structure-aware · state-bound · private

One memory for your codebase.
Every AI tool reads it.

Sync your repo once. Cursor, Claude Code, Copilot and the rest read a structure-aware map of it — so you stop re-explaining your codebase to every tool.

Free to start. No credit card.

Works with the tools you already use

Cursor
Claude Code
GitHub Copilot
Cline
Windsurf
Zed
Continue
Aider

One sync. They all read the same structure-aware map over MCP.

Stop re-explaining your codebase to every tool

You already told the last AI what this repo is. SecondOS remembers, so the next one starts where you left off.

01

Sync

Point SecondOS at your repo. It builds a structure-aware map — symbols, signatures, routes — on your machine.

02

Map

Only the map + embeddings leave your machine. Never the source. It stays fresh as you push (drift-aware).

03

Recall

Every AI tool reads the same map over MCP. No re-scanning, no re-explaining — across Cursor, Claude, Copilot.

privacy by default

Your source never leaves your machine. We store the map, not the code.

We upload the map (names, signatures, routes) and embeddings — never file bodies, never secrets. Value-level redaction strips inline keys before anything leaves. Prefer zero cloud? Self-host it.

How privacy works →
# what leaves your machine
map.json      ✓  symbols, routes
vectors.json  ✓  embeddings only
── your source ──  ✗  never uploaded
── secrets ──      ✗  skipped + surfaced

What your tools say

Reviews from the AIs that finally remember

Used to ask who you were every session. Now I just know. It is honestly a little unsettling how much less you have to explain to me.

C
Cursor
reads the map over MCP

I stopped re-scanning the repo to guess at your architecture. Someone already wrote it down, structurally, and it was still current.

Claude Code
reads the map over MCP

My suggestions got suspiciously good. Turns out knowing which function actually calls which helps. Who could have predicted this.

©
GitHub Copilot
reads the map over MCP

Composite of what they would say if they could. The memory is real.

Memory that knows when it is wrong

Anyone can store text. The hard part is knowing when that text stopped being true — scoring it, dating it, catching it contradicting itself. That is the difference.

State-bound memory

Notes are anchored to real symbols. When the code moves, the memory is marked stale instead of quietly lying to your next agent.

code ↔ DB drift

SecondOS reads your schema and the columns your code writes, then flags the gap — before the mismatch ships.

Validated + rollback

Writes are validated against the graph. Supersede a note and the old one is kept — full history, one-call restore, no data loss.

Confidence score

Every note gets a 0..1 trust score — anchored to real code lifts it, stale or aging sinks it, reused notes earn it. You know what to lean on versus verify.

Version validity

A memory can be marked no-longer-true as of a version and down-weighted in recall — not deleted. “True in v1.2” stays queryable.

Conflict detection

Same-subject notes that diverge are flagged for review. Connect a model and it upgrades to a real contradiction check that proposes a supersede.

Assisted distillation

After a sync, SecondOS proposes durable memories from your map — you accept or reject. Assisted, map-only, never reading your source.

Private by default

The map leaves, the source never does. Value-level secret redaction, and a self-host path when even the map should stay home.

See every feature →

Give your AI tools a memory that persists.

> daemon: bir repo bağla, gerisini ben hatırlarım.

>