Skip to content

index.md

Latest commit

 

History

History
71 lines (52 loc) · 4.08 KB

index.md

File metadata and controls

71 lines (52 loc) · 4.08 KB
Raw

Synerise base-context documentation

Base Context is a coding and research agent built around a persistent Python workspace, recursive agents, and source-backed context management. It is an MIT-licensed fork of Prime Agent by Synerise.

Quick start

On macOS or Linux:

curl -fsSL https://github.com/BaseModelAI/base-context/releases/latest/download/install.sh | bash

The installer prepares missing prerequisites and managed Python before activating the CLI. Run its final PATH command, then start base-context in your project. Use /login for your provider, /model for your model, and /effort for its reasoning level.

See quickstart for a first session and installation for npm, Windows, source builds, updates, rollback, and uninstall. Coming from Codex? Start with goals, worker limits, and side questions.

Read why we forked Prime Agent and how context management works for the design and its limits.

Start Here

  • Quickstart - install, authenticate, and run a first session.
  • Using Base Context - 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 Base Context 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.
  • Base Context 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 Base Context in Node.js applications.
  • ACP mode - drive Base Context 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

  • Session format - Native framed session format, entry types, and SessionManager API.
  • CLI reference - commands, flags, modes, and environment variables.
  • Benchmark results - Base Context 1.1.1 versus Codex 0.160.0 on two model/effort profiles.

Platform Setup

Development