ob-labs/memory-powermem/install-memory-powermem-full
Claude Code and agent skill by ob-labs/memory-powermem
- community
Checking that the SKILL.md file is still in the repository.
OpenClaw full guide skill (id and folder name install-memory-powermem-full). Step-by-step install and configuration for the PowerMem long-term memory plugin—default powermem-ts (npm) CLI, optional Python pmem, HTTP, tools, troubleshooting—and bundled reference docs. Complements install-memory-powermem; either can be used alone.
Install
npx vskill@latest install ob-labs/memory-powermem/install-memory-powermem-fullSKILL.md
PowerMem Memory — Full Guide
Skill id / OpenClaw folder name: install-memory-powermem-full. For the shortest install-only path, use `install-memory-powermem` (quickstart).
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
<relevant-memories>block into context. - Auto-Experience: Optionally distills procedural experiences and stores them as memories for later recall.
When User Asks to Install
Recommended order (TO C): (1) OpenClaw installed and default model + provider auth configured. (2) Install the memory-powermem plugin. (3) Default CLI uses powermem-ts (npm package `powermem`) via `pmemPath: bundled`—no Python required; the plugin’s npm install / pnpm install pulls powermem, `@langchain/openai`, and native deps (`better-sqlite3`). (4) Optional: use Python pmem from oceanbase/powermem instead by setting `pmemPath` to the venv binary. No `powermem.env` is required for the default path when `useOpenClawModel` is true.
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 require pip install powermem. That file is not required if the user relies on OpenClaw-injected LLM + default SQLite + bundled npm CLI.
- 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).
- Install the plugin
openclaw plugins install /path/to/memory-powermem (or openclaw plugins install memory-powermem from npm), or run `install.sh` from the memory-powermem repo — see One-click plugin deploy (`install.sh`) below for curl / flags / --workdir.
- PowerMem CLI — default: powermem-ts (npm), no Python
- Plugin default `pmemPath: bundled`: runs the `powermem` npm package (TypeScript / powermem-ts) shipped with the plugin (
node_modules/.../powermem/dist/cli.js). - After
openclaw plugins installor `install.sh`, dependencies are installed under the plugin directory; for a local path / symlink install, run `pnpm install` / `npm install` in that directory. - pnpm 10+: allow `better-sqlite3` install scripts (see plugin `package.json` → `pnpm.onlyBuiltDependencies`) or run `pnpm rebuild better-sqlite3` if the native module failed to build.
- Defaults: Plugin injects SQLite at
<OpenClaw stateDir>/powermem/data/powermem.dband LLM + embedding env vars derived from OpenClaw. TypicalstateDiris~/.openclawunless the user uses another instance (OPENCLAW_STATE_DIR,--workdir). - Optional `envFile`: Path to a PowerMem
.envfor extra tuning. If the file exists,pmemloads it; OpenClaw-derived vars still override the same keys whenuseOpenClawModelis true. - `useOpenClawModel: false`: Disables injection; user must supply a complete PowerMem config via
.envand/or environment variables.
- Optional: Python CLI instead of bundled npm
For oceanbase/powermem Python pmem: Python 3.10+, venv + pip install powermem, then set `pmemPath` to the absolute path of the pmem binary (gateway may not inherit venv PATH). Verify with `pmem --version`.
- HTTP path (enterprise / shared server)
- Run `powermem-server` from the same powermem-ts stack (npm) or from a Python/Docker deployment;
.envin server working directory with DB + LLM + embedding; e.g.powermem-server --host 0.0.0.0 --port 8000. - Check:
curl -s http://localhost:8000/api/v1/system/health(or/api/v2/system/healthfor v2).
- Configure OpenClaw
CLI — defaults (recommended, matches plugin defaults): Do not set envFile unless you need a file. Example:
``bash 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 bundled 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.autoExperience true --json openclaw config set plugins.entries.memory-powermem.config.experienceRecall true --json openclaw config set plugins.entries.memory-powermem.config.inferOnAdd true --json ``
CLI — optional `.env` override file:
``bash 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:
``bash 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. For v2, set: ``bash openclaw config set plugins.entries.memory-powermem.config.httpApiVersion v2 openclaw config set plugins.entries.memory-powermem.config.requestConfig '{"memory_db":{"host":"db-host","port":2881}}' --json ``
- Verify
Restart gateway, then in another terminal:
``bash 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.
``bash openclaw ltm health openclaw ltm add "I prefer coffee in the morning" openclaw ltm search "coffee" ``
One-click plugin deploy (install.sh)
Requires: OpenClaw installed (openclaw --version). The script runs `npm install` (or equivalent) inside the deployed plugin directory so powermem-ts is available; it does not run pip install powermem. Default `pmemPath` is `bundled` (npm CLI).
Default: configures plugin CLI mode. With `-y`, it may still create `~/.openclaw/powermem/powermem.env` as an optional template — not required if you use OpenClaw-injected LLM + default SQLite + bundled CLI.
From a local clone (no download):
Non-interactive (defaults: CLI, may seed env file):
Target a different OpenClaw instance:
What the script does: resolve OpenClaw workdir → choose or default cli / http and paths → for CLI, optionally seed powermem.env if missing → deploy plugin to <workdir>/extensions/memory-powermem → npm install there → set OpenClaw config (plugins.enabled, slots.memory, entries.memory-powermem).
After (CLI): openclaw gateway, then openclaw ltm health — you usually do not need to edit powermem.env when using plugin defaults.
After (HTTP): start PowerMem with a proper .env in the server cwd, then start the gateway.
Copy a skill into OpenClaw
Copy one skill you want into ~/.openclaw/skills/<skill-name>/ (folder name should match the skill id). The quickstart and full-guide skills are independent.
Quickstart (`install-memory-powermem`) — Linux / macOS:
Full guide (`install-memory-powermem-full`) — Linux / macOS: copy all .md files in that folder.
Full guide — Windows (PowerShell):
Multi-instance OpenClaw (--workdir / OPENCLAW_STATE_DIR)
Install script:
Manual config for that instance:
Plugin data and default SQLite follow that instance’s stateDir.
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. | |
| experience_store | Store a procedural experience. | |
| experience_recall | Recall experiences. | |
| agent_memory_add | Add memory to another agent (HTTP v2 only). | |
| agent_memory_list | List an agent’s memories (HTTP v2 only). | |
| agent_memory_share | Share memories across agents (HTTP v2 only). | |
| agent_memory_shared | List memories shared with an agent (HTTP v2 only). |
Configuration (summary)
This is the start of the file. Read the full SKILL.md on GitHub.
Security
- Security scanPassed, 96 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/install-memory-powermem-full/SKILL.md
Popularity
- Repository stars
- 30
- Repository forks
- 7
- 7-day trend score
- 17
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/ob-labs/memory-powermem/install-memory-powermem-full)