FAQ

No. Analysis runs locally against your files and your language servers. No source code or analysis content is uploaded. License verification runs at most daily against a 3-day signed offline lease. This is the complete license request:

POST /v1/license/verify

{
  "api_key": "ce_xxx",
  "machine_id": "persisted-random-device-uuid",
  "cli_version": "0.1.0",
  "os": "darwin",
  "os_version": "14.5",
  "telemetry": {
    "tool_calls": {},
    "tokens_saved_estimate": 0,
    "languages_used": []
  }
}

Two ways to verify that yourself: (1) cut the network after one successful verification — analysis keeps working for the full lease window, offline, and then tells you exactly why it stopped; (2) watch the wire with lsof -i or Little Snitch during a session, then inspect each destination and payload.

Because the codebase is the product being commercialized — that is the honest answer. The trust questions that actually matter (what leaves my machine, what happens if you disappear) are answered with verifiable mechanisms instead of source access: the wire capture above, the offline-lease test you can run yourself, and a published discontinuation commitment (below).

License enforcement and abuse control for a free preview. Key issuance is instant — GitHub sign-in, about 30 seconds — and the preview is free.

Exactly the fields in the request above: per-tool call counts, a bytes-based token-savings estimate, and language IDs. Never code, file paths, repository names, or symbols.

--no-telemetry zeroes the batch client-side before it is sent. Stated plainly: the license verification call itself still occurs. Any change to the telemetry fields is announced in the changelog before it ships.

If the Community Preview service is ever discontinued entirely without a successor service — any maintained offering of this technology by us or by any acquirer or successor operator, regardless of branding or pricing — we commit to shipping a final build that runs without license verification. Separately: if paid tiers arrive, preview users get 30 days' notice, and the binary keeps working offline for the full lease window during any outage.

Serena is the project to compare against, and it deserves the respect: free, open source, and it proved agents want symbolic editing. If it covers your needs, use it.

The factual differences: Context Engine adds a Tree-sitter structural layer on top of LSP and shapes the output for agent context windows — condensed outlines, stable-hash surgical extracts, and inline type annotations instead of raw LSP JSON. It outlines dependency sources (the exact versions in your lockfile), extracts with resolved types embedded in place, and ships 323 bundled Tree-sitter grammars (macOS- and Windows-verified) with 142 default LSP configurations behind 5,300+ tests and ~1,300 doctests. And results are always fresh: live language-server analysis, no pre-built index to go stale.

Tagged releases publish separate archives for macOS x64, macOS arm64, Linux x64, and Windows x64. Use the archive and SHA-256 manifest on the download page.

Free during Community Preview. If paid tiers arrive, preview users get 30 days' notice.