threadline

Persistent memory and context layer for AI agents. inject() before your LLM call, update() after. Relevance-scored injection, grant-based access control, user-owned context. Works with OpenAI, Anthropic, Vercel AI SDK, and LangChain. < 50ms retrieval. GDPR-ready. Free tier: 2,500 calls/month.

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

接入信息

传输形态: http
鉴权方式: 需 API Key（需要配置：apiKey）
端点: https://threadline--vidursharma202-del.run.tools

该服务需要凭证，请按官方文档申请后替换占位符

{
  "mcpServers": {
    "threadline": {
      "headers": {
        "Authorization": "Bearer \u003cYOUR_KEY\u003e"
      },
      "url": "https://threadline--vidursharma202-del.run.tools"
    }
  }
}

能力清单

工具	说明
inject	Inject user context into a base system prompt before an LLM call. Returns an enriched prompt with relevant facts about the user automatically inserted.
update	Update a user's context after an LLM interaction. Extracts structured facts from the conversation and stores them for future sessions.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。