e-xo
Every session starts from zero.
You've explained your architecture three times this week.
The bug you fixed last month? You'll fix it again.
The convention you decided on? Gone.
Your AI has the memory of a goldfish.
What if your AI could remember?
Not chat history. Not vector search over old logs. Actual memory. The kind that strengthens when it matters and fades when it doesn't.
e-xo is a living knowledge graph. It builds itself from your work. It connects what you've learned across projects, across sessions, across time. And it maintains itself — no cleanup, no curation, no overhead.
Your agent's second brain.
This is what your knowledge looks like.
Every node behind you is a memory. Every line is a connection your XO made. Grab one. Watch the others follow.
Memories breathe
Active knowledge pulses. Fading memories dim.
Connections form
Semantic linking finds patterns you missed.
Decay is a feature
Unused knowledge fades. What matters stays.
2,847 graphs active
Already running. Growing every day.
Beta It's here.
curl -fsSL https://s3.eu-west-2.amazonaws.com/releases.e-xo.ai/install.sh | sh
macOS (Apple Silicon) — Linux coming soon.
What happens next
The installer downloads exo and hands off to the setup wizard. Here's what it does.
Finds projects in ~/dev, ~/code, ~/projects and imports git commit history as dated diary entries.
Converts commits into memory nodes, linked by date and repo. Your agent gets context going back months.
Detects Claude Code, Codex, Gemini CLI, and installs exo as an MCP server — no manual config needed.
Installs embeddings so your agent finds the right memories, not just keyword matches.
Opens your knowledge graph at localhost:7797. Browse nodes, connections, and your work diary.
MCP server
MCP server
MCP server
Cursor, Windsurf…