openloomi-memory
openloomi Memory tools - search and manage the holistic context (people, projects, decisions, knowledge base, chat insights). Triggers: memory search, knowledge base, search documents, list insights, who is John, what did we decide about X, tiered memory, knowledge graph, people/projects/decisions, search-all, conversation memory
npx skills add melandlabs/openloomi --skill openloomi-memory --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
OpenLoomi Memory provides access to three searchable surfaces over a local/connected memory: Memory files (local markdown/json), Knowledge Base (documents via RAG on an OpenLoomi server), and Insights (AI-extracted records from chats and messages). It supports searching across all surfaces with a single surface, and exposes operations to add/delete memory, list/search documents and insights, and retrieve document content or specific insights.
How it works
- The skill documents a tiered memory model: raw information, insights, contextual memory, and knowledge-base memory, stored locally under ~/.openloomi/data/memory/ and synced from Connectors to an OpenLoomi server when connected.
- It provides commands such as:
- Adding a memory file via: node $SKILL_DIR/scripts/openloomi-memory.cjs add-memory "Content to remember" --file=filename.md --directory=notes
- Deleting a memory file via: node $SKILL_DIR/scripts/openloomi-memory.cjs delete-memory filename.md --directory=notes
- Searching memory with: node $SKILL_DIR/scripts/openloomi-memory.cjs search-memory "boss"
- Searching knowledge base with: node $SKILL_DIR/scripts/openloomi-memory.cjs search-knowledge "project plan"
- Listing documents with: node $SKILL_DIR/scripts/openloomi-memory.cjs list-documents
- Getting a document with: node $SKILL_DIR/scripts/openloomi-memory.cjs get-document doc_xxx
- Listing insights with time filters via: node $SKILL_DIR/scripts/openloomi-memory.cjs list-insights --days=7
- Broad search across all memory via: node $SKILL_DIR/scripts/openloomi-memory.cjs search-all "query"
- It describes authentication via a token located at ~/.openloomi/token and local filesystem structure under ~/.openloomi/data/memory/ with subfolders for chats, channels, people, projects, notes, strategy.
- The API-like sections define endpoints for knowledge base, insights, and chat-insights in the OpenLoomi server, with curl examples for interacting with the RAG search, document list/get, insights CRUD, and analytics.
When to use it
Use the memory search surface when you need to retrieve information across memory files, knowledge base documents, or derived insights. Use the search-all surface for general memory questions that should be resolved by querying all three surfaces.
What it can touch
- Local filesystem: memory files under ~/.openloomi/data/memory/ (read-only for search, write-enabled for add/delete as described).
- Knowledge Base server via RAG endpoints (openloomi server) for search and document listing/get.
- CLI script at node $SKILL_DIR/scripts/openloomi-memory.cjs to perform all operations.
Caveats
- Local memory filesystem searches are case-insensitive and operate on .md and .json files, with a max depth of 5 for memory search routines.
- Memory writes (add/delete) are described as direct operations on local files; behavior assumes proper directory creation when adding.
- The skill relies on OpenLoomi readiness and, if needed, onboarding via openloomi-setup; readiness state is noted in the instructions.
> **Note:** If OpenLoomi readiness is unknown, use `openloomi-setup` first. If OpenLoomi Desktop is not installed, follow [Getting Started](https://openloomi.ai/docs/getting-started). # OpenLoomi Memory Skill OpenLoomi Memory is the **long-lived context layer of OpenLoomi** — a tiered, locally-stored knowledge graph that grows on its own from your Connectors, chats, and Screen Capture. Memory is what makes Chat grounded and what Loop reads before it produces a Decision. It is always on your machine (local-first), always visible, and always auditable — see [Memory](https://openloomi.ai/docs/memory) for the full model. This skill exposes three searchable surfaces over that context: | Surface | What it is | Where it lives | |---|---|---| | **Memory files** | People, projects, notes, strategy — your hand-edited knowledge graph | `~/.openloomi/data/memory/` | | **Knowledge Base** | Documents you uploaded (PDF, DOCX, TXT, MD, slides, sheets, images) chunked + embedded via RAG | openloomi server | | **Insights** | AI-extracted records (decisions, action items, preferences, relationships, events) derived from chats and source messages, with usage analytics + automatic maintenance | openloo
- Overview
- Authentication
- Local Memory Filesystem
- Directory Structure
- Write Operations
- How search-memory Works
- Example Output
- API Endpoints
- Knowledge Base (RAG)
- Insights
- Insight Usage Analytics & Maintenance
- CLI Script
- Quick Start
- Command Reference
node $SKILL_DIR/scripts/openloomi-memory.cjs add-memory "Content to remember" --file=filename.md --directory=notes node $SKILL_DIR/scripts/openloomi-memory.cjs delete-memory filename.md --directory=notes curl -X POST http://localhost:3414/api/rag/search \ curl http://localhost:3414/api/rag/documents?limit=50 \ curl http://localhost:3414/api/rag/documents/doc_xxx \ curl "http://localhost:3414/api/insights?days=7&limit=50" \ curl -X POST http://localhost:3414/api/insights \ curl -X PUT http://localhost:3414/api/insights/insight_xxx \ curl "http://localhost:3414/api/insights/insight_xxx?fetch=true" \ curl -X DELETE http://localhost:3414/api/insights/insight_xxx \
What does the openloomi-memory skill do?
openloomi Memory tools - search and manage the holistic context (people, projects, decisions, knowledge base, chat insights). Triggers: memory search, knowledge base, search documents, list insights, who is John, what did we decide about X, tiered memory, knowledge graph, people/projects/decisions, search-all, conversation memory
How do I install it?
Run `npx skills add melandlabs/openloomi --skill openloomi-memory --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From melandlabs/openloomi, a repository with 764 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.