> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lyzr.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Configuration

> Global settings, per-project config, environment variables, and memory scoping

## Global Settings

Stored in `~/.cognis-claude/settings.json`. These apply to all projects.

| Setting             | Type       | Default     | Description                                                         |
| ------------------- | ---------- | ----------- | ------------------------------------------------------------------- |
| `apiKey`            | `string`   | —           | Your Lyzr API key                                                   |
| `maxMemoryItems`    | `number`   | `5`         | Maximum memories loaded into session context                        |
| `debug`             | `boolean`  | `false`     | Enable debug logging                                                |
| `signalExtraction`  | `boolean`  | `false`     | Only capture important conversation turns (instead of full session) |
| `signalKeywords`    | `string[]` | 17 built-in | Keywords that trigger signal capture                                |
| `signalTurnsBefore` | `number`   | `3`         | Context turns to include before a signal keyword                    |

**Default signal keywords:** `remember`, `architecture`, `bug`, `fix`, `pattern`, `convention`, `decision`, `important`, `note`, `todo`, `caveat`, `workaround`, `implementation`, `refactor`, `solution`, `design`, `tradeoff`

## Per-Project Config

Override settings per project in `.claude/.cognis-claude/config.json`. Run `/claude-cognis:project-config` to configure interactively, or create the file manually.

| Setting            | Type       | Default         | Description                                 |
| ------------------ | ---------- | --------------- | ------------------------------------------- |
| `apiKey`           | `string`   | Global key      | Project-specific API key                    |
| `ownerId`          | `string`   | System username | Override the owner identifier               |
| `agentId`          | `string`   | Auto-generated  | Override the personal agent ID              |
| `repoAgentId`      | `string`   | `repo_<name>`   | Override the team agent ID                  |
| `signalExtraction` | `boolean`  | Global setting  | Override signal extraction for this project |
| `signalKeywords`   | `string[]` | Global setting  | Override signal keywords for this project   |

## Environment Variables

| Variable                   | Default                         | Description                                                    |
| -------------------------- | ------------------------------- | -------------------------------------------------------------- |
| `LYZR_API_KEY`             | —                               | Lyzr API key (required if not in settings)                     |
| `COGNIS_API_URL`           | `https://memory.studio.lyzr.ai` | Custom API base URL                                            |
| `COGNIS_OWNER_ID`          | System username                 | Override owner identifier                                      |
| `COGNIS_PRIVATE`           | `false`                         | Set `true` to disable cross-session memories for this terminal |
| `COGNIS_ISOLATE_WORKTREES` | `false`                         | Set `true` to treat git worktrees as separate projects         |

## API Key Priority

Keys are resolved in this order (first found wins):

1. Per-project config (`.claude/.cognis-claude/config.json`)
2. Environment variable (`LYZR_API_KEY`)
3. Global settings (`~/.cognis-claude/settings.json`)

## Memory Scoping

Cognis separates memory into two scopes:

**Personal memory** — Tied to your identity and the current project. Only you see these. The `agent_id` is derived from a SHA256 hash of your git root, making it unique per project per user.

**Team memory** — Tied to the repository name. Shared across everyone using the plugin on the same repo. The `agent_id` is the sanitized repo name (e.g., `repo_my_project`).

When you search memories, both scopes are queried by default so you get the full picture.

## Privacy and Data

* **No data sent without an API key.** If `LYZR_API_KEY` is not set, all hooks exit immediately — no network requests
* **SessionStart hook** sends search queries to retrieve your stored memories. No conversation data is sent
* **UserPromptSubmit hook** sends the first 150 characters of your prompt to find relevant memories. Trivial inputs ("yes", "ok", slash commands) are skipped
* **Stop hook** sends a compressed summary of your session. Tool outputs are intelligently abbreviated (file edits become one-line summaries). Raw transcripts are not stored
* **All data is scoped** to your `owner_id` and `agent_id`
* **Signal extraction** (`signalExtraction: true`) limits capture to turns containing specific keywords, rather than the full session
* **Privacy mode** (`COGNIS_PRIVATE=true`) disables memory entirely for a terminal session
* **Delete your data** anytime using the `delete_memory` or `delete_all_memories` MCP tools