经 AI Skill Hub 精选评估,当前为常用粗语程器:PowerMem 获评「推荐使用」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
常用粗语程器为常用粗语程器的常用粗语程器:PowerMem,常用粗语程器为常用粗语程器的常用粗语程器,常用粗语程器为常用粗语程器的常用粗语程器:PowerMem;常用粗语程器为常用粗语程器的常用粗语程器,常用粗语程器为常用粗语程器的常用粗语程器:PowerMem
当前为常用粗语程器:PowerMem 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
常用粗语程器为常用粗语程器的常用粗语程器:PowerMem,常用粗语程器为常用粗语程器的常用粗语程器,常用粗语程器为常用粗语程器的常用粗语程器:PowerMem;常用粗语程器为常用粗语程器的常用粗语程器,常用粗语程器为常用粗语程器的常用粗语程器:PowerMem
当前为常用粗语程器:PowerMem 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:pip 安装(推荐)
pip install powermem
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install powermem
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/oceanbase/powermem
cd powermem
pip install -e .
# 验证安装
python -c "import powermem; print('安装成功')"
# 命令行使用
powermem --help
# 基本用法
powermem input_file -o output_file
# Python 代码中调用
import powermem
# 示例
result = powermem.process("input")
print(result)
# powermem 配置文件示例(config.yml) app: name: "powermem" debug: false log_level: "INFO" # 运行时指定配置文件 powermem --config config.yml # 或通过环境变量配置 export POWERMEM_API_KEY="your-key" export POWERMEM_OUTPUT_DIR="./output"
Persistent, self-evolving memory for AI agents and applications.
PowerMem combines vector, full-text, and graph retrieval with LLM-driven memory extraction and Ebbinghaus-style time decay. It ships two-layer Experience + Skill distillation for self-evolving memory, multi-agent isolation, user profiles, and multimodal signals (text, image, audio).
Memory pipeline and retrieval — Smart extraction and updates; Experience + Skill distillation (self-evolving); Ebbinghaus-style decay; Hybrid retrieval (vector / full-text / graph); Sub stores and routing.
Profiles and multi-agent — User profile; Shared / isolated memory and scopes.
Multimodal — Text, image, audio.
Provider matrix
| Layer | Providers (built in) |
|---|---|
| LLM | Anthropic, OpenAI, Azure OpenAI, Gemini, Qwen (+ ASR), DeepSeek, Ollama, vLLM, SiliconFlow, Z.AI, LangChain-wrapped |
| Embedding | OpenAI, Azure OpenAI, Qwen (+ VL multimodal, sparse), Gemini, Vertex AI, AWS Bedrock, Ollama, LM Studio, HuggingFace, Together, SiliconFlow, Z.AI, OceanBase MASS, LangChain-wrapped |
| Rerank | Jina, Qwen, Z.AI, generic |
| Storage | OceanBase (+ graph), embedded seekdb, PostgreSQL/pgvector, SQLite |
---
| Version | Date | Notes |
|---|---|---|
| 1.2.0 | 2026-04 | Experience + Skill two-layer distillation and distill_all() (self-evolving memory; AppWorld +15 pts); OB MASS embedding; Qwen VL multimodal embedding; OceanBase Zero Mode compatibility; LOCOMO accuracy lifted to 87.79% |
| 1.1.0 | 2026-04-02 | Embedded seekdb for OceanBase storage without a separate database service; [IDE integrations](apps/README.md) (VS Code extension, Claude Code plugin) |
| 1.0.0 | 2026-03-16 | CLI (pmem): memory ops, config, backup/restore/migrate, interactive shell, completions; Web Dashboard |
| 0.5.0 | 2026-02-06 | Unified SDK/API config (pydantic-settings); OceanBase native hybrid search; memory query + list sorting; user-profile language customization |
| 0.4.0 | 2026-01-20 | Sparse vectors for hybrid retrieval; profile-based query rewriting; schema upgrade & migration tools |
| 0.3.0 | 2026-01-09 | Production HTTP API Server; Docker |
| 0.2.0 | 2025-12-16 | Advanced profiles; multimodal (text/image/audio) |
| 0.1.0 | 2025-11-14 | Core memory + hybrid retrieval; LLM extraction; forgetting curve; multi-agent; OceanBase/PostgreSQL/SQLite; graph search |
```bash
pip install "powermem[server]"
pip install "powermem[mcp]"
pip install "powermem[cli,server,mcp,seekdb]"
For zero-install MCP clients such as Cursor, Codex, Claude Desktop, Cline, or
Goose, use the wrapper package:
bash uvx powermem-mcp
The `powermem-mcp` wrapper is version-locked to the main `powermem` release and
installs `powermem[mcp,seekdb]` for the same version. If `uv` has cached an older
tool environment, refresh it explicitly:
bash uvx --refresh --upgrade powermem-mcp ```
Prerequisites: Copy .env.example to .env and set your LLM API key — that is the only required credential. For zero-config local storage, install the seekdb extra (pip install "powermem[seekdb]", or combine it with server / mcp) so the default OceanBase provider can boot embedded seekdb on disk. Without seekdb, set OCEANBASE_HOST to point at a remote OceanBase cluster, or switch to sqlite / postgres. The default embedder is a local all-MiniLM-L6-v2 model (384 dims) that needs no API key and auto-downloads on first use. Need to tune providers or unlock advanced features? Copy .env.example.full instead — it documents every available knob, grouped by component. After install, pmem config init walks you through the same setup interactively. See Getting started.
