功能描述

Step-by-step guide to install and configure the PowerMem long-term memory plugin (full path, options, troubleshooting). After setup, the plugin auto-captures...

使用说明 (SKILL.md)

PowerMem Memory Guide

Name: Install Powermem Memory
Author: teingi

This skill folder includes supplementary docs:

powermem-intro.md — What PowerMem is, features, vs file-based memory.
config-reference.md — Config keys, state dir, commands.

How It Works

Auto-Capture: After a conversation, the plugin sends valuable user/assistant text to PowerMem (optional infer / intelligent extraction).
Auto-Recall: Before each turn, it searches memories and can inject a \x3Crelevant-memories> block into context.

When User Asks to Install

Recommended order (TO C): (1) OpenClaw installed and default model + provider auth configured. (2) Python 3.10+ verified (python3 --version) before venv / pip install. (3) pip install powermem and pmem available to the gateway (PATH or pmemPath). (4) Install the memory-powermem plugin. No powermem.env is required for the default path.

The curl install.sh deploys the plugin and OpenClaw entries; with -y it may still create ~/.openclaw/powermem/powermem.env as an optional template—it does not run pip install powermem. That file is not required if the user relies on OpenClaw-injected LLM + default SQLite.

Check OpenClaw
openclaw --version. If missing: npm install -g openclaw, openclaw onboard.
Ensure agents.defaults.model is set (e.g. openai/gpt-4o-mini) and the corresponding provider / API key works for normal chat—the plugin reuses that for PowerMem when useOpenClawModel is true (default).
Check Python (required before venv / pip)
PowerMem needs Python 3.10 or newer. Run python3 --version first; the minor version must be ≥ 10 (e.g. 3.10.x, 3.12.x). Optional strict check:
```
python3 -c "import sys; assert sys.version_info >= (3, 10), 'Need Python 3.10+'; print(sys.version.split()[0], 'OK')"
```
If it fails: upgrade Python or use a specific binary (e.g. python3.12) for all commands below instead of python3.
Install PowerMem (CLI — default)
- Venv recommended: e.g. python3 -m venv ~/.openclaw/powermem/.venv && source ~/.openclaw/powermem/.venv/bin/activate.
- pip install powermem.
- Defaults: Plugin injects SQLite at \x3COpenClaw stateDir>/powermem/data/powermem.db and LLM + embedding env vars derived from OpenClaw. Typical stateDir is ~/.openclaw unless the user uses another instance (OPENCLAW_STATE_DIR, --workdir).
- Optional envFile: Path to a PowerMem .env for extra tuning. If the file exists, pmem loads it; OpenClaw-derived vars still override the same keys when useOpenClawModel is true.
- useOpenClawModel: false: Disables injection; user must supply a complete PowerMem config via .env and/or environment variables.
- Verify: pmem --version. If the gateway does not inherit the venv, set pmemPath to the absolute path of pmem.
HTTP path (enterprise / shared server)
- Same Python 3.10+ requirement as CLI; then pip install powermem, .env in server working directory, powermem-server --host 0.0.0.0 --port 8000.
- Check: curl -s http://localhost:8000/api/v1/system/health.
Install the plugin
openclaw plugins install /path/to/memory-powermem, or install.sh from INSTALL.md.

Configure OpenClaw

CLI — minimal (recommended, matches plugin defaults):
Do not set envFile unless you need a file. Example:

openclaw config set plugins.enabled true
openclaw config set plugins.slots.memory memory-powermem
openclaw config set plugins.entries.memory-powermem.config.mode cli
openclaw config set plugins.entries.memory-powermem.config.pmemPath pmem
openclaw config set plugins.entries.memory-powermem.config.useOpenClawModel true --json
openclaw config set plugins.entries.memory-powermem.config.autoCapture true --json
openclaw config set plugins.entries.memory-powermem.config.autoRecall true --json
openclaw config set plugins.entries.memory-powermem.config.inferOnAdd true --json

CLI — optional .env override file:

openclaw config set plugins.entries.memory-powermem.config.envFile "$HOME/.openclaw/powermem/powermem.env"

(Only matters if that path exists; OpenClaw can still override LLM keys when useOpenClawModel is true.)

