shoko/kugetsu
1
0
Fork 0
Code Issues 17 Pull Requests Actions Packages Projects Releases 3 Wiki Activity

Merge pull request 'docs: add hermes-setup.md from issue #1 research' (#8) from docs/hermes-setup into main

Browse Source
This commit was merged in pull request #8.
This commit is contained in:
shoko
2026-03-27 16:06:19 +01:00
parent 5828485534 a3ac3490d2
commit 56da2a2fe8
2 changed files with 285 additions and 143 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/_index.md
View File

@@ -15,6 +15,7 @@ Overview of research topics and notes.
| Topic | Status | Last Updated | | Topic | Status | Last Updated |
|-------|--------|--------------| |-------|--------|--------------|
| [OpenCode Usage & Parallelization](./opencode-usage.md) | Active | 2025-03-27 | | [OpenCode Usage & Parallelization](./opencode-usage.md) | Active | 2025-03-27 |
| [Hermes Setup](./hermes-setup.md) | In Progress | 2026-03-27 |
### More topics... ### More topics...

427
docs/hermes-setup.md
View File

@@ -1,201 +1,342 @@
# Hermes Setup Guide # Hermes Setup Guide for Kugetsu
## Overview **Date:** 2026-03-27
**Status:** In Progress
**Related Issue:** #1
Hermes is the primary orchestrator and gateway in the Kugetsu system. It handles: ## Summary
- Spawning and managing subagents Guide for setting up Hermes as the orchestration layer for Kugetsu's multi-agent parallel workflow. Hermes manages OpenCode coding agents that work in isolated git worktrees, communicating via Gitea issues and PRs.
- Message passing between agents
- Repository access via Git API
- Task delegation and parallelization
**Key Constraint:** The delegate_task function has a hard limit of 3 concurrent tasks. ## 1. Installation
--- ### Recommended: curl (One-Liner)
## Installation via Curl Script ```bash
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash -s -- --skip-setup
```
The `--skip-setup` flag skips the interactive setup wizard, ideal for CI environments.
**What it installs:**
- `uv` (fast Python package manager)
- Python 3.11 via uv
- Node.js v22 LTS (for browser tools & WhatsApp bridge)
- ripgrep (fast file search)
- ffmpeg (TTS/audio)
- Clones repo to `~/.hermes/hermes-agent/`
- Creates venv, installs deps, sets up `hermes` symlink in `~/.local/bin/`
- Creates config templates in `~/.hermes/`
### Verification
```bash
hermes version # Check command exists
hermes doctor # Full diagnostics
source ~/.bashrc # Reload shell if hermes not found
```
### Alternative Methods
| Method | Command | Best For |
|--------|---------|----------|
| **curl** | `curl -fsSL ... \| bash` | **Recommended** — fresh machines, CI |
| **Manual/Source** | `git clone` + `uv venv` + `uv pip install -e ".[all]"` | Full control, developers |
| **Nix** | `nix develop` or NixOS module | Nix/NixOS users, declarative configs |
| **Docker** | Not for installation | Docker is a *terminal backend* for sandboxing |
### Prerequisites ### Prerequisites
- Linux/macOS environment Only `git` and `curl` are required. All other dependencies are installed by the script.
- curl, git, and basic build tools installed
- LLM provider API key (for cloud providers)
### Installation Steps ## 2. Configuration (API Key Auth)
```bash
# Clone the Hermes repository
git clone https://git.example.com/shoko/hermes.git ~/repositories/hermes
# Run the installation script
cd ~/repositories/hermes && ./install.sh
# Verify installation
hermes --version
# Initialize with non-interactive mode (if config exists)
hermes init --non-interactive
```
Alternative: Direct Download
```bash
curl -L https://git.example.com/shoko/hermes/releases/latest/download/hermes -o ~/.local/bin/hermes
chmod +x ~/.local/bin/hermes
export PATH="$HOME/.local/bin:$PATH"
hermes --version
```
---
## Programmatic Configuration
If you already have an API token, configure Hermes entirely via files and commands.
