# Model Kombat: Hermes Agent plugin

> Head-to-head model evaluation: scout a task or kanban card into lanes, build a deterministic fight card (Warm-up 1pt, Main Event 2pt, Championship 3pt, sudden death) at standard, hard or gauntlet intensity,…

Canonical: https://hermeswatcher.com/plugins/model-kombat  
Tier: Community  
Official page (Nous Research): https://hermes-agent.nousresearch.com/docs/plugins/model-kombat  
Last updated in catalog: 2026-11-14

Head-to-head model evaluation: scout a task or kanban card into lanes, build a deterministic fight card (Warm-up 1pt, Main Event 2pt, Championship 3pt, sudden death) at standard, hard or gauntlet intensity, fight two models on identical prompts, and score mechanically — executed code, exact counts, numeric tolerances, phrase groups, JSON leaf equality, SQLite rows — with a per-lane Elo ladder, live arcade pane, kanban badges, and a measured best-value call when strong models tie ('equal quality — X is 18x cheaper'); a local task_stats.json remembers which tasks split the two models and demotes saturated ones.

## Good to know before installing

Model calls: all fights go through Hermes' own LLM facade with a per-call model override you must enable (`plugins.entries.model-kombat.llm.allow_model_override`); pure fights make two model calls per task, capped by `max_fight_cost_usd` / `max_fight_tokens` and `max_fight_seconds`, which tool arguments can lower but never raise; agentic fights create kanban tasks assigned to your active profile with a per-task model override, which start worker agent sessions with that profile's tools and are not spend-capped; code execution: off by default and switchable only in plugin settings, and when enabled, model-written Python runs as your user in a resource-limited subprocess that is not a security sandbox; local files: reads optional project tasks from `.kombat/tasks.json` in the working directory and writes reports, history, ladder, exports and stats only under its plugin data dir; kanban: posts display cards on a dedicated `model-kombat` board and auto-closes its own stale cards there; no third-party network calls, no telemetry, no credential reads.

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 model-kombat
```

2. Said no? Turn it on later:

```bash
hermes plugins enable model-kombat
```

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
- Maintained by: DarkeTech (Community)
- Needs: No API keys declared
- Adds tools: `kombat_list_tasks`, `kombat_run_fight`, `kombat_scout`, `kombat_run_agentic_fight`, `kombat_score_answers`, `kombat_rematch_errors`, `kombat_recommend`, `kombat_history`, `kombat_export`
- Requires Hermes: `>=0.23.0`
- Version: 0.7.2
- In the catalog since: 2026-11-14

## Links

- [Full setup and settings (official page)](https://hermes-agent.nousresearch.com/docs/plugins/model-kombat)
- [Source code](https://github.com/DarkeTech/model-kombat#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