HTTP:

openclaw config set plugins.entries.memory-powermem.config.mode http
openclaw config set plugins.entries.memory-powermem.config.baseUrl http://localhost:8000

Optional: apiKey if the server uses auth.

Verify
Restart gateway, then in another terminal:
```
openclaw plugins list
```
Confirm memory-powermem is listed and its status is loaded. If it is missing or not loaded, fix install/slot config and restart the gateway before running LTM checks.
```
openclaw ltm health
openclaw ltm add "I prefer coffee in the morning"
openclaw ltm search "coffee"
```

Available Tools

Tool	Description
memory_recall	Search long-term memories. Params: `query`, optional `limit`, `scoreThreshold`.
memory_store	Save text; optional infer. Params: `text`, optional `importance`.
memory_forget	Delete by `memoryId` or by `query` search.

Configuration (summary)

Field	Default	Description
`mode`	`cli`	`cli` or `http`.
`baseUrl`	—	Required for HTTP; if `mode` omitted and `baseUrl` set → HTTP.
`apiKey`	—	HTTP server auth.
`envFile`	—	Optional CLI `.env` (used only if file exists).
`pmemPath`	`pmem`	CLI binary path.
`useOpenClawModel`	`true`	Inject LLM/embedding from OpenClaw + default SQLite under state dir.
`recallLimit`	`5`	Max memories per recall.
`recallScoreThreshold`	`0`	Min score 0–1.
`autoCapture` / `autoRecall` / `inferOnAdd`	`true`	Auto memory pipeline and infer on add.

Daily Operations

openclaw gateway

openclaw ltm health
openclaw ltm add "Some fact to remember"
openclaw ltm search "query"

openclaw config set plugins.slots.memory none
openclaw config set plugins.slots.memory memory-powermem

Restart the gateway after slot or plugin config changes.

Troubleshooting

Symptom	Fix
Python \x3C 3.10	Run step 2 first; upgrade Python or use `python3.11` / `python3.12` for venv and `pip install`. Do not skip the version check.
`pip install powermem` fails	Confirm Python 3.10+, clean venv. See PowerMem issues.
`pmem` not found	Activate venv or set `pmemPath` to the full binary.
`openclaw ltm health` unhealthy (CLI)	Confirm `agents.defaults.model` and provider keys in OpenClaw; gateway version should expose plugin `config` + `runtime.modelAuth`. Or set `useOpenClawModel: false` and a full `envFile`.
Health OK but add/search errors	Embedding/LLM mismatch for your provider—see gateway logs; try optional PowerMem `.env` from .env.example.
Wrong SQLite file / instance	Data is under that OpenClaw instance’s `stateDir` (`OPENCLAW_STATE_DIR` / `--workdir`).
HTTP mode	Server running, `baseUrl` correct, `apiKey` if enabled.
`openclaw plugins list`: no `memory-powermem`, or status is not loaded	Re-run plugin install; set `plugins.enabled` true and `plugins.slots.memory` = `memory-powermem`; restart gateway; run `openclaw plugins list` again until memory-powermem shows loaded.

安全使用建议

This guide appears to do what it claims (install and configure PowerMem for OpenClaw), but take these precautions before proceeding: - Verify sources: confirm the powermem package on PyPI and inspect the upstream repositories referenced in the docs (oceanbase/powermem and ob-labs/memory-powermem). Don't install packages or run scripts from unknown sources without review. - Never run curl | sh blindly: if you use the referenced install.sh, open it in a text editor and review what it will do (file writes, downloads, system changes). Prefer manual steps you understand. - Use a virtualenv: install powermem inside an isolated venv to limit scope and avoid polluting system Python. - Prefer local SQLite for personal use: the default CLI mode stores data locally under the OpenClaw stateDir; avoid HTTP/server mode unless you control the server and trust its network exposure. - Inspect any created powermem.env: if the installer writes ~/.openclaw/powermem/powermem.env, review its contents and credentials before leaving it on disk. - Understand auto-capture: the plugin can automatically store conversation highlights. If you have privacy concerns, set autoCapture/autoRecall to false or tighten recall/retention settings. - Protect provider keys: the plugin may use OpenClaw-injected LLM/embedding credentials; ensure those credentials are stored securely in OpenClaw and audit which services the plugin will call. If you want a higher-assurance review, provide the exact install.sh referenced or the memory-powermem plugin source so those artifacts can be inspected for unexpected behaviors.