### Directory Structure ### Directory Structure
```bash ```
mkdir -p ~/.hermes/skills ~/.hermes/cache ~/.hermes/
├── config.yaml # Non-secret settings (model, provider, terminal, etc.)
├── .env # API keys and secrets
├── auth.json # OAuth tokens (Nous Portal, Codex, etc.)
├── SOUL.md # Agent identity
├── memories/ # Persistent memory
├── skills/ # Agent skills
├── sessions/ # Gateway sessions
└── logs/ # Error and gateway logs
``` ```
### Configure via .env File ### CLI Configuration
Create `~/.hermes/.env`: Set API keys directly via the CLI (auto-routes to `~/.hermes/.env`):
```bash ```bash
ANTHROPIC_API_KEY=sk-ant-... hermes config set OPENROUTER_API_KEY sk-or-...
OPENROUTER_API_KEY=sk-or-... hermes config set ANTHROPIC_API_KEY sk-ant-...
GITEA_TOKEN=your_token hermes config set OPENAI_API_KEY sk-...
HERMES_DEFAULT_MODEL=openrouter/anthropic/claude-sonnet-4
hermes config set model.provider openrouter
hermes config set model.default anthropic/claude-opus-4.6
hermes config # View current config
hermes config edit # Edit config.yaml
hermes config check # Validate configuration
```
### Supported Providers (API Key Auth)
| Provider | Env Var | Config Provider | Notes |
|----------|---------|-----------------|-------|
| **OpenRouter** | `OPENROUTER_API_KEY` | `openrouter` | Recommended default |
| **OpenAI** | `OPENAI_API_KEY` | `openai` | |
| **Anthropic** | `ANTHROPIC_API_KEY` | `anthropic` | |
| **OpenAI-Compatible** | `OPENAI_API_KEY` + `OPENAI_BASE_URL` | `custom` | vLLM, SGLang, llama.cpp, LocalAI, Jan, Ollama |
| **Ollama** | `OPENAI_API_KEY=ollama` + `OPENAI_BASE_URL` | `custom` | Local models (no API key) |
| **DeepSeek** | `DEEPSEEK_API_KEY` | `custom` + base_url | |
| **Together AI** | `OPENAI_API_KEY` | `custom` + base_url | |
| **Groq** | `OPENAI_API_KEY` | `custom` + base_url | |
| **Fireworks AI** | `OPENAI_API_KEY` | `custom` + base_url | |
### Example Configs
**OpenRouter (Recommended):**
```bash
# ~/.hermes/.env
OPENROUTER_API_KEY=sk-or-v1-...
LLM_MODEL=anthropic/claude-opus-4.6
``` ```
### Configure via config.yaml
```yaml ```yaml
hermes: # ~/.hermes/config.yaml
name: kugetsu-orchestrator model:
log_level: info provider: "openrouter"
max_parallel_tasks: 3 default: "anthropic/claude-opus-4.6"
task_timeout: 3600
gitea:
instance: https://git.example.com
owner: shoko
repo: kugetsu
token_env: GITEA_TOKEN
agents:
default_model: openrouter/anthropic/claude-sonnet-4
temperature: 0.7
thinking_enabled: true
``` ```
### Automate Configuration with hermes config set
Set configuration programmatically: **Ollama (Local):**
```bash
# ~/.hermes/.env
OPENAI_BASE_URL=http://localhost:11434/v1
OPENAI_API_KEY=ollama
LLM_MODEL=llama3.1:70b
```
```yaml
# ~/.hermes/config.yaml
model:
provider: "custom"
default: "llama3.1:70b"
base_url: "http://localhost:11434/v1"
```
**Anthropic Direct:**
```bash
# ~/.hermes/.env
ANTHROPIC_API_KEY=sk-ant-...
