docs/development
a5c Development Documentation guide
Architecture, philosophy, and component guides for the a5c agent orchestration platform.
Pages in this section
Start with the section hub, then move sideways into adjacent pages when you need more detail.
a5c is an agent orchestration platform that enables any coding agent (Claude Code, Codex, Pi, Gemini CLI, Copilot CLI, etc.) to execute structured processes — from simple CI tasks to complex multi-phase development workflows. It unifies the fragmented landscape of coding agents behind a single launch, orchestration, and observability surface.
wiki/docs/development/01-overview-and-philosophy.md
The knowledge layer that drives all runtime behavior.
wiki/docs/development/02-atlas-graph-and-agent-catalog.md
How the babysitter orchestration system works across coding agent harnesses, from plugin generation through session lifecycle to run completion.
wiki/docs/development/03-babysitter-plugin-flows.md
The @a5c-ai/transport-adapter package bridges API protocol differences between harnesses and upstream providers.
wiki/docs/development/04-transport-adapter-proxy.md
The @a5c-ai/triggers-adapter package provides a GitHub Action and CLI for running coding agents from CI pipelines.
wiki/docs/development/05-triggers-ci-integration.md
Kradle is the Kubernetes-native deployment and management layer for the a5c platform.
wiki/docs/development/06-kradle-cloud-platform.md
The live-stack workflow validates end-to-end harness compatibility by running real agent/model combinations through the transport-adapter proxy. Each scenario installs a harness adapter, configures a model provider, and executes a babysitter process to confirm that the full pipeline — from agent CLI through transport-adapter translation to model API and back — works correctly.
wiki/docs/development/07-live-stack-qa-guide.md
a5c Development Documentation
Architecture, philosophy, and component guides for the a5c agent orchestration platform.
Documents
1. **Overview & Philosophy** — What a5c is, development philosophy (ontology-driven, evidence-backed), high-level architecture 2. **Atlas Graph & Agent Catalog** — The knowledge graph, how capabilities are modeled, evidence system, agent-catalog query layer 3. **Babysitter Plugin Flows** — The three muxes, activation modes, session lifecycle, run orchestration, harness-specific flows 4. **Transport Adapter & Proxy** — Provider protocol bridging, completion engines, message translation, tool forwarding, streaming 5. **Triggers & CI Integration** — GitHub Action, trigger evaluation, harness setup, invocation modes, example workflows 6. **Kradle & Cloud Platform** — Kubernetes operator, web UI, API, resource model, deployment