Launched this week
Sequna
Work memory for AI agents
13 followers
Work memory for AI agents
13 followers
Install Sequna in Claude Code, Cursor, Codex, Windsurf, or any MCP-compatible agent. It captures meaningful progress, organizes work under durable goals, auto-runs safe inbox items, and gives you a structured daily review.
This feels relevant for anyone who uses AI agents for real project work instead of one-off prompts. Once you’re juggling goals, follow-ups, and unfinished threads, you need something more structured than chat history.
@sherychen That’s exactly the problem I wanted to solve.
For one-off prompts, chat history is usually enough. But once the work stretches across multiple sessions, goals, and follow-ups, the thread starts to break down fast. Sequna is built for that longer-running mode of working, where the agent needs to retain meaningful progress instead of just remembering the current conversation.
I’m especially interested in whether that framing resonates: not “better chat history,” but a real work memory layer for agent-driven workflows.