环境以执行数据任务。定价:产品页未标明。截至 2026-10-27,KanonAgent 记录到 93 票。本站首次收录于 2026-07-07。
开源的可执行上下文层，为数据代理（data agents）提供运行时环境，让代理能安全、可复用地执行数据任务
93 票
Kanon 于 2026 年 7 月 7 日 收录
状态依据:npm_downloads_7d gained 19 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
📈 时间线什么时候变了什么
- 加速 npm_downloads_7d gained 19 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- 加速 npm_downloads_7d gained 19 in the last 3d vs 5 in the 3d before (ratio 3.8x, threshold 1.5x)
- 加速 npm_downloads_7d gained 19 in the last 3d vs 5 in the 3d before (ratio 3.8x, threshold 1.5x)
- 加速 npm_downloads_7d gained 19 in the last 3d vs 5 in the 3d before (ratio 3.8x, threshold 1.5x)
- 降温 npm_downloads_7d momentum fell to -14 per 3d from 48 (<= 40% of the prior window)
- 降温 npm_downloads_7d momentum fell to -7 per 3d from 73 (<= 40% of the prior window)
- 降温 npm_downloads_7d momentum fell to 1 per 3d from 120 (<= 40% of the prior window)
- 降温 npm_downloads_7d momentum fell to 15 per 3d from 120 (<= 40% of the prior window)
- 加速 npm_downloads_7d gained 120 in the last 3d vs 6 in the 3d before (ratio 20.0x, threshold 1.5x)
- 加速 npm_downloads_7d gained 87 in the last 3d vs 6 in the 3d before (ratio 14.5x, threshold 1.5x)
- 降温 npm_downloads_7d momentum fell to -59 per 3d from 39 (<= 40% of the prior window)
- 降温 npm_downloads_7d momentum fell to -15 per 3d from 69 (<= 40% of the prior window)
- 降温 npm_downloads_7d momentum fell to -5 per 3d from 117 (<= 40% of the prior window)
- 降温 npm_downloads_7d momentum fell to 30 per 3d from 90 (<= 40% of the prior window)
- 降温 npm_downloads_7d momentum fell to 35 per 3d from 90 (<= 40% of the prior window)
- 加速 npm_downloads_7d gained 117 in the last 3d vs 8 in the 3d before (ratio 14.6x, threshold 1.5x)
- 加速 npm_downloads_7d gained 90 in the last 3d vs 5 in the 3d before (ratio 18.0x, threshold 1.5x)
- 异常 daily change 48.0 is 4.9 standard deviations from this entity's own prior mean (-3.8±10.5, baseline excludes this point) — unusual, not necessarily adoption
- 加速 npm_downloads_7d gained 90 in the last 3d vs 5 in the 3d before (ratio 18.0x, threshold 1.5x)
- 异常 daily change 48.0 is 4.9 standard deviations from this entity's own prior mean (-3.8±10.5, baseline excludes this point) — unusual, not necessarily adoption
- 降温 npm_downloads_7d momentum fell to -76 per 3d from 33 (<= 40% of the prior window)
- 降温 npm_downloads_7d momentum fell to -60 per 3d from 33 (<= 40% of the prior window)
- 加速 npm_downloads_7d gained 5 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
- 加速 npm_downloads_7d gained 33 in the last 3d after a flat 3d baseline (no prior movement to compare a ratio against)
🔎 已知 / 未知
23 个字段里 15 个未知
| 可机器调用 | — | 未知 | — |
| 开源 | 1 | 推断 | 1 条引文 |
| 可自托管 | — | 未知 | — |
| 需自带 key | 1 | 推断 | 1 条引文 |
| 自主度 | 2 | 推断 | 2 条引文 |
| 计费模式 | — | 未知 | — |
| 集成面 | — | 未知 | — |
「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
解决什么场景为数据代理提供安全可复用的运行时环境以执行数据任务
自主度L2 · 有工具调用(引文: "teaches agents how to query your warehouse accurately…")
前置条件开源 · 需自带 API key
牵引 · 为什么在涨93票
为什么值得关注
构建数据代理的底层运行时框架，是AI Agent生态的关键基础设施，具备可扩展性与标准化潜力
证据引文判定所依据的原文 · 逐字引用
“public GitHub repository (README fetched)”— structural
“Run ktx with your own LLM API keys or a local agent sign-in”— readme
“teaches agents how to query your warehouse accurately”— readme
“self-improving context layer”— readme
“ktx is a self-improving context layer that teaches agents how to query your warehouse”— readme
信号来源: Show HN
访问官网 →
📛 官方徽章挂到官网 / README
你是 Ktx 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
Ktx 是什么?
开源的可执行上下文层，为数据代理（data agents）提供运行时环境，让代理能安全、可复用地执行数据任务
Ktx 解决什么问题?
为数据代理提供安全可复用的运行时环境以执行数据任务
Ktx 为什么值得关注?
构建数据代理的底层运行时框架，是AI Agent生态的关键基础设施，具备可扩展性与标准化潜力
Ktx 是开源的吗?
是。Ktx 为开源项目。
Ktx 有多少人在用?
KanonAgent 记录到:93 票(本站首次收录于 2026-07-07)。
Ktx 有什么替代品?
KanonAgent 库内的同类 agent:Stealth Venture、taste-skill、archify、open-design、deer-flow、ruflo。