Skip to main content

Restart-on-exit supervisor for autonomous CLI agents

Project description

中文 · English

CI PyPI Downloads License codecov

agent-runner

A restart-on-exit supervisor for autonomous coding CLIs. Tested with Claude Code and aider out of the box; any prompt-arg CLI via custom config. Spawn the agent round-after-round under defenses that prevent the failure modes that bite in production: stuck rounds, orphan commits, OAuth burn loops, full disks, runaway memory.

┌──────────────────────────────────────────┐
│ Layer 3: The Witness (monitor)           │  11 detectors + auto-stop
├──────────────────────────────────────────┤
│ Layer 2: The Loop (serve, ~120 LOC)      │  signal-trapping restart loop
├──────────────────────────────────────────┤
│ Layer 1: The Round (round)               │  one agent invocation
└──────────────────────────────────────────┘

Install

pip install cli-agent-runner

The installed CLI command is agent-runner (the PyPI distribution name is prefixed for namespace disambiguation; the import name and command are not).

Quick start

cd your-project
agent-runner init                 # scaffold agent-runner.toml + prompts/main.md
$EDITOR agent-runner.toml         # point agent.command at your CLI
agent-runner install --monitor    # systemd user units for serve + monitor
agent-runner status               # confirm running
agent-runner peek                 # snapshot of project state
agent-runner monitor              # live anomaly detection

Full walkthrough: docs/quickstart.md.

14 verbs

Lifecycle Observation
init / install / uninstall peek — state snapshot
start / stop / kill / cancel watch — peek in a refresh loop
restart / status monitor — 11 detectors, alerts, auto-stop
round / serve / upgrade events — query / stream events.jsonl

Verb reference: docs/commands.md.

Defenses (built in)

11 named defenses, structured as data — see agent-runner peek --select defenses. Each carries the historical incident it codifies and the invariant test that guards it. Highlights:

  • round_timeout_s — hard wall, never the agent's word on when to stop
  • process_group_isolation — kill the round, not just the parent
  • orphan_stash_idempotency_s — no 3-stashes-per-second pile-ups
  • sha_locked_stashstash@{N} indices drift; SHAs don't
  • set_diff_classification — line-set comparison, not unified-diff +/- scan
  • startup_smoke_check — refuse to run with a clearly-truncated prompt

Full list and rationale: docs/architecture.md.

Monitor: 11 detectors

Notify only: timeout_rate, hung, orphan_chain, disk_warning, mem_pressure, smoke_fail_rate, network_fail, rate_limit_active, anomaly_repetitive_active.

Auto-stop the service (continuing is harmful):

  • oauth_fail — burning API quota on auth-rejected rounds
  • disk_critical — writing to a near-full disk risks corruption

Runs locally or against a remote host via ssh:

agent-runner monitor                  # local, 30s poll
agent-runner monitor --host pi        # remote, 60s poll
agent-runner monitor --json | jq -c   # pipe to downstream consumers

SSH trust boundary: monitor --host <alias> shells out via plain SSH using your local ~/.ssh/config (aliases, StrictHostKeyChecking behavior). A monitor with auto_stop enabled can issue agent-runner stop on the remote — verify your SSH config before pointing monitor at a remote service. See docs/runbook.md § "Remote monitor & SSH trust" for recommended hygiene.

Documentation

Development

git clone https://github.com/wan9yu/cli-agent-runner.git
cd cli-agent-runner
python3 -m venv .venv && source .venv/bin/activate
pip install -e ".[dev]"

./build.sh check                          # full local-CI sweep
./build.sh test                           # unit + integration only
AGENT_RUNNER_E2E_PI=1 ./build.sh e2e      # opt-in pi e2e (needs ssh alias `pi`)

Some docs/*.md blocks are generated from code — ./build.sh docs rewrites the <!-- gen:* --> regions, and ./build.sh check verifies they are fresh.

POSIX-only (Linux, macOS). Tested under Python 3.11+ on x86_64 and aarch64.

License

Apache License 2.0.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cli_agent_runner-0.1.34.tar.gz (277.6 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

cli_agent_runner-0.1.34-py3-none-any.whl (108.2 kB view details)

Uploaded Python 3

File details

Details for the file cli_agent_runner-0.1.34.tar.gz.

File metadata

  • Download URL: cli_agent_runner-0.1.34.tar.gz
  • Upload date:
  • Size: 277.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for cli_agent_runner-0.1.34.tar.gz
Algorithm Hash digest
SHA256 97e08439b3c699c278f3efcc338bf36688ded728607fb8621b9cbfba0f0d1355
MD5 037ea9bb4f90035e558be8bf8c4fae18
BLAKE2b-256 277d340d43c7ea57910fe7192f2a2afaa8b0a4d17d0b0053265adf4c4e46cafa

See more details on using hashes here.

Provenance

The following attestation bundles were made for cli_agent_runner-0.1.34.tar.gz:

Publisher: release.yml on wan9yu/cli-agent-runner

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file cli_agent_runner-0.1.34-py3-none-any.whl.

File metadata

File hashes

Hashes for cli_agent_runner-0.1.34-py3-none-any.whl
Algorithm Hash digest
SHA256 41452a7fcc60b8ebd897800c3d9458a42426466ac483b1cbd663c66bd49fac4c
MD5 c6857c922cc845765c9ba836deb2b42b
BLAKE2b-256 a9a333d48450bcb6f75794e8079f1e278277fbcbc1bab96783cbc0e298580b46

See more details on using hashes here.

Provenance

The following attestation bundles were made for cli_agent_runner-0.1.34-py3-none-any.whl:

Publisher: release.yml on wan9yu/cli-agent-runner

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page