加载中…
Long-term and multimodal memory for AI agents - character-aware, mem0-compatible, fully-local option
io.github.TeleAI-UAGI/telemem 是 ChatHome Skills 收录的 MCP 条目，来源为 Official MCP Registry，质量分 78/100。 作为 Model Context Protocol 服务器，它向 Claude、Cursor、Copilot 等兼容 MCP 的 LLM 客户端暴露可直接调用的工具，让 agent 的能力超出模型内置范围。 该条目由 ChatHome Skills 的每日抓取从官方 registry 和 GitHub 发现查询中收录，每次运行都会重新核验仓库事实、新鲜度信号和安装元数据。 质量分综合了官方 registry 收录情况、可用安装命令、许可证完整性、仓库活跃度和 GitHub star 趋势，完整算法说明见来源页。安装命令已列于上方，可直接复制使用。 在将 io.github.TeleAI-UAGI/telemem 加入生产 agent 工作流前，请核对上方的最近更新日期和仓库状态——下方事实快照是最近一次抓取的时点值。
uvx telemem==1.10.1运行此命令前，请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-23T11:09:44.463518Z",
"publishedAt": "2026-10-23T11:09:44.463518Z",
"statusChangedAt": "2026-10-23T11:09:44.463518Z"
}
},
"server": {
"name": "io.github.TeleAI-UAGI/telemem",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "1.10.1",
"packages": [
{
"version": "1.10.1",
"transport": {
"type": "stdio"
},
"identifier": "telemem",
"runtimeHint": "uvx",
"registryType": "pypi",
"registryBaseUrl": "https://pypi.org",
"environmentVariables": [
{
"name": "OPENAI_API_KEY",
"isSecret": true,
"description": "API key for the default OpenAI LLM/embedder (not needed with a local TELEMEM_CONFIG)"
},
{
"name": "TELEMEM_CONFIG",
"description": "Path to a TeleMem YAML/JSON config, e.g. the fully-local Ollama + FAISS setup (config/config.ollama.yaml)"
},
{
"name": "TELEMEM_DEFAULT_USER_ID",
"description": "Default memory scope when tool calls omit user_id/agent_id/run_id (default: telemem-mcp)"
}
]
}
],
"repository": {
"url": "https://github.com/TeleAI-UAGI/telemem",
"source": "github"
},
"description": "Long-term and multimodal memory for AI agents - character-aware, mem0-compatible, fully-local option"
}
}