Skip to content

index.md

Latest commit

 

History

History
75 lines (55 loc) · 3.81 KB

index.md

File metadata and controls

75 lines (55 loc) · 3.81 KB
Raw

Prime Agent Documentation

Prime Agent is an RLM-native coding and research harness built around a persistent IPython kernel, recursive subagents, durable sessions, and a multi-process local runtime. It began as a hard fork of pi-mono, but Prime Agent is now the product, CLI, install source, and development repository.

Quick Start

Install the latest stable release on Linux or macOS:

curl -fsSL https://app.primeintellect.ai/prime-agent/install.sh | sh

Then run it in a project directory:

cd /path/to/project
prime-agent

Authenticate with /login for subscription or stored API-key providers, or set an environment variable such as ANTHROPIC_API_KEY before launch. See the Quickstart for the complete first-run flow.

Public releases are currently installed from versioned release artifacts. The inherited npm workspace names in the source tree are implementation details, not the public install path.

Start Here

  • Quickstart - install, authenticate, and run a first session.
  • Using Prime Agent - interactive mode, RLM subagents, slash commands, context files, and CLI reference.
  • Architecture overview - client, daemon, worker, session, kernel, provider, and storage boundaries.
  • RLM programming model - programmatic execution, native subagents, Python skills, and durable state.
  • Long-running and background agents - daemon workers, messaging, heartbeats, goals, schedules, and autonomous mode.
  • Providers - subscription and API-key setup for built-in providers.
  • Settings - global and project settings.
  • Keybindings - default shortcuts and custom keybindings.
  • Sessions - session management, branching, and tree navigation.
  • Compaction - context compaction and branch summarization.

Customization

  • Extensions - TypeScript modules for tools, commands, events, and custom UI.
  • Skills - markdown and Python-backed skills, including how to ask Prime Agent to create them.
  • MCP integrations - use MCP servers through Python skills without expanding the model's tool surface.
  • Prompt templates - reusable prompts that expand from slash commands.
  • Themes - built-in and custom terminal themes.
  • Prime Agent packages - bundle and share extensions, skills, prompts, and themes.
  • Custom models - add model entries for supported provider APIs.
  • Custom providers - implement custom APIs and OAuth flows.

Programmatic Usage

  • SDK - embed Prime Agent in Node.js applications.
  • ACP mode - drive Prime Agent from any Agent Client Protocol client.
  • RPC mode - integrate over stdin/stdout JSONL.
  • JSON event stream mode - print mode with structured events.
  • TUI components - build custom terminal UI for extensions.

Reference

Platform Setup

Development