Local coding agent with Hermes and Ollama

• Understand the role of Hermes, Ollama, and the local model.
• Configure a safe workflow for editing code on a branch.
• Avoid loops, broken tool calling, and changes without tests.

Minimal architecture

For a local coding agent, think in three layers: Hermes orchestrates the task, Ollama serves the model, and Git/tests verify whether the change deserves to stay. If one of those layers is missing, the system becomes fragile.

• Hermes: memory, skills, tools, and work loop.
• Ollama: compatible local endpoint for inference.
• Repository: isolated branch, tests, lint, and reviewable diff.

# Comprueba que Ollama responde
ollama --version
ollama list
curl http://localhost:11434/api/tags

# Elige un modelo pequeño para empezar
ollama pull qwen2.5-coder:7b
ollama run qwen2.5-coder:7b "Resume qué hace este archivo package.json"

# Trabaja siempre en rama
git checkout -b agent/hermes-prueba-segura

Recommended initial assignment

A local agent should not start by editing. It should observe, scope, and propose a plan first. This pattern reduces impulsive changes and lets you detect when context is insufficient.

Objetivo:
Corrige el bug descrito en BUG.md sin tocar otras áreas.

Reglas:
- Primero lista archivos relevantes y riesgos.
- No edites hasta proponer un plan de 5 pasos.
- Máximo 8 pasos de agente.
- Si una tool falla dos veces, para y resume.
- Después de editar, ejecuta lint/test/build disponibles.
- No hagas commit sin mostrar diff y resultado de pruebas.

Stop logic so it doesn't wander off

limits:
  max_steps: 8
  max_tool_calls_total: 20
  max_repeated_tool_args: 2
  max_runtime_minutes: 15
  stop_when:
    - tests_pass
    - same_error_twice
    - missing_context
    - needs_secret_or_external_login

Official sources

• Ollama: Hermes Agent integration
• Hermes Agent documentation
• Hermes Agent: AI providers
• Google Gemma 4 model card
• Ollama API