--- title: relate agent-context description: "relate, the embedded Cypher graph database (relatedb.ai): The relate agent-context command that prints a compact text briefing of the installed binary, its commands, query-run flags and exit codes, quoted in full." type: reference surfaces: - cli - agents status: stable verified: 0.1.2 verified_by: - cli canonical_url: https://relatedb.ai/docs/reference/cli/agent-context/ prerequisites: [] related: - reference/cli/agent-mode#the-agent-context-briefing - reference/cli - reference/cli/exit-codes-and-errors - get-started/agent-quickstart#read-the-briefing - guides/agents/drive-relate-from-an-agent - concepts/agent-native last_updated: 2026-11-09 --- # relate agent-context The relate agent-context command that prints a compact text briefing of the installed binary, its commands, query-run flags and exit codes, quoted in full. > Verified against relate 0.1.2. If your `relate --version` is newer, read https://relatedb.ai/docs/reference/changelog/#since-0.1.2 `relate agent-context` prints a compact plain-text briefing of the binary that runs it: its version, one line per command it contains, the names of its query-run flags, and its exit code table. With a command word, it prints that command's usage line, flags, examples, and the exit code table instead. The briefing is built from the same command table as `--help`, so it describes the installed binary and no other: the version it prints is the version that answers. It reads no store, needs no network, and takes no flags beyond `--help`. ## Synopsis ```text relate agent-context [COMMAND] ``` | Argument | Meaning | | --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | `COMMAND` | Optional. One command word: `query`, `clone`, `info`, `pull`, `push`, `skill`, `upgrade`, `telemetry`, `run`, `serve`, `agent-context` or `extension`. `update` names `upgrade`, its alias | | Run | Prints | | -------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------- | | `relate agent-context` | The version line, the command index, the query-run flag names, the exit code table | | `relate agent-context ` | ` — `, the usage line, a `Flags:` list when the command has its own flags, an `Examples:` list, the exit code table | | `relate agent-context --help` | The command's help page, exit code 0 | The output is plain text in every run, with [agent mode](https://relatedb.ai/docs/reference/glossary/#agent-mode) on or off. `RELATE_HELP_EXAMPLES=0`, which drops the examples from every `--help` page, leaves the briefing's `Examples:` list in place. ## The briefing These examples run in a new, empty directory. The whole briefing, 26 lines: ```bash verify relate agent-context ``` ```text relate v0.1.2 — agent context Commands (detail: relate agent-context ): query Run a statement session (oneshot, stdin, or shell) clone Copy a database into a new store and exit info Print store metadata for a database without opening it pull Copy a Neo4j/Aura subgraph into a database push Copy a database subgraph into Neo4j/Aura skill Install, inspect, or remove the embedded agent skill bundle upgrade Update the relate binary (alias: update) telemetry Manage anonymous usage metrics (on, off, status) run Run an installed extension action into a store the host owns serve Host the HTTP Query API and MCP surfaces on a database agent-context Print the compact agent briefing (commands, flags, exit codes) extension Scaffold, install, check, list, or remove command extensions Query-run flags (relate [OPTIONS] [QUERY]): --help --version --database --json --csv --markdown --jsonl --toon --noheader --mode --format --pretty --param --fetch-params --snapshot-format --markdown-body-properties --wal-dir --checkpoint-interval-secs --durability-mode --logical-graph-size-limit --expression-memory-limit --concurrent-logical-workspace-limit --max-traversal-depth --safe --no-safe --agent-mode --no-agent-mode --max-rows --width --timeout --load --read-only --load-csv-dir --namespace --command Exit codes: 0 success: success, including an empty result 1 fatal_error: runtime failure: store open or I/O error, capacity limit, query execution failure, internal error 2 usage_error: unknown flag, bad or missing value, extra positional 5 conflict: write-write conflict, or the store is locked by another opener 6 validation_error: the statement is rejected: syntax, semantic or type error 7 timeout: a statement exceeded --timeout ``` | Section | Holds | | ----------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Version line | `relate v — agent context`: the version of the binary that printed it | | `Commands` | Each command compiled into this binary, with the one-line summary `relate --help` prints. A build without a command leaves its line out | | `Query-run flags` | The names of the flags that the path-first form and `relate query` accept; no arguments or defaults | | `Exit codes` | Each [exit code](https://relatedb.ai/docs/reference/glossary/#exit-code), its `code` name as the [error object](https://relatedb.ai/docs/reference/glossary/#error-object) carries it, and what it means | The flag list names flags only. `relate agent-context query` repeats them with the usage line, the [relate query page](https://relatedb.ai/docs/reference/cli/query/) describes the session they apply to, and the [flags page](https://relatedb.ai/docs/reference/cli/flags/#query-run-flags) gives each one's argument, default, and environment variable. The briefing needs no network and names the release that answers; the [agent quickstart](https://relatedb.ai/docs/get-started/agent-quickstart/#read-the-briefing) and [Drive relate from an agent](https://relatedb.ai/docs/guides/agents/drive-relate-from-an-agent/) use it, and the [skill bundle](https://relatedb.ai/docs/guides/agents/install-the-skill/) lists it among its commands. ## One command A command word narrows the briefing to that command: ```bash verify relate agent-context info ``` ```text info — Print store metadata for a database without opening it Usage: relate info --database PATH [--json] Flags: --database --json Examples: # Describe a database without opening it, as JSON relate info --database ./mydata --json Exit codes: 0 success: success, including an empty result 1 fatal_error: runtime failure: store open or I/O error, capacity limit, query execution failure, internal error 2 usage_error: unknown flag, bad or missing value, extra positional 5 conflict: write-write conflict, or the store is locked by another opener 6 validation_error: the statement is rejected: syntax, semantic or type error 7 timeout: a statement exceeded --timeout ``` ## Errors and exit codes | Exit code | When | | ------------------------------------------------------------------------- | ---------------------------------------------- | | [0](https://relatedb.ai/docs/reference/cli/exit-codes-and-errors/#exit-0) | The briefing printed | | [2](https://relatedb.ai/docs/reference/cli/exit-codes-and-errors/#exit-2) | An unknown command word, or more than one word | An unknown word, or anything that is not a command word, exits 2: ```bash verify relate agent-context --json echo "exit=$?" ``` ```text Error: agent-context: unknown command '--json' (expected one of: query, clone, info, pull, push, skill, upgrade, telemetry, run, serve, agent-context, extension) Usage: relate agent-context [COMMAND] Run 'relate agent-context --help' for more information. exit=2 ``` A second word exits 2 with `Error: unexpected argument to agent-context: ` and the same two lines. ## Examples A command with no flags of its own, such as `telemetry`, prints no `Flags:` list: ```bash verify relate agent-context telemetry ``` ```text telemetry — Manage anonymous usage metrics (on, off, status) Usage: relate telemetry on|off|status Examples: # See whether anonymous usage metrics are on relate telemetry status Exit codes: 0 success: success, including an empty result 1 fatal_error: runtime failure: store open or I/O error, capacity limit, query execution failure, internal error 2 usage_error: unknown flag, bad or missing value, extra positional 5 conflict: write-write conflict, or the store is locked by another opener 6 validation_error: the statement is rejected: syntax, semantic or type error 7 timeout: a statement exceeded --timeout ``` ## See also - [Agent mode](https://relatedb.ai/docs/reference/cli/agent-mode/): detection, the row cap and the envelope, the rest of the agent-facing CLI - [relate CLI](https://relatedb.ai/docs/reference/cli/): every command with its usage line - [Exit codes and errors](https://relatedb.ai/docs/reference/cli/exit-codes-and-errors/): the exit code table with the error object's fields - [Drive relate from an agent](https://relatedb.ai/docs/guides/agents/drive-relate-from-an-agent/): the briefing, the envelope and the row cap from the agent's side ## Terms used on this page - **agent mode**: CLI defaults for a detected agent harness on a non-terminal stdout, or forced on: at most 100 rows printed per statement, the cut reported, TOON in a pipe. - **exit code**: The number a `relate` run returns to the shell; each nonzero value names a class of failure, such as 2 for usage, 5 for conflict, 6 for a rejected statement. - **error object**: The JSON object a failed query run prints on stdout in the `json`, `jsonl`, `envelope` and `speedscope` modes: the class, the kind, the message, the exit code.