agenteye 0.1.4

Command-line client for the AgentEye dashboard API

AgentEye CLI (agenteye)

A command-line client for the AgentEye dashboard API. It lets a developer — or the coding agent working alongside them — authenticate and query agent sessions, event logs, and evaluations from the terminal, with a --json flag on every command for scripting.

This is the agenteye CLI, distinct from the collector daemon (agenteye-collector). The PyPI package and the installed command are both agenteye.

Install

pipx install agenteye      # recommended (isolated)
# or: uv tool install agenteye  /  pip install agenteye

Install isolated (pipx / uv tool) — the AgentEye Python SDK shares the agenteye distribution name, so isolation avoids a clash in a shared virtualenv.

For development in this repo:

cd cli
uv sync --extra dev
uv run agenteye --help

Authentication

The CLI talks to your dashboard (set --base-url or AGENTEYE_DASHBOARD_URL) and logs in with an emailed one-time code:

agenteye login --email [e-mail]
# enter the 6-digit code; the session is stored in ~/.agenteye/cli.json (mode 0600)
agenteye whoami
agenteye logout

Sessions expire (24h by default); re-run agenteye login when prompted.

Commands

agenteye sessions [--since 24h] [--status error] [--agent-id <id>] [--score helpfulness:..0.5] [--all]
agenteye events --session-id <id> [--event-type tool_use,tool_result] [--all]
agenteye logs ...                       # alias of events
agenteye evals --score helpfulness:0.5..0.8 --latest-per-session
agenteye session show <id>
agenteye session export <id> -o out.json
agenteye re-evaluate <id>
agenteye jobs                           # in-flight evaluation queue
agenteye environments [--source events|evals]
agenteye version                        # print the CLI version
agenteye help                           # show top-level help

Every command and subcommand has --help / -h; agenteye -h documents auth, exit codes, and the global options. Global options go before the command (agenteye --json events, not agenteye events --json).

Add --json for machine-readable output, and --fields to project just the keys you need:

agenteye --json events --session-id run-001 --all | jq '.events[].payload'
agenteye --json sessions --since 7d --fields session_id,status,scores

Configuration

Setting	Flag	Env var	Default
Dashboard URL	--base-url	AGENTEYE_DASHBOARD_URL	required (no default)
Session token	--token	AGENTEYE_CLI_TOKEN	from ~/.agenteye/cli.json
JSON output	--json	AGENTEYE_CLI_JSON	off
Skip TLS verification	--insecure / --secure	AGENTEYE_INSECURE	off (saved at login)
Disable usage telemetry	(none)	AGENTEYE_ANALYTICS_DISABLED (or DO_NOT_TRACK)	telemetry on

Precedence is flag > environment variable > config file. The dashboard URL is required (no default) — set --base-url or AGENTEYE_DASHBOARD_URL, or it's saved after your first login. The config directory honours AGENTEYE_HOME (same as the SDK and collector).

For a dashboard with a self-signed or internal TLS certificate, add --insecure to skip certificate verification (saved at login, so you set it once). This disables protection against man-in-the-middle attacks — prefer a valid certificate outside internal/testing use.

Telemetry

The CLI sends anonymous usage analytics (which commands run, success/exit status, and duration) to help prioritise improvements. No data, URLs, tokens, emails, or query values are ever sent, and operators are identified only by an opaque id. It's on by default — disable it with AGENTEYE_ANALYTICS_DISABLED=1 (or the cross-tool DO_NOT_TRACK=1). Sending is time-bounded, so it never delays a command. See enterprise-docs/cli.md for the full privacy details.

Exit codes

Code	Meaning
0	Success
2	Usage error (bad arguments)
3	Cannot reach the dashboard
4	Not logged in / session expired
5	Authenticated but missing permission

Tests

cd cli
uv run --extra dev pytest