Agent skill · writing content · aiskillstore
opencontext
Persistent memory and context management for AI agents using OpenContext. Keep context across sessions/repos/dates, store conclusions, and provide document search workflows.
Why this skill is useful
Provides specific commands and workflows for managing persistent memory and context that the AI wouldn't reliably generate on its own.
What it needs
Requires npm installed locally. About 4k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
OpenContext Context Management (Persistent Memory) Give your AI assistant persistent memory. Stop repeating explanations, and build smarter. When to use this skill When you need to keep context across sessions When you need to record project background/decisions When you need to search prior conclusions/lessons When you need knowledge sharing in a Multi-Agent workflow When you want to reduce repetitive background explanations --- 1. Core concepts Problem When working with an AI assistant, context gets lost (across sessions, repos, and dates). You end up repeating background, re-explaining decisions, and sometimes the assistant continues with incorrect assumptions. Solution OpenContext is a lightweight personal context/knowledge store for AI assistants. Default paths Item Path ------ ------ Contexts ~/.opencontext/contexts Database ~/.opencontext/opencontext.db --- 2. Install and initialize Install CLI Initialize (run inside the repo) What oc init does: Prepare the global context store (on first run) Generate user-level commands/skills + mcp.json for the selected tool Update the repo's AGENTS.md --- 3. Slash Commands Beginner-friendly commands Command Purpose --------- ------ /opencontext-help When you don't know where to start /opencontext-context (Recommended default) Load background before work /opencontext-search Search existing documents /opencontext-create Create a new document/idea /opencontext-iterate Store conclusions and citations Install locations --- 4. Core CLI commands Folder/document management Search & manifest Search modes Mode Description Requirements ------ ------ ---------- --mode keyword Keyword-based search No embeddings required --mode vector Vector search Embeddings + index required --mode hybrid Hybrid (default) Embeddings + index required Embedding configuration (for semantic search) --- 5. MCP Tools OpenContext MCP Tools Multi-Agent integration --- 6. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/opencontext