pip install powermem
pip install "powermem[seekdb]"
| App / framework | Details |
|---|---|
| Python SDK | pip install powermem, see [Quick start](#quick-start-python-sdk) |
| LangChain / LangGraph | pip install powermem, see [LangChain guide](docs/integrations/langchain.md) |
| AgentScope | Connect to powermem-mcp with AgentScope's MCP client, see [AgentScope guide](docs/integrations/agentscope.md) |
| Go apps | [SDKs](#sdks) |
| Java apps | [SDKs](#sdks) |
| TypeScript apps | [SDKs](#sdks) |
| Any MCP client | powermem-mcp sse (default :8848), see [MCP client guide](docs/integrations/mcp_client.md) |
| HTTP REST apps | powermem-server --host 0.0.0.0 --port 8848, see [API server](docs/api/0005-api_server.md) |
| Language | Package |
|---|---|
| Python | pip install powermem (this repo) |
| Go | [ob-labs/powermem-go](https://github.com/ob-labs/powermem-go) |
| Java | [ob-labs/powermem-java](https://github.com/ob-labs/powermem-java) |
| TypeScript | [ob-labs/powermem-ts](https://github.com/ob-labs/powermem-ts) |
---
pip install "powermem[cli]"
pip install "powermem[server,seekdb]"
Run from a directory that contains your configured .env:
from powermem import Memory, auto_config
memory = Memory(config=auto_config())
memory.add("User likes coffee", user_id="user123")
for r in memory.search("user preferences", user_id="user123").get("results", []):
print("-", r.get("memory"))
More patterns: Getting Started.
pmem memory add "User prefers dark mode" --user-id user123
pmem memory search "preferences" --user-id user123
pmem shell # interactive REPL
Full reference: CLI usage.
Uses the same .env as the SDK. Dashboard is served under /dashboard/.
powermem-server --host 0.0.0.0 --port 8848
On an interactive local terminal, the server automatically opens the Dashboard in your default browser once it is ready. You can also open http://localhost:8848/dashboard/ manually to browse memories, view analytics, and monitor system health. Use --no-open-browser to disable auto-open, or --open-browser when output is redirected. Browser opening is skipped in CI, containers, SSH sessions, headless environments, and when Dashboard assets are unavailable. See the Web Dashboard Guide for a complete walkthrough.
Docker / Compose: see API Server and Docker & deployment. The official image is oceanbase/powermem-server:latest.
---
PowerMem ships first-party plugins and setup guides for the most common AI clients. All of them point at the same backend (HTTP server, MCP server, or local pmem CLI) — no per-client schema rewrites. All agents share the same memory server.
First download the code and enter the directory:
git clone https://github.com/oceanbase/powermem
cd powermem
Then open the AI agent window in your IDE and paste this one line:
Read and follow apps/vscode-extension/SETUP.md to setup PowerMem
The agent follows apps/vscode-extension/SETUP.md: it prefers a reusable powermem-server HTTP API backend, falls back to MCP-only only when HTTP is unavailable, and configures the current IDE/client instead of unrelated tools.
Prefer to wire it by hand? Use the per-IDE guide:
| Client | Details |
|---|---|
| VS Code | [docs/integrations/vs_code.md](docs/integrations/vs_code.md) |
| Cursor | [docs/integrations/cursor.md](docs/integrations/cursor.md) |
| Windsurf | [docs/integrations/windsurf.md](docs/integrations/windsurf.md) |
| GitHub Copilot | [docs/integrations/github_copilot.md](docs/integrations/github_copilot.md) |
| Qoder | [docs/integrations/qoder.md](docs/integrations/qoder.md) |
The same extension also provides Query memories, Add selection to memory, Quick note, and a status-bar Dashboard. See apps/vscode-extension/README.md and the full VS Code guide.
常用粗语程器为常用粗语程器的常用粗语程器:PowerMem,常用粗语程器为常用粗语程器的常用粗语程器:PowerMem,常用粗语程器为常用粗语程器的常用粗语程器:PowerMem
该工具使用 NOASSERTION 协议,商用场景请仔细阅读协议条款,必要时咨询法律意见。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
📄 NOASSERTION — 请查阅原始协议条款了解具体使用限制。
AI Skill Hub 点评:当前为常用粗语程器:PowerMem 的核心功能完整,质量良好。对于自动化工程师和运维人员来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | powermem |
| 原始描述 | 开源AI工作流:PowerMem: AI Memory Plugin— Accurate, Agile, Affordable. Make AI Agent smarter.。⭐703 · Python |
| Topics | workflowagenticagentsaiai-agentsai-companionpython |
| GitHub | https://github.com/oceanbase/powermem |
| License | NOASSERTION |
| 语言 | Python |
收录时间:2026-06-11 · 更新时间:2026-06-11 · License:NOASSERTION · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端