菜单
Check Nowledge Mem setup, detect your agent, and guide native connector setup. Use when the user asks about setup, configuration, or when memory tools aren't working as expected.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | check-integration |
| description | Check Nowledge Mem setup, detect your agent, and guide native connector setup. Use when the user asks about setup, configuration, or when memory tools aren't working as expected. |
Verify Nowledge Mem is running and guide the user to the best connector for their agent.
nmem --json status
Use this rule before repairing anything:
nmem. Ask the user to open Nowledge Mem; if the command is still missing, use Settings → Preferences → Developer Tools → Install bundled CLI.nmem-cli on this machine, then point it at the user's Mem server. This covers remote servers, dev boxes, CI runners, hosted agents, and SSH machines. Python 3.11+ is required.Do not install the PyPI CLI over the desktop-bundled CLI on the user's own desktop unless the user explicitly asks for a standalone CLI.
If the agent is not on the desktop machine and nmem is missing, install the PyPI CLI:
python3 -m pip install --user nmem-cli
# or: pipx install nmem-cli
# or for one-off checks: uvx --from nmem-cli nmem --json status
nmem config client set url https://<their-mem-server>
nmem config client set api-key nmem_...
nmem --json status
If nmem exists but status fails, Nowledge Mem is not reachable from this machine. Guide the user:
nmem --json statusnmem config client showFor a fresh install, start from the universal connect skill:
Read https://mem.nowledge.co/SKILL.md and follow the instructions to install or update Nowledge Mem for the AI tool I am using.
Use this check-integration skill as the diagnostic fallback: confirm what was installed, explain what behavior the user should expect, and repair configuration when something failed.
Do not only answer "install X". Explain the behavior contract the user will get:
Use this priority order:
Fresh users care about outcome, not transport. Tell them what they will actually get after setup.
| Path | What usually happens | What it does not guarantee |
|---|---|---|
| Native connector | Strongest setup: session bootstrap is often automatic; some hosts also add auto-capture or hook-driven recall | Exact proactive recall/distill timing can still be host-specific |
| Reusable package | Working Memory, recall, and distill are guided by rules/skills | The host may still ignore the guidance unless prompts and project guidance are strong |
| Direct MCP | Tools are available; with the recommended prompt block, the agent can use them proactively | MCP alone does not create host-enforced autonomy |
Check which agent you're running in and recommend the native connector if available.
The canonical source for this table is community/integrations.json.
| Agent | How to Detect | Native connector setup | Docs |
|---|---|---|---|
| Claude Code | Running as Claude Code agent; ~/.claude/ exists | claude plugin marketplace add https://github.com/nowledge-co/community && claude plugin install nowledge-mem@nowledge-community | Guide |
| Grok | Running as Grok; ~/.grok/ exists | grok plugin install nowledge-co/community#nowledge-mem-claude-code-plugin --trust | Guide |
| OpenClaw | Running as OpenClaw agent; ~/.openclaw/ exists | openclaw plugins install clawhub:@nowledge/openclaw-nowledge-mem | Guide |
| Cursor | Running inside Cursor IDE | Copy nowledge-mem-cursor-plugin from the community repo into ~/.cursor/plugins/local/nowledge-mem-cursor, then reload Cursor | Guide |
| Gemini CLI | Running as Gemini CLI agent; ~/.gemini/ exists | gemini extensions install https://github.com/nowledge-co/nowledge-mem-gemini-cli --auto-update or install "Nowledge Mem" from the Extensions Gallery | Guide |
| Antigravity 2.0 | Running as Antigravity; ~/.gemini/antigravity/ exists | Use npx skills add nowledge-co/community/nowledge-mem-npx-skills; global skills should appear under ~/.gemini/config/skills, not the old ~/.gemini/antigravity/skills path. For conversation import, use the Antigravity Trajectory Extractor. | Import guide |
| Alma | Running inside Alma; ~/.config/alma/ exists | In Alma: Settings > Plugins > Marketplace, search "Nowledge Mem" | Guide |
| Droid | Running inside Droid (Factory) | Add nowledge-co/community marketplace, install nowledge-mem@nowledge-community | Guide |
| Codex | Running inside Codex desktop or Codex CLI; ~/.codex/ exists | codex plugin marketplace add nowledge-co/community --sparse .agents --sparse nowledge-mem-codex-plugin && codex plugin add nowledge-mem@nowledge-community, enable [features] plugins = true, hooks = true, plugin_hooks = true, and [plugins."nowledge-mem@nowledge-community"] enabled = true, then run the installed scripts/install_hooks.py once for automatic thread capture. Add mcp_servers.nowledge-mem only when overriding the bundled local MCP endpoint. The desktop app and CLI share the same ~/.codex config. | Guide |
| Bub | Running inside Bub | pip install nowledge-mem-bub | Guide |
| Pi | Running as Pi agent; ~/.pi/ exists | pi install npm:nowledge-mem-pi | Guide |
| OMP | Running as OMP agent; ~/.omp/ exists | omp plugin install nowledge-mem-omp | Guide |
| OpenCode | Running as OpenCode agent; ~/.config/opencode/ or .opencode/ exists | opencode plugin opencode-nowledge-mem -g; restart OpenCode so idle-event capture hooks load | Guide |
| Craft Agent | Running inside Craft Agent; ~/.craft-agent/ exists or CRAFT_CONFIG_DIR is set | nmem config mcp show --host craft-agent, then add the generated source config and guide to the active Craft workspace. Use nmem t sync --from craft-agent --all-projects --apply for real session import. | Guide |
| Hermes Agent | Running as Hermes agent; ~/.hermes/ exists | Install the native Hermes provider (or use MCP only as fallback) | Guide |
For Hermes updates, run the setup command from the guide and confirm it prints Thread import endpoint: /threads/import. If it prints an old endpoint or no endpoint, the user is likely launching Hermes with a different HERMES_HOME; set that explicitly and rerun setup before restart.
If the agent is not listed above:
npx skills package when the host supports itDo not describe raw MCP as equivalent to a native connector.
After setup, verify with:
nmem --json m search "test" -n 1
If this returns results (or an empty list with no error), the connector is working.
Then state the expected outcome in plain language:
If the path is only guided, say what strengthens it:
nmem available locallyAGENTS.md or equivalent repo guidance when recommendednmem client in remote modeSkills give you CLI-based memory access. Native connectors usually add:
/remember, /recall, /forget (where supported)Do not promise all of these on every host. Match the actual path the user is setting up.
Use Nowledge Mem from WorkBuddy or CodeBuddy for startup context, memory search, durable saves, thread search, and WorkBuddy/CodeBuddy transcript import.
Read your daily Working Memory briefing to understand current context. Contains active focus areas, priorities, unresolved flags, and recent knowledge changes. Load this automatically at the beginning of sessions for cross-tool continuity.
Search memory store when past insights would improve response. Recognize when user's stored breakthroughs, decisions, or solutions are relevant. Search proactively based on context, not just explicit requests.
Use Nowledge Mem from Kimi Code for startup context, memory search, durable saves, thread search, and Kimi Code transcript import.
Save decisions, insights, preferences, and procedures as durable memories. Fires when the conversation produces knowledge worth keeping across sessions.
Load today's Working Memory briefing at session start. Shows your current focus areas, priorities, and recent knowledge changes across all AI tools.