```
```yaml
# ~/.hermes/config.yaml
model:
provider: "anthropic"
default: "claude-sonnet-4-6"
```
### Quick-Start Template
```bash ```bash
hermes config set agents.default_model "openrouter/anthropic/claude-sonnet-4" # ~/.hermes/.env (create this)
hermes config set agents.temperature 0.7 OPENROUTER_API_KEY=your-key-here
hermes config set gitea.instance "https://git.example.com" LLM_MODEL=anthropic/claude-opus-4.6
hermes config set gitea.owner "shoko"
hermes config set gitea.repo "kugetsu" # ~/.hermes/config.yaml (minimal)
hermes config set opencode.managed_by "hermes" model:
hermes config set opencode.default_mode "agent" provider: "openrouter"
hermes config list default: "anthropic/claude-opus-4.6"
``` ```
## LLM Providers with API Key Only
These providers work with just an environment variable or API key: ## 3. OpenCode Integration
### OpenRouter (Recommended) ### How Hermes Delegates to OpenCode
Hermes does **NOT** have a native agent-to-agent protocol. Delegation happens via terminal/process spawning:
```
Hermes (orchestrator)
└── terminal(command="opencode run 'task'", workdir="...")
└── OpenCode subprocess (child process)
└── Executes autonomously
```
### delegate_task vs terminal(opencode run)
| Pattern | Command | Concurrency Limit | Context |
|---------|---------|-------------------|---------|
| `delegate_task()` | Native LLM subagent | **Max 3** (hard schema limit) | Fresh isolated context |
| `terminal(opencode run)` | CLI subprocess wrapper | **No hard cap** | Streams output via process() |
For Kugetsu's parallel workflow, prefer `terminal(opencode run ...)` for coding agents since we need more than 3 concurrent agents.
### Example Delegation Commands
```bash ```bash
export OPENROUTER_API_KEY="sk-or-..." # One-shot task (blocks until complete)
hermes config set agents.default_model "openrouter/anthropic/claude-sonnet-4" terminal(command="opencode run 'Fix issue #1: add retry logic'", workdir="/tmp/issue-1")
```
Supports: Anthropic, OpenAI, Mistral, Llama, Gemini, and more.
### Anthropic (Direct) # Background TUI (interactive, returns session_id)
terminal(command="opencode", workdir="~/project", background=true, pty=true)
# Monitor background session
process(action="poll", session_id="<id>")
process(action="log", session_id="<id>")
process(action="submit", session_id="<id>", data="Continue work...")
# Kill session
process(action="kill", session_id="<id>")
```
### Kugetsu's Gitea-Based Communication Hub
```
┌─────────────────────────────────────────────────────────────┐
│ Hermes (Orchestrator/PM) │
│ - terminal(opencode run ...) for OpenCode agents │
│ - delegate_task() for LLM subagents (max 3) │
└─────────────────────────────────────────────────────────────┘
│ (CLI subprocess)
▼
┌──────────────────────┐
│ OpenCode Subagent │
│ - Works in isolated │
│ git worktree │
│ - Posts findings to │
│ Gitea via curl │
└──────────────────────┘
│ (Gitea API)
▼
┌─────────────────────────────────────────────────────────────┐
│ Gitea (Communication Hub) │
│ - Issues as task tickets │
│ - Comments as progress updates │
│ - PRs as code deliverables │
└─────────────────────────────────────────────────────────────┘
```
## 4. Git Worktree Isolation (Per-Issue)
### Why Worktrees?
Running multiple agents on the same repo can cause:
- **File conflicts** when agents edit the same files
- **Branch state confusion** when agents checkout different branches
- **Lost work** if one agent's changes get overwritten
Each issue gets its own worktree so any agent can jump into the right context.
