
Llongterm is a long-term memory layer for AI apps and agents. It sits between your chatbot and its memory, remembering users across conversations and storing everything in a fully human-readable format through a simple JavaScript API.
| 维度 / 指标 | ![]() | |
|---|---|---|
| 官方域名 | deepseek.com | llongterm.com |
| 定价模式 | 免费增值 | 免费增值,付费 |
| 月访问量 | 3.73亿 (372,761,591) | 0 (0) |
| 月度环比流量变化 | +1536.22万 (+4.3%) | 0 (0%) |
| 主要市场与份额 | 🇨🇳 中国 (50.5%) | 🌐 全球 (—) |
| 直接访问 / 月 | 2.92亿 | 0 |
| 用户评分 | 4.8 | 4.2 |
| 支持的平台 | 网站 | 网站 |
由 DeepSeek-V4 与 R1 驱动的高效开源权重与托管推理 AI,token 成本极低。
依托稀疏混合专家架构(V4-Pro 为 1.6T 中的 49B 激活参数),以极低延迟与内存开销处理最多 100 万 token。
由 DeepSeek-R1 开创并融入 V3.2 与 V4 思考模式,对复杂数学、逻辑与代码调试展示逐步自校验过程。
缓存命中时,输入 token 成本降至 Flash 的每百万 0.003 美元与 V4-Pro 的每百万 0.022 美元,非高峰 UTC 时段费率再低 50%。
在 chat.deepseek.com 及 iOS/Android 上免费提供文档上传、推理模式与网页搜索,核心模型不必付费墙。

Llongterm is a long-term memory layer for AI apps and agents. It sits between your chatbot and its memory, remembering users across conversations and storing everything in a fully human-readable format through a simple JavaScript API.
Store and recall user details across sessions so an assistant remembers preferences, history and context.
Memories are stored with named keys and nested structure, so you can read and audit exactly what is retained.
A JavaScript SDK plus Python on the way, with a sandbox so you can try the flow before integrating.
Llongterm sits between your app and any chatbot or agent, including assistants, support bots and analysis workflows.

提供巨大的上下文窗口与深度的 Google 生态系整合,但对于纯推理任务感觉较不够专精。
提供巨大的上下文窗口与深度的 Google 生态系整合,但对于纯推理任务感觉较不够专精。

免费 / 开源提供同等级的开源权重基础模型与多语言效能,但需要自行架构主机或第三方推理设定。
免费 / 开源Enables running open-source models locally on consumer hardware, but lacks DeepSeek's cloud-scale hosted reasoning power.
免费 / 开源Enables running open-source models locally on consumer hardware, but lacks DeepSeek's cloud-scale hosted reasoning power.
让 AI 智能体安全接入 1700+ 应用