screenpipe
Local-first workflow memory for AI agents through MCP/API.
screenpipe captures selected screen, audio, app, and meeting context locally so Claude, Codex, Cursor, and local AI workflows can search real work history through MCP and API. It helps teams turn daily work into cited notes, SOPs, workflow reports, and automation candidates while keeping sensitive context under user control.
Features
Category
Install with `npx -y screenpipe-mcp@latest`, make sure the local screenpipe app/API is running, then add the server to Claude Desktop, Cursor, Windsurf, VS Code, or any MCP client.
search
Search local screen, audio, app, and meeting history captured by screenpipe.
query_memory
Retrieve workflow context and cited historical activity for AI agents.
local workflow memory
Local-first screen, audio, app, and meeting context indexed for MCP clients.
screenpipe://memory/{query}
{"mcpServers":{"screenpipe":{"command":"npx","args":["-y","screenpipe-mcp@latest"]}}}Context7
Up-to-date code documentation for LLMs and AI code editors.
Cognee
Memory manager with graph/vector stores, 30+ data sources.
Mem0
Manages coding preferences/patterns for IDEs like Cursor.
Graphlit
Ingests from Slack/Discord/websites into knowledge graphs.
MCP Ragdocs
Vector search for documentation retrieval.
Ragie AI
Retrieves from RAG knowledge bases (e.g., Google Drive, Notion).