# Hermes Regress: Hermes Agent plugin

> Regression tests built from your own sessions.

Canonical: https://hermeswatcher.com/plugins/hermes-regress  
Tier: Community  
Official page (Nous Research): https://hermes-agent.nousresearch.com/docs/plugins/hermes-regress  
Last updated in catalog: 2026-11-17

Regression tests built from your own sessions. Capture is passive: every finished turn is written as a plain JSON case holding the prompt, the model, each tool call with its exact arguments and the output it returned. Replay a case through the real agent loop with every tool call vetoed at pre_tool_call and answered from the recording, so a model, provider or config change can be measured without side effects — /regress run --model X reports pass, drift, regressed and error per case, with markdown, JUnit XML and a hash-chained export bundle for CI. Fixtures match only on identical tool and arguments; a case whose tool plan cannot be reproduced is reported as a gap instead of being answered from the wrong recording, and a replay window that never reaches the hook is marked error and stops the run rather than executing live tools.

## Good to know before installing

Writes captured cases under HERMES_HOME/plugin-data/hermes-regress/ (mode 0600) with the prompt, answer, tool arguments and tool results all passed through redaction first (provider keys, GitHub/Slack/AWS tokens, JWTs and inline password/token values become [REDACTED], counts recorded per case); keeps replay state in the same directory (armed.json plus an audit line per armed tool call in hook.log), scopes the replay veto to the single session that claims the armed case (only a first turn whose message exactly matches the recorded prompt can claim it, recorded from pre_llm_call), keeps that scope through a mid-turn context compression by matching the claimed task id as well as the session id, and serialises claims with a file lock, so an unclaimed window serves and blocks nobody, a late claim cannot revive a disarmed window, and other chats and cron runs are never affected, and runs the local hermes CLI as a subprocess when you ask for a replay; no network calls of its own, no telemetry.

From the plugin's catalog listing.

## How to install

1. Install it. Hermes asks for any API keys it needs, then asks whether to turn it on.

```bash
hermes plugins install hermes-regress
```

2. Said no? Turn it on later:

```bash
hermes plugins enable hermes-regress
```

3. Restart Hermes so it loads the plugin.

Some plugins also need a sign-in or settings: see the official page. Memory plugins ask whether to become your memory provider instead. Steps follow the official plugins guide: https://hermes-agent.nousresearch.com/docs/user-guide/features/plugins

## Facts

- Category: AI models & providers, Automation & multi-agent
- Maintained by: harishkotra (Community)
- Needs: No API keys declared
- Requires Hermes: `>=0.22.0`
- Version: 0.1.0
- In the catalog since: 2026-11-17

## Links

- [Full setup and settings (official page)](https://hermes-agent.nousresearch.com/docs/plugins/hermes-regress)
- [Source code](https://github.com/harishkotra/hermes-regress#readme)
- [All plugins](https://hermeswatcher.com/plugins.md)

---

HermesWatcher is an independent guide. It is not affiliated with or endorsed by Nous Research. The [official Hermes Agent documentation](https://hermes-agent.nousresearch.com/docs) and [repository](https://github.com/NousResearch/hermes-agent) from Nous Research are the authority; each page here lists the official sources it was written from. If this site and the official docs disagree, trust the official docs. Index for agents: https://hermeswatcher.com/llms.txt
