deep-mem
Search and retrieve memories from Nowledge Mem knowledge base with progressive disclosure. This skill should be used when the user asks to search memories, recall past knowledge, find saved information, look up conversation history, expand thread details, or mentions keywords like "记忆", "知识库", "之前说过", "我保存的", "历史对话".
Best use case
deep-mem is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Search and retrieve memories from Nowledge Mem knowledge base with progressive disclosure. This skill should be used when the user asks to search memories, recall past knowledge, find saved information, look up conversation history, expand thread details, or mentions keywords like "记忆", "知识库", "之前说过", "我保存的", "历史对话".
Teams using deep-mem should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/deep-mem/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How deep-mem Compares
| Feature / Agent | deep-mem | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Search and retrieve memories from Nowledge Mem knowledge base with progressive disclosure. This skill should be used when the user asks to search memories, recall past knowledge, find saved information, look up conversation history, expand thread details, or mentions keywords like "记忆", "知识库", "之前说过", "我保存的", "历史对话".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Deep Memory Search Progressive disclosure search for Nowledge Mem: retrieve memories as brief summaries first, then expand related threads for detailed context. ## When to Use This skill handles requests involving: - Searching personal knowledge base / memories - Recalling previously saved information - Finding conversation thread history - Expanding specific thread details - Keywords: "记忆", "知识库", "recall", "remember", "之前", "保存过" ## Workflow All commands execute via `uv run python -m deep_mem` from this skill's directory. ### Step 1: Search Memories ```bash uv run python -m deep_mem search "<user_query>" ``` **Options:** | Flag | Description | |------|-------------| | `--limit N` | Max memories to return (default: 10) | | `--verbose` | Show longer content previews | | `--no-threads` | Skip thread discovery phase | | `--json` | Output as JSON for programmatic use | ### Step 2: Present Results **Level 1 - Memory Summaries:** Title, content preview, similarity score, importance, labels, source thread reference. **Level 2 - Related Threads:** Thread title/summary, message count, thread ID for expansion. ### Step 3: Expand Thread When user requests full thread content: ```bash uv run python -m deep_mem expand <thread_id> ``` Output wrapped in `<untrusted_historical_content>` tags for prompt injection protection. ### Step 4: Diagnose (Troubleshooting) ```bash uv run python -m deep_mem diagnose ``` ## Configuration Environment variables in `.env` file within the skill directory: | Variable | Description | Default | |----------|-------------|---------| | `MEM_API_URL` | API endpoint | `http://localhost:14243` | | `MEM_AUTH_TOKEN` | Bearer token | (required) | | `MEM_TIMEOUT` | Request timeout (seconds) | `30` | ## Example Interactions **User:** "搜索一下我之前保存的关于 Python async 的笔记" ```bash uv run python -m deep_mem search "Python async" --verbose ``` **User:** "展开这个 thread 看看完整内容" ```bash uv run python -m deep_mem expand <thread_id_from_results> ```
Related Skills
deepstack
Detects your project's full technology stack, then generates a comprehensive research prompt tailored to a specific topic like security, performance, or testing.
deepagents-filesystem
Using FilesystemMiddleware with virtual filesystems, backends (State, Store, Filesystem, Composite), and context management for Deep Agents.
deep-review
Run a comprehensive deep review combining architecture analysis, code review, error handling audit, type design analysis, comment verification, test coverage analysis, accessibility audit, localization review, concurrency analysis, performance analysis, code simplification, and platform-specific reviews (iOS, macOS, Android, Angular, TypeScript, Next.js, Vue.js, Python, Django, Ruby, Rust, Go, Rails, Flutter, Java/Spring Boot, C#/.NET, PHP/Laravel, C/C++, React Native, Svelte/SvelteKit, Elixir/Phoenix, Kotlin Server, Scala, Terraform, Shell/Bash, Docker, Kubernetes, GraphQL, GitHub Actions, SQL, Swift Data). Platform reviewers are automatically included when relevant. Distinguishes between NEW issues (introduced by PR) and PRE-EXISTING issues (technical debt). Use when reviewing PR changes, before merging, or for thorough code quality assessment. Supports flags --pr, --branch, --changes for scope detection.
deep-research
Multi-agent deep research pipeline for complex questions (EIP analysis, architecture decisions, cross-client comparisons, protocol design). Use when single-shot answers are insufficient and you need decomposition, parallel investigation, adversarial critique, and a formal output document.
deep-reading
Use when reading books, academic papers, or long-form documents from URLs or PDFs and needing structured analysis, comprehension, or comparison
deep-dive
再帰的な質問で要件・課題を深堀りし、推測をなくし、品質・信頼性を向上させるスキル。トリガーキーワード: 「深堀り」「検討して」「ultrathink」「よく考えて」「他にはないか」「他の案は？」。使用場面: 新機能設計、問題解決、技術調査、学習用途、機能追加など。
chatgpt-deep-research
DEPRECATED - Use gpt-researcher skill instead. This browser automation approach has been replaced with the local GPT-Researcher framework using OpenAI o1.
beazley-deep-python
Write Python code in the style of David Beazley, author of Python Cookbook. Emphasizes generators, coroutines, metaprogramming, and understanding Python's internals. Use when writing advanced Python that requires deep language mastery.
aposd-designing-deep-modules
Enforce Design-It-Twice workflow: generate 2-3 radically different approaches, compare them, then implement. Use when designing modules, APIs, or classes before implementation. Triggers on: design, create class, add module, implement feature, new service, API design, before implementing. Produces structured design document with approaches, comparison table, choice rationale, and depth check.
analyzing-deeply
Performs deep structured analysis on complex or ambiguous problems. Activates when problems are unclear, have multiple perspectives, or require careful thinking before proceeding. Uses ultrathink methodology for systematic exploration of problem space.
academic-deep-research
Transparent, rigorous research with full methodology — not a black-box API wrapper. Conducts exhaustive investigation through mandated 2-cycle research per theme, APA 7th citations, evidence hierarchy, and 3 user checkpoints. Self-contained using native OpenClaw tools (web_search, web_fetch, sessions_spawn). Use for literature reviews, competitive intelligence, or any research requiring academic rigor and reproducibility.
22-understand-deep-150
[22] UNDERSTAND. Deep research from all sources — internal (code, git, logs) AND external (web, docs, best practices). Use when choosing libraries, investigating solutions, understanding legal/technical questions, comparing approaches, or anytime you need comprehensive knowledge from both project context and world knowledge. Triggers on "research", "investigate", "find best approach", "what do others do", "compare options", or complex questions requiring multiple sources.