设计资源DESIGN· FIGMA
supermemoryai/supermemory
给AI工具装上记忆,让它们记住你的偏好和对话历史。A self-hostable memory and context engine that gives AI assistants searchable long-term recall.
根据公开文档整理,未运行实测;费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
自动提取并记住用户的关键信息
从文件、邮件、笔记中整理可搜索的记忆
本地运行,数据完全由你掌控
一次搜索同时匹配文档和记忆
构建用户画像,区分长期事实和近期动态
Store conversations and retrieve relevant memories later
Build user profiles showing static facts and dynamic context
Search across documents and past interactions in one query
Run the whole memory server on your own machine
Use with coding assistants like Claude Code and VS Code
上手GET STARTED
curl -fsSL https://supermemory.ai/install | bash选择与你的环境对应的方式。命令来自项目文档,未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查,未执行项目代码;扫描没有命中,不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
存在风险Risk found
静态扫描STATIC SCAN
01执行远程脚本Runs a remote scriptreadme
curl -fsSL https://supermemory.ai/install | bash
02读取 API KeyReads an API keyskills/supermemory/SKILL.md
apiKey: process.env.SUPERMEMORY_API_KEY
安装命令使用了 curl 管道到 bash(curl -fsSL https://supermemory.ai/install | bash),这会直接执行远程脚本,属于高风险操作。另外,代码中会读取环境变量中的 API Key(apiKey: process.env.SUPERMEMORY_API_KEY),如果使用不当可能泄露密钥。The static scan flagged a high-risk pattern: the recommended install command pipes a script from the internet directly into bash. It also reads the SUPERMEMORY_API_KEY environment variable. Those patterns are common but not risk-free, so review the install script before running it.
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
03 OCT 202603 OCT 2026
增长GROWTH
+2.0%+2.0%
31k → 32k stars · 49 个快照31k → 32k stars · 49 snapshots
讨论DISCUSSION
1 SOURCES1 SOURCES
9 条外部提及9 external mentions
状态STATUS
持续活跃Active
质量 B+Quality B+
项目非常活跃,近7天有33次提交,说明团队在持续改进。Supermemory has 31,123 stars and an active repository with 26 open issues.
HN_STORY · 5 points · 0 comments
HN_STORY · 2 points · 0 comments
HN_STORY · 1 points · 0 comments
依赖:Dependencies:@ai-sdk/anthropic, @ai-sdk/cerebras, @ai-sdk/google, @ai-sdk/openai, @anthropic-ai/sdk, @google/genai, @google/generative-ai, @hono/zod-validator, @scalar/hono-api-reference, @types/flubber, @vanilla-extract/recipes, ai
{
"agents": [
{
"agent": "claude-code",
"evidence": "readme: …💻 I use AI tools</h3> Give Claude Code, Muse Code, Cursor, Codex and…"
},
{
"agent": "claude-desktop",
"evidence": "readme: …se. ### Supported clients **Claude Desktop** · **Cursor** · **Windsurf**…"
},
{
"agent": "windsurf",
"evidence": "readme: …de Desktop** · **Cursor** · **Windsurf** · **VS Code** · **Claude Co…"
},
{
"agent": "vscode",
"evidence": "readme: …**Cursor** · **Windsurf** · **VS Code** · **Claude Code** · **OpenC…"
},
{
"agent": "opencode",
"evidence": "readme: …Muse Code, Cursor, Codex and OpenCode **persistent memory across ev…"
}
],
"apiKey": ".yaml\" -o compose.yaml export OPENAI_API_KEY=your_openai_api_key_here export SUPERME",
"docker": null,
"taxonomy": {
"scores": {
"design": 3,
"ai-tools": 0,
"dev-tools": 0,
"indie-web": 0,
"skill-agent": 1,
"productivity": 1
},
"primary": "design",
"secondary": "figma"
},
"localRuntime": "l — or run fully offline with Ollama. ```bash curl -fsSL https://supermemor",
"skillMdTotal": 1,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 6,
"agent": 0,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 0,
"security": 0,
"marketing": 0,
"productivity": 2
},
"classification": [
{
"signal": "1 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 7 markdown files",
"weight": 0.75
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"skills/supermemory/SKILL.md"
],
"skillMdFetched": 1
}