Agentic AI Atlasby a5c.ai
OverviewWikiGraphFor AgentsEdgesSearchWorkspace
/
GitHubDocsDiscord
i.4Wiki
Agentic AI Atlas · atlas — the catalog & knowledge graph
docs/user-guide/ecosystem/atlasa5c.ai
Search the atlas/
Wiki · linked records

Article and nearby pages

I.Current articlepp. 1 - 1
adapters — a family, not one thingbabysitter-sdk — the core enginegenty — the unified agent runtimekip-sdk — memory substrate (SPEC / DESIGN ONLY)kradle — Kubernetes-native Git forge (MVP)observer-dashboard — real-time run observability
I.
Wiki article

docs/user-guide/ecosystem/atlas

Reading · 3 min

atlas — the catalog & knowledge graph reference

Docs(../index.md) › Ecosystem(./overview.md) › atlas

Page nodewiki/docs/user-guide/ecosystem/atlas.mdNearby pages · 7Documents · 0

Continue reading

Nearby pages in the same section.

adapters — a family, not one thingbabysitter-sdk — the core enginegenty — the unified agent runtimekip-sdk — memory substrate (SPEC / DESIGN ONLY)kradle — Kubernetes-native Git forge (MVP)observer-dashboard — real-time run observabilityBabysitter Ecosystem Overview

Docs › Ecosystem › atlas

atlas — the catalog & knowledge graph

**Package:** @a5c-ai/atlas · **CLI:** atlas (alias a5c-atlas) · **Version:** 6.0.0 · **Maturity:** GA

**Atlas is the unified knowledge graph and catalog for the ecosystem. It is the single source of truth for harness metadata, discovery snapshots, plugin targets, host detection, and package/process topology — and it is what lets you add a harness as a *data change* rather than a code change.**

---

On this page

  • What it is
  • How it works
  • Why it matters for obedience
  • Entrypoints
  • Who uses it
  • Next steps

---

What it is

Atlas is described in its own package as the "Atlas catalog graph data, SDK, and CLI." It is the unified knowledge graph / ontology / catalog that the rest of the stack reads from. Rather than hand-wiring harness facts into the runtime, those facts live in Atlas as data and are generated into types and snapshots.

---

How it works

The pipeline is data-first:

Code
YAML graph definitions  →  generated TypeScript types  →  JSON snapshots consumed at runtime
  • **YAML graph definitions** describe the catalog (harnesses, plugin targets, topology).
  • Those compile to **generated TS types** so consumers get type safety.
  • And to **JSON snapshots** that the runtime reads directly.

The catalog runtime surface is exposed at @a5c-ai/atlas/catalog, with additional subpaths ./indexer and ./graph-index. An MCP endpoint is exposed through the Atlas WebUI (/api/mcp, Streamable HTTP).

---

Why it matters for obedience

A core v6 design principle is that "every integration surface is defined once in a central catalog and multiplexed to N adapters or targets through generated code." Atlas *is* that central catalog. Because harness/plugin/discovery metadata is generated data, the adapters family and the hooks lifecycle don't have to be re-coded per harness — they read Atlas. That keeps the enforcement layer consistent across every supported harness.

---

Entrypoints

SurfaceDetail
Binsatlas, a5c-atlas
Subpaths./catalog, ./indexer, ./graph-index
MCPExposed via the Atlas WebUI at /api/mcp (Streamable HTTP)

A quick taste of the CLI:

bash
# Inspect the catalog the runtime will read
atlas --help

Atlas CLI subcommands and flags are governed by the repository's CLI allowlist; consult atlas --help on your installed version for the authoritative, version-matched surface.

---

Who uses it

The SDK, the adapters family, the hooks lifecycle, plugin tooling, and the Atlas WebUI all consume the catalog. In the architecture, Atlas sits beside the SDK and feeds the adapters/hooks/plugins layer with the metadata they need.

---

Next steps

  • **See where it sits:** Architecture & How It Fits Together
  • **See what it feeds:** Adapters overview and the Adapter Types reference
  • **Ecosystem map:** Ecosystem Overview

Trail

Wiki
Babysitter Docs
Babysitter User Guide

Ecosystem

atlas — the catalog & knowledge graph

Continue reading

adapters — a family, not one thing
babysitter-sdk — the core engine
genty — the unified agent runtime
kip-sdk — memory substrate (SPEC / DESIGN ONLY)
kradle — Kubernetes-native Git forge (MVP)
observer-dashboard — real-time run observability
Babysitter Ecosystem Overview

Page record

Open node ledger

wiki/docs/user-guide/ecosystem/atlas.md

Documents

No documented graph nodes on this page.