# LiveGraph — full listing > LiveGraph is a model-agnostic multi-agent orchestration platform built around a live, > editable canvas: agents are nodes, routing is edges, and a run can be watched, interrupted, > approved, and rerouted while it is executing — the engine re-reads the graph on every hop, > so dragging an edge mid-run changes where the run goes next. Hosted at livegraph.ai. > > This is the expanded variant of /llms.txt — every public page, generated from the same > registries the sitemap reads. /agents.md is the guide for AI agents integrating LiveGraph. ## Pages - [https://www.livegraph.ai/](https://www.livegraph.ai/) - [https://www.livegraph.ai/pricing](https://www.livegraph.ai/pricing) - [https://www.livegraph.ai/demo](https://www.livegraph.ai/demo) - [https://www.livegraph.ai/privacy](https://www.livegraph.ai/privacy) - [https://www.livegraph.ai/terms](https://www.livegraph.ai/terms) - [https://www.livegraph.ai/docs](https://www.livegraph.ai/docs) - [https://www.livegraph.ai/blog](https://www.livegraph.ai/blog) - [https://www.livegraph.ai/changelog](https://www.livegraph.ai/changelog) - [https://www.livegraph.ai/status](https://www.livegraph.ai/status) - [https://www.livegraph.ai/migrate/flowise](https://www.livegraph.ai/migrate/flowise) - [https://www.livegraph.ai/migrate/agent-builder](https://www.livegraph.ai/migrate/agent-builder) - [https://www.livegraph.ai/migrate/n8n](https://www.livegraph.ai/migrate/n8n) - [https://www.livegraph.ai/migrate/langflow](https://www.livegraph.ai/migrate/langflow) - [https://www.livegraph.ai/migrate/dify](https://www.livegraph.ai/migrate/dify) - [https://www.livegraph.ai/migrate/crewai](https://www.livegraph.ai/migrate/crewai) - [https://www.livegraph.ai/migrate/make](https://www.livegraph.ai/migrate/make) - [https://www.livegraph.ai/model-radar](https://www.livegraph.ai/model-radar) - [https://www.livegraph.ai/security](https://www.livegraph.ai/security) - [https://www.livegraph.ai/templates](https://www.livegraph.ai/templates) - [https://www.livegraph.ai/mcp](https://www.livegraph.ai/mcp) - [https://www.livegraph.ai/compare](https://www.livegraph.ai/compare) ## Blog - [We gave LiveGraph a paragraph. It built citepath.ai — and it hasn't stopped.](https://www.livegraph.ai/blog/livegraph-built-citepath) (2026-10-06): citepath.ai is a live GEO SaaS built entirely by a LiveGraph bootstrap run and its improvement loop: provisioning, self-hosted CI, thirty-three merged PRs, every failure — and what each failure became. - [A loop wrote a complete SaaS for $23.85 — then handed over the keys.](https://www.livegraph.ai/blog/livegraph-built-findefend) (2026-10-06): findefend.com went from a paragraph-long brief to a live, self-improving product: one bootstrap run, fourteen reviewed PRs, real incidents that became platform fixes — and a credential handoff where the model never saw the password. - [Our engineering team is a LiveGraph graph. Here is what broke.](https://www.livegraph.ai/blog/engineering-team-as-a-graph) (2026-10-04): LiveGraph's own repo is improved by a LiveGraph loop: a tick fires the Lead, an engineer works through the GitHub MCP, CI routes its own verdict, and a human gate decides every merge. Including the three ways it failed. - [Share a run people can watch, not a log they can't](https://www.livegraph.ai/blog/share-your-runs) (2026-10-04): POST /runs/:id/share mints a stateless token that renders a read-only, live-updating canvas — topology and hop status, never hop content. Embed it in docs, status pages, or a client deliverable. - [LangGraph edits a run's state. LiveGraph edits a run's route.](https://www.livegraph.ai/blog/langgraph-vs-editable-canvas) (2026-10-03): LangGraph compiles your topology into code; LiveGraph keeps it in data you can mutate between hops. Two different primitives — an honest