shoko
ecfd0b1160
- Hermes Detective Agency: Open-ended mystery investigation game - Roles: Chief (human), Witness (Kimi), Detective (Hermes) - 5 difficulty levels, community cases, open-ended solving - Scoring: Alignment %, Evidence %, Time - Features: Retry, Journal, Observe mode - Tech: Kimi Vision + Hermes Agent + Pollinations Changelog: - Research phase: Kimi capabilities, Hermes agent, image APIs - Brainstorming: 14 ideas explored - Comparison matrix: Detective selected as winner - Concept finalized with all design decisions
1.4 KiB
1.4 KiB
Research: Hermes Agent Capabilities
Date: 2026-04-19
Purpose: Understand Hermes Agent framework for hackathon integration
Hermes 3 (Nous Research)
Core Capabilities
- Advanced agentic capabilities
- Reliable function calling - Trained specifically for tool use
- Structured output - JSON mode / Pydantic schemas
- ChatML prompt format - OpenAI-compatible
- Multi-turn conversation
- Long context coherence
Benchmark Performance
| Benchmark | Hermes 3 Score |
|---|---|
| IFEval (0-shot) | 61.70% |
| MMLU-Redux | 92.7% |
| MMLU-Pro | 81.1% |
| SimpleQA | 31.0% |
Function Calling
- Trained on specific prompts for tool use
- XML-based tool call format:
<tool_call>{"name": "...", "arguments": {...}}</tool_call> - Supports recursive/chain tool calls
- Native tool integration via NousResearch/Hermes-Function-Calling repo
Hermes Agent Framework
Key Components
- ChatML format - Structured system/user/assistant turns
- Tool definitions - JSON schema for function signatures
- Tool parsing - Parse and execute function calls
- Response loop - Multi-turn agentic execution
Integration Points
- HuggingFace Transformers
- vLLM inference
- Ollama local deployment
- OpenAI-compatible API