Getting Started

Prerequisites

• Linux (sandbox via bubblewrap; bwrap auto-installs through apt/dnf/yum/pacman/apk if missing) or macOS (sandbox-exec)
• At least one LLM provider account — an OAuth subscription (Codex, Copilot, Grok) or an API key (OpenAI, Claude, Gemini, DeepSeek, NVIDIA, OpenRouter, Cloudflare)
• Go 1.25.1 or higher, only if building from source
• Optional: pdftotext (poppler-utils) so read_files can parse PDFs
• Optional: OPENAI_API_KEY to enable semantic search (text-embedding-3-small)

Install

curl -fsSL https://agenvoy.com/scripts/install.sh | bash
agen

Or build from source:

git clone https://github.com/pardnchiu/Agenvoy.git
cd agenvoy
make build

make build compiles, embeds the latest git tag as projectVersion, installs the binary to /usr/local/bin/agen, and refreshes the bundled skills and tools.

Configure at least one provider

Launch the TUI and run /model — it walks through provider selection, live model discovery from that provider's API, and credential storage. Tokens land in the OS keychain (security on macOS, secret-tool on Linux, encrypted file fallback otherwise) under the fixed service name agenvoy.

The main config lives at ~/.config/agenvoy/config.json; it holds registered models and runtime limits, never credentials.

First run

agen

The daemon starts automatically if it isn't already running. Inside the TUI, /new creates a named session and /switch moves between sessions.

The input box is always focused — type your message and press Enter to send (Alt+Enter inserts a newline; Enter during a run queues a steer message instead). Type / to open the command palette (matches command name or description); Tab/Enter confirms the highlighted entry, Esc dismisses it. With the input empty: Shift+Tab toggles auto-approve, Shift+F toggles fast mode, Shift+W/Shift+S cycles the dispatcher model, and Shift+A/Shift+D cycles the reasoning level.

For one-shot CLI usage:

make cli "summarize the latest changes in main.go"
make run "use playwright to open example.com and screenshot"

make cli confirms each non-read-only tool call; make run auto-approves everything.

Next steps

• Sessions & Agents — sessions, agent routing, and subagents
• Execution Engine — the iteration loop and three-pass tool dispatch
• Providers — supported LLM backends and the dispatcher model
• MCP Client — plug in external tool servers
• CLI Commands — full command list

[!NOTE] This document was auto-generated by Claude after reading the full source code.