map of where each one fits. - [We pointed LiveGraph at an empty domain. It shipped a product.](https://www.livegraph.ai/blog/livegraph-built-modelright) (2026-10-02): modelright.dev went from a domain name to a live, self-improving app through one bootstrap run and a 10-minute improvement loop — approvals, conflicts, and all. - [Steer a running agent workflow](https://www.livegraph.ai/blog/steer) (2026-09-28): LiveGraph re-reads the graph after every hop, so dragging an edge changes where this run goes next. - [Why you can't reroute a running n8n workflow (and why you can in LiveGraph)](https://www.livegraph.ai/blog/why-you-cant-reroute-a-running-workflow) (2026-09-12): Most engines compile a run before executing it, so mid-run edits only affect the next run. A per-hop engine makes rerouting free — here's the architecture. - [Giving agents write access to real code without losing sleep](https://www.livegraph.ai/blog/giving-agents-write-access-without-losing-sleep) (2026-09-12): Worktree isolation, operator allowlists, encrypted secrets, and pushes only a human's literal keystrokes can trigger — the safety model, decision by decision. ## Comparisons - [LiveGraph vs n8n](https://www.livegraph.ai/compare/n8n): n8n executes a persisted workflow snapshot and its canvas goes inert at run time; LiveGraph's canvas stays live and steerable while a run executes. An honest side-by-side. - [LiveGraph vs Lindy](https://www.livegraph.ai/compare/lindy): Lindy hides the agent graph entirely — there's no canvas to open or steer. LiveGraph is the graph: visible, editable, and live while a run executes. An honest side-by-side. - [LiveGraph vs Gumloop](https://www.livegraph.ai/compare/gumloop): Gumloop's flow canvas goes inert once a run starts — the documented answer to a stuck run is restarting it. LiveGraph's canvas stays live and steerable mid-run. An honest side-by-side. - [LiveGraph vs Zapier Agents](https://www.livegraph.ai/compare/zapier-agents): Zapier Agents is the black-box end of the category — no orchestration graph to inspect or steer. LiveGraph is a live, editable agent canvas. An honest side-by-side. - [LiveGraph vs LangGraph](https://www.livegraph.ai/compare/langgraph): LangGraph's checkpointing is the deepest intervention model in the field — but it forks state inside a topology frozen in code. LiveGraph rewires the topology itself, mid-run. An honest side-by-side. - [LiveGraph vs Langflow](https://www.livegraph.ai/compare/langflow): Langflow's drag-and-drop canvas is where you build a flow — at run time it's a test surface, not a steering wheel. LiveGraph's canvas stays live and steerable mid-run. An honest side-by-side. - [LiveGraph vs Dify](https://www.livegraph.ai/compare/dify): Every Dify run executes the published workflow version — the canvas you edit is a draft the run never sees. LiveGraph's engine re-reads the live graph on every hop. An honest side-by-side. - [LiveGraph vs CrewAI](https://www.livegraph.ai/compare/crewai): CrewAI defines role-based agent teams in Python; its visual Studio is an enterprise tier that observes runs rather than steering them. LiveGraph puts the wiring on a live, editable canvas. An honest side-by-side. - [LiveGraph vs Make](https://www.livegraph.ai/compare/make): Make runs activated scenarios on schedule — once an execution is in flight you can't even stop it from outside the editor. LiveGraph's canvas stays steerable mid-run. An honest side-by-side. ## Agent-facing files - [https://www.livegraph.ai/agents.md](https://www.livegraph.ai/agents.md): how an AI agent uses or integrates LiveGraph — MCP serving, the runs API, API keys - [https://www.livegraph.ai/llms.txt](https://www.livegraph.ai/llms.txt): the curated short version of this file - [https://www.livegraph.ai/llms-full.txt](https://www.livegraph.ai/llms-full.txt): this file