功能分析

Type: OpenClaw Skill Name: install-powermem-memory-full Version: 0.3.0 The skill bundle provides a legitimate and detailed guide for installing the PowerMem long-term memory plugin. It includes instructions for Python environment verification, package installation via pip, and OpenClaw configuration (SKILL.md, config-reference.md). The behavior is transparently aligned with the stated purpose of enabling persistent memory, referencing established open-source projects like oceanbase/powermem (powermem-intro.md), and lacks any indicators of malicious intent, data exfiltration, or obfuscation.

能力评估

ℹ Purpose & Capability

The SKILL.md describes installing and configuring the memory-powermem plugin and PowerMem (pip package or server). The actions described (checking python/openclaw, pip installing powermem, configuring OpenClaw plugin entries) match the stated purpose. Minor inconsistency: the registry metadata declares no required env vars/credentials, but the instructions explicitly rely on OpenClaw 'agents.defaults.model' and provider API keys being configured (these are necessary for the default 'useOpenClawModel' flow).

ℹ Instruction Scope

The runtime instructions tell the agent/user to run local commands (python3 checks, venv creation, pip install, openclaw CLI config, optional powermem-server and curl health checks). They also document auto-capture/auto-recall behavior (the plugin will send conversation content to PowerMem). This scope is appropriate for an installer, but it explicitly instructs the agent to modify OpenClaw config and to possibly capture conversation text—this has privacy implications and should be reviewed by the user. The SKILL.md also references an install.sh (GitHub) which, if executed blindly, could run arbitrary commands.

ℹ Install Mechanism

There is no baked install spec in the skill bundle — installation is manual via standard tools: 'pip install powermem', optional 'powermem-server', and installing the OpenClaw plugin or a referenced install.sh on GitHub. These are standard package sources (PyPI, GitHub). No obscure download URLs or embedded archives are present in the skill bundle, but users should still inspect any remote install.sh before running it.

ℹ Credentials

The metadata declares no required environment variables, but the instructions rely on OpenClaw-provided model and provider credentials (LLM + embedding keys) when 'useOpenClawModel: true' (the default). That is proportionate to the plugin's function (it needs embeddings/LLM to run intelligent extraction), but the skill does not explicitly declare those credentials in the registry metadata—users should be aware that provider keys stored in OpenClaw will be used and that PowerMem may see injected LLM/embedding environment values when invoked.

ℹ Persistence & Privilege

The skill does not request 'always: true' and is user-invocable. Installing the plugin modifies OpenClaw's configuration (enabling a plugin slot) and results in persistent behavior (autoCapture/autoRecall enabled by default). That persistence is consistent with the plugin's purpose but increases the impact of stored memories; consider disabling autoCapture/autoRecall or reviewing retention settings if you don't want automatic long-term storage.

版本历史

v0.3.0

- Added a complete, independent step-by-step guide for installing and configuring the PowerMem long-term memory plugin, including prerequisites, setup sequence, and troubleshooting. - Clarified plugin behavior: auto-capture of conversation highlights and auto-recall of relevant memories, with configuration for intelligent extraction. - Described minimal working configuration—including OpenClaw integration, Python 3.10+ requirement, and plugin slot setup—with command examples. - Provided troubleshooting steps for frequent issues (Python version, CLI not found, unhealthy status, etc.). - Summarized available tools, plugin config fields, and daily operational commands for users.

元数据

Slug install-powermem-memory-full

版本 0.3.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题

Install Powermem Memory 是什么？

Step-by-step guide to install and configure the PowerMem long-term memory plugin (full path, options, troubleshooting). After setup, the plugin auto-captures... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 137 次。

如何安装 Install Powermem Memory？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install install-powermem-memory-full」即可一键安装，无需额外配置。

Install Powermem Memory 是免费的吗？

是的，Install Powermem Memory 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Install Powermem Memory 支持哪些平台？

Install Powermem Memory 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Install Powermem Memory？

由 powermem（@teingi）开发并维护，当前版本 v0.3.0。

Install Powermem Memory