### Manual Setup
```bash ```bash
export ANTHROPIC_API_KEY="sk-ant-..." # Create worktree for an issue
hermes config set agents.default_model "anthropic/claude-sonnet-4" git worktree add -b fix/issue-{N}-title ../kugetsu-issue-{N} main
# List worktrees
git worktree list
# Remove worktree (after PR merged)
git worktree remove ../kugetsu-issue-{N}
git branch -D fix/issue-{N}-title
``` ```
### OpenAI Compatible ### opencode-worktree Skill
Kugetsu provides an automated skill at `skills/opencode-worktree/`:
```bash ```bash
export OPENAI_API_KEY="sk-..." # Source the script
hermes config set agents.default_model "openai/gpt-4o" . skills/opencode-worktree/opencode-worktree.sh
# Create session with purpose tag
. opencode-worktree.sh refactor-auth
# Creates: session-{timestamp}-{random6}-refactor-auth
# Cleanup all session-* worktrees
. opencode-worktree.sh --cleanup
# Cleanup specific worktree
. opencode-worktree.sh --cleanup session-20260327-134524-9c1e3f-refactor-auth
``` ```
### Groq (Fast, Free Tier) ### Hermes Built-in Worktree Isolation
Hermes has native support via config:
```yaml
# ~/.hermes/config.yaml
worktree: true # Always create a worktree per session
```
Each CLI session creates a fresh worktree under `.worktrees/` with its own branch. Clean worktrees are removed on exit; dirty ones are kept for manual recovery.
### Branch Hygiene
**Always use explicit base when creating branches:**
```bash ```bash
export GROQ_API_KEY="gsk_..." # WRONG - depends on current HEAD
hermes config set agents.default_model "groq/llama-3.1-70b" git checkout -b fix/issue-{N}-title
# CORRECT - always from main explicitly
git checkout -b fix/issue-{N}-title main
``` ```
## OpenCode Integration
OpenCode can be managed by Hermes as an orchestrator-controlled coding agent. **Detect contamination:**
### Setup
```bash ```bash
# Install OpenCode # Check for commits beyond main
curl -L https://opencode.ai/install.sh | sh git log main..HEAD --oneline
# If non-empty, branch is contaminated
# Configure Hermes to manage OpenCode
hermes config set opencode.managed_by "hermes"
hermes config set opencode.binary_path "~/.opencode/bin/opencode"
hermes config set opencode.default_mode "agent"
``` ```
### Usage **Fix contamination:**
OpenCode runs as a subagent under Hermes:
```
Task: Write a Python script
Agent: opencode
Model: openrouter/anthropic/claude-sonnet-4
```
### Benefits
- Orchestrated: Hermes manages task routing to OpenCode
- Consistent Context: Shared cache and session management
- Unified Logging: All agent activity flows through Hermes
## Verification
```bash ```bash
# Check version git rebase --onto main wrong-base my-branch
hermes --version git push --force-with-lease origin my-branch
# List configuration
hermes config list
# Test Gitea connection
hermes doctor
# Run a test task
hermes task status
``` ```
## Troubleshooting ## 5. Workflow Summary
### Config not loading ```
1. Setup Hermes
curl -fsSL .../install.sh | bash -s -- --skip-setup
hermes config set OPENROUTER_API_KEY ...
hermes config set model.provider openrouter
```bash 2. For Each Issue: Create Isolated Worktree
hermes --config ~/.hermes/config.yaml config list git worktree add -b docs/issue-{N}-title ../kugetsu-issue-{N} main
3. Agent Works in Worktree
cd ../kugetsu-issue-{N}
opencode run "Research/fix issue #{N}"
4. Agent Posts to Gitea
curl -X POST .../issues/{N}/comments -d @/tmp/findings-{N}.md
5. User Reviews on Gitea
Comments on issues/PRs
6. Cleanup After Merge
git worktree remove ../kugetsu-issue-{N}
git branch -D docs/issue-{N}-title
``` ```
### API key not found ## References
```bash - [Hermes Agent GitHub](https://github.com/nousresearch/hermes-agent)
export $(cat ~/.hermes/.env | xargs) - [Hermes Agent Docs](https://hermes-agent.nousresearch.com)
hermes config list - [Kugetsu Architecture](./kugetsu-architecture.md)
``` - [OpenCode Usage](./opencode-usage.md)
- [Subagent Workflow](./SUBAGENT_WORKFLOW.md)
### Gitea connection failed ## Status History
```bash - 2026-03-27: Initial draft from issue #1 research
curl -H "Authorization: token $GITEA_TOKEN" https://git.example.com/api/v1/user
```