Harvey User Manual

Harvey is a terminal-based coding agent backed by a local Ollama server (or any provider supported by mozilla-ai/any-llm-go). It provides an interactive REPL where you chat with a large language model while also reading files, running commands, searching code, and applying suggested changes, all sandboxed to a single workspace directory.

🚀 Quick Start Guide

For users who want to get Harvey running immediately

1. Installation

INSTALL.md — Step-by-step instructions to install Harvey on Linux, macOS, or Windows

2. First Session

getting_started.md — Launch Harvey, connect to Ollama, and run your first commands

3. System Prompt Customization

HARVEY.md — The default system prompt and how to customize it for your project

📚 Core User Guide

For daily Harvey usage

Working with Harvey

• Overview — What Harvey is, its philosophy, and core features
• Configuration — Workspace configuration in agents/harvey.yaml, including permissions, timeouts, and memory settings

Commands and Workflows

• Command Reference — Primary man page with all available commands and flags
• Getting Started — Detailed session walkthrough, keyboard shortcuts, and slash commands

Security Features

• Security Guide — Safe mode, command allowlists, workspace permissions, audit logging, and threat model
• Security Review — Pre-release security assessment and known limitations

🎯 Advanced Features

Retrieval-Augmented Generation

• RAG Setup & Usage — Complete guide to retrieval-augmented generation, including named stores, ingest commands, and configuration
• RAG Commands — Detailed reference for all RAG-related slash commands

Knowledge Management

• Knowledge Base — SQLite-backed knowledge base schema, FTS5 search, CLI commands, and Go API
• Memory System — Unified memory architecture with rolling summaries and token budget tracking

Model Management

• Model Guide — Model selection guide based on /ollama probe results
• Model Cache — Model capability caching architecture, database schema, and probing mechanisms
• Routing — Connect to remote model endpoints (Anthropic, DeepSeek, Gemini, Mistral, OpenAI) via @mention syntax
• Llamafile Notes — Mozilla AI’s single-file runnable models (note: not currently integrated with Harvey)

Sessions & Recording

• Sessions — Session recording, file structure, replay functionality, and programmatic access
• Fountain Format — Fountain screenplay format specification for conversation recordings

🔧 Extending Harvey

Skills System

• Skills Overview — Extend Harvey with custom skills, including SKILL.md format, discovery paths, compiled skills, triggers, and the skill wizard
• Skill Sets — Manage named bundles of skills for specific workflows

📖 What’s New

• See CHANGES.md for version history and new features in each release

🔍 Can’t Find What You Need?

• Use /help inside Harvey for a live command list
• Use /help <command> for specific command help
• See Developer Guide for development and contribution information
• See Reference for complete command and configuration reference