Skip to main content

AgentMetrics observability plugin for Hermes agents

Project description

agentmetrics-hermes

PyPI License: MIT

AgentMetrics observability plugin for Hermes agents. Auto-discovered via the hermes_agent.plugins entry-point — no code changes needed.


Install

pip install agentmetrics-hermes

Configuration

Create ~/.config/hermes/agentmetrics.yaml:

api_key: am_your_key
server_url: http://localhost:4000
agent_id: my-hermes-agent
environment: production

Or set environment variables (take precedence over the file):

Variable Description
AGENTMETRICS_API_KEY API key
AGENTMETRICS_SERVER_URL Server URL
AGENTMETRICS_AGENT_ID Agent identifier
AGENTMETRICS_ENVIRONMENT Deployment environment

What gets tracked

Metric Description
input_tokens / output_tokens Aggregated LLM token usage
cache_read_tokens / cache_write_tokens Prompt cache statistics
estimated_cost_usd Computed from model pricing
duration_ms Session wall-clock time
tool_calls / tool_errors Per-step tool tracking
llm_calls Number of model API requests
secrets_blocked_count Credentials redacted before transmission
error Exception message on failure (secrets scrubbed)

Durability

Events are written to a local WAL before transmission. If the server is unreachable the plugin retries automatically via an internal circuit breaker. Events that exhaust all retries go to a dead-letter queue and are surfaced as audit_dlq_alert events.


Security

All event payloads are scanned for API keys, JWTs, and passwords before transmission. Set redaction_mode: debug in the config to disable scrubbing during local development (expires automatically after a configurable TTL).


License

MIT

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

agentmetrics_hermes-0.2.2.tar.gz (30.8 kB view details)

Uploaded Source

Built Distribution

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

agentmetrics_hermes-0.2.2-py3-none-any.whl (26.9 kB view details)

Uploaded Python 3

File details

Details for the file agentmetrics_hermes-0.2.2.tar.gz.

File metadata

  • Download URL: agentmetrics_hermes-0.2.2.tar.gz
  • Upload date:
  • Size: 30.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for agentmetrics_hermes-0.2.2.tar.gz
Algorithm Hash digest
SHA256 f7c1f284ebea03bb3f8d20ed9a1fcad08f008f729801dbab2c92696e95033821
MD5 845ff5c271144d5411f71094347111a8
BLAKE2b-256 a08a66bdcad4c1c2b78bceb43bb8641bad566864e4995686bda7dd01124a62bb

See more details on using hashes here.

File details

Details for the file agentmetrics_hermes-0.2.2-py3-none-any.whl.

File metadata

File hashes

Hashes for agentmetrics_hermes-0.2.2-py3-none-any.whl
Algorithm Hash digest
SHA256 4374018ff7d048e5568fdb994ce0949dbbbe3d387b63498a4630a6796521cc22
MD5 c536dd3b793dd225dd502dfc74258431
BLAKE2b-256 5d0ff29bd2b50f059caec3595e91a7769ba2debab3f3c8999091b1b839245d4c

See more details on using hashes here.

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