bubbuild / bub
Bub it. Build it. A common shape for Agents.
AI Architecture Analysis
This repository is indexed by RepoMind. By analyzing bubbuild/bub in our AI interface, you can instantly generate complete architecture diagrams, visualize control flows, and perform automated security audits across the entire codebase.
Our Agentic Context Augmented Generation (Agentic CAG) engine loads full source files into context on-demand, avoiding the fragmentation of traditional RAG systems. Ask questions about the architecture, dependencies, or specific features to see it in action.
Embed this Badge
Showcase RepoMind's analysis directly in your repository's README.
Repository Overview (README excerpt)
Crawler viewBub Bub is a common shape for agents. It starts from a simple question: if there are many agents in the world, what kind of agent is a Bub? A Bub is an agent that can live inside shared operator environments with explicit boundaries, visible execution evidence, and safe handoff. The point is not only to complete tasks, but to remain understandable, reviewable, and continuable when more humans and agents join the work. Current Implementation This repository is the current Python implementation of Bub. It is hook-first, built on , and keeps the core small while builtins and plugins provide behavior. In this implementation, Bub uses Republic as its context runtime and constructs context from tape. • CLI bootstrap: (Typer app) • Turn orchestrator: • Hook contract: • Builtin hooks/runtime: + • Skill discovery and validation: Quick Start CLI Commands • : execute one inbound turn and print outbound messages • : persist OpenAI Codex OAuth credentials for later runs • : print hook-to-plugin bindings • : install plugin from PyPI or (GitHub shorthand) Runtime Behavior • Regular text input: uses ; if runtime is unavailable, output falls back to the prompt text • Comma commands: , , , etc. • Unknown comma commands: executed as in workspace • Session event log: • : if present in workspace, appended to runtime system prompt Skills • Discovery roots with deterministic override: • 2. • • Each skill directory must include • Supported frontmatter fields: • required: , • optional: , , , Plugin Development Plugins are loaded from Python entry points in : Implement hooks with following . Runtime Environment Variables • : (default), , • : default • : runtime provider key; optional when using models with • : optional provider base URL • : upstream API shape; default Use for OpenAI Responses-compatible providers and for chat-completions-style providers. • : default • : default • : default Documentation • : overview • : lifecycle, precedence, and failure isolation • : skill discovery and frontmatter constraints • : CLI usage and comma command mode • : implemented capabilities and limits Development Checks License Apache-2.0