The Terraform model for agent harnesses. Declare your whole harness once — agents, memory, tools, gates, flows — validate it before you ship, then provision native configs for Claude Code, OpenClaw, Codex, Cursor, and more.
Every agent harness is hand-assembled — 15 files, custom prompts, hooks, MCP servers, memory wired by hand. It's the agentic equivalent of clicking through a cloud console. No source of truth, and no two harnesses built the same way twice.
You apply blind. There's no validate, no preview of the loop, no graph of how your agents actually connect. You learn the wiring is broken when it fails at runtime — never before.
Built your harness for Claude Code? Now re-author the whole thing for OpenClaw, Codex, or Cursor — completely different config formats. There's no provider abstraction for harnesses. You rewrite everything from scratch.
Write your whole harness in a single .at file — agents, memory, tools, flows, gates, groups. Or start from a template.
29 built-in rules validate the wiring and an interactive graph shows the loop — before you ever apply.
One command emits platform-native configs. Claude Code, OpenClaw, Codex, Cursor — same harness, any provider.
A declarative topology file that describes agents, their memory, capabilities, and how they connect. The single source of truth — no boilerplate.
topology dev-team : [pipeline, fan-out, debate] { orchestrator { model: opus, handles: [intake] } agent researcher { model: sonnet, tools: [Read, WebSearch] } agent writer { model: sonnet, tools: [Read, Write] } agent reviewer { model: opus outputs: { verdict: approve | revise } } group design-review { members: [architect, security-lead] speaker-selection: "round-robin" max-rounds: 3 } gates { gate quality-check { after: reviewer run: "scripts/lint.sh" on-fail: halt } } flow { intake -> researcher -> writer -> reviewer reviewer -> writer [when verdict == revise, max 2] reviewer -> design-review [when verdict == approve] } }
Real-world topologies you can explore, download, and scaffold in seconds.
Parallel lint, test, and security analysis with consolidated senior review.
Test-driven debugging with iterative fix loops and verification.
Research trends, draft articles, edit for brand voice, and publish across channels.
Triage, respond, and escalate customer support with multi-tier oversight.
AgenTopology is Apache 2.0. Your .at files are the source of truth and work everywhere — no vendor lock-in, no proprietary formats.