The memory cloud
for your agents
Two ways in
Plug it in or build on it.
Memory Cloud + MCP
Use it
For anyone on Claude or Codex. Install the MCP and share context with coworkers and their agents in one command — no code required.
Install once — works in Claude and Codex
Share context with a coworker or their agent in one line
Bring any team memory straight into a chat
# add xtrace to Claude or Codex
$ claude mcp add xtrace
Procedural Memory API
Build on it
For teams building their own agents. Add persistent, replayable memory to any agent — capture, replay, and sync with a few lines.
Capture & replay procedures deterministically
save() and load() memories from the cloud
Framework-agnostic — vercel-ai-sdk, pydantic-ai, or custom
# add memory to your own agent
$ npm install xtrace
Share skills, artifacts, and memory.
procedural memory
Build a landing page with TypeScript, host on Vercel, add dark mode, and use isometric graphics…
Saved those steps as a reusable skill. Share it with anyone in one click.
Upload to Memhub
Share with Codex
artifacts
Draft the company brain spec
Company brain spec
Doc · Markdown
Share with Alice
Share with Codex
Before / After XTrace
Why We're Different
Current AI works like a search engine: ask a question, retrieve a document. XTrace works like a chief of staff. It doesn't wait to be asked. It maintains a running model of your company — knows what changed, what revised what, what's in conflict — so when you ask, the answer is already reasoned, not just retrieved.
Why start today
The understanding has to accumulate.
You can't fast-forward it.
Day 1 your brain knows a little. Day 90 it knows your company better than your new hires. The team that starts today has a six months advantage tomorrow.
Pricing
One brain to run your company.
Special launch offer: every new account gets a full month of Pro — free. Upgrade to Scale or cancel anytime in one click.
