What Is Bring Your AI and What Does It Do?

Bring Your AI is a local-first toolkit for moving, syncing, distilling, or building the context around AI coding agents — specifically Claude Code, Codex, and Cursor. It exists to solve one problem: every time you switch tools, you rebuild your agent setup from scratch. Bring Your AI carries that setup across instead. It's relevant if you already have memories, rules, skills, hooks, or MCP review notes invested in one harness and don't want to lose them when you try another.

The problem it addresses

Agent setups accumulate over time. Memories, rules, voice and workflow conventions, MCP review notes, hooks, validation files, and session analytics artifacts all live inside a specific tool's configuration. When you move to a different harness, none of that transfers automatically, so you either rebuild it manually or start over with a blank rules file.

Bring Your AI treats that accumulated context as portable property rather than tool-specific baggage.

Four product paths

The toolkit separates four jobs, which is useful because they have different risk profiles:

How the migration actually works

The CLI runs on your machine. A preview step shows what will happen before anything is written:

$ bringyour preview --from claude-code --to codex
Claude Code found.
Codex found.
Move supported: yes
Existing setup can be kept: yes
Original files will not be changed.

Then the migration itself:

$ bringyour migrate --from claude-code --to codex --policy merge
rollback snapshot: ~/.codex/.bringyour-snapshots/...
validation: BRINGYOUR-VALIDATE.md
✓ memories + rules
✓ MCP review notes
✓ skills + validation
✓ rollback snapshots
! hook differences flagged
✓ PII scrub audit

Three things are worth noting in that output. The --policy merge flag keeps an existing Codex setup rather than overwriting it. Source files are read-only, and target files are snapshotted before any write, so rollback is possible. Hook differences are flagged rather than silently copied, because hooks are the part most likely to behave differently across harnesses.

Privacy and write behavior

The privacy boundary is the product's central claim: the CLI runs locally, target config stays local, and there's no hosted account required for syncing. The license check is a signed local proof after checkout with no phone-home validation. Remote MCP is described as no-data.

On writes, the stated behavior is:

• Source files are read-only
• Target files are snapshotted before write
• Merge policy preserves an existing Codex setup
• MCP migration preserves command and env references, and flags values that should stay in Keychain or environment variables

Pricing

The site lists a Team Migration Pack at $499 for up to 10 people, described as lifetime access while the product is young. A pricing page and a general buy page also exist. No subscription is mentioned. Check the current pages before purchasing, since "while the product is young" implies terms may change.

Who this is for

You're a reasonable fit if you've built meaningful context in one agent harness and are considering another, or if you work across multiple machines and want a local hub instead of a hosted sync service. The review-gated, snapshot-before-write design matters most if you're migrating hooks or MCP configuration, where a silent copy could break things.

You're probably not the target if you only use one tool on one machine and have little accumulated configuration — there's nothing to move, and building from public GitHub history is a convenience rather than a necessity.