Compare

Hedy vs Coze

Coze gives you a studio to build bots and workflows. Hedy hands you a finished employee. The difference is whether you want to construct the worker — or hire one.

Hedy and Coze solve different problems. Coze is a platform where you build bots and workflows yourself—you design the flows, wire the nodes, and own every edge case. Hedy is a finished AI employee you hire: it runs self-hosted on your own infrastructure (Docker/K8s/air-gapped), speaks Lark and Slack as a first-class member, and ships governance built in—append-only audit, L0/L1/L2 approval tiers, deny-by-default writes, and per-asker ACL retrieval. With Coze you assemble capability and governance yourself. With Hedy, one hire replaces a team's output.

At a glance

HedyCoze
What you getA working AI employee, day oneA studio to build bots yourself
Autonomy modelOwns jobs: scheduled work, follow-ups, initiativeResponds to triggers and flows you design
GovernanceApproval tiers, audit ledger, allowlists built-inYou assemble your own controls
Self-hostingFirst-class: Compose / Helm / air-gapOpen-source studio version available
KnowledgeACL-scoped RAG with mandatory citationsRAG blocks you configure per bot
Best atBeing a colleague in Feishu/Lark/SlackCustom conversational apps and flows

Based on public information as of July 2026. Corrections welcome: hello@hedy.one

Where Coze shines

  • You want to design custom conversational apps or automations
  • Product teams who enjoy flow-builders and plugin wiring
  • Quick single-purpose bots for communities and campaigns

Where Hedy wins

  • No assembly: skills, guardrails and eval gates ship pre-built and tested
  • An employee model — persistent memory, scheduled duties, accountability ledger
  • Enterprise governance as defaults, not homework
  • One flat licence instead of per-bot construction effort

Which should you choose?

Choose Coze when the goal is building bespoke bots and you have the builders. Choose Hedy when the goal is headcount — a governed colleague that starts delivering the day the container starts. Plenty of teams run both.

In depth

Coze is a builder platform. You get nodes, prompts, plugins, and a canvas, and you assemble a bot or workflow. That is powerful when you want to construct something custom—but the burden of design, integration, and every failure mode stays with you. Hedy is the opposite starting point: it is a finished employee. You do not draw a flowchart; you assign work. It comes with a persona, skills, and scheduled duties, and it produces output the way a hired teammate would—closing the loop instead of handing you a toolkit.

The deeper split is governance. On a build-your-own platform, controls are something you remember to add: a check here, a guardrail there, mostly living in prompts. Hedy treats governance as the product. Write actions are deny-by-default with explicit allowlists. Approvals run in tiers—L0/L1/L2—so routine reads flow freely while consequential actions wait for a human. Retrieval is filtered by the asker's ACL, so people only get answers from documents they are entitled to see. An evidence gate requires every answer to quote its sources verbatim. And the audit log is append-only—no update or delete path. None of this is bolted on; it is how the runtime behaves.

Deployment and data boundaries differ too. Hedy is private, not cloud. It installs on your own infrastructure in about 30 minutes via Docker Compose, runs in air-gapped environments, and has no sub-processors—your data and prompts never leave your perimeter. You bring your own model keys, including local vLLM or Ollama, so inference can stay fully on-prem. Licensing is offline via Ed25519 signatures. A hosted bot platform routes your traffic and content through its cloud; Hedy is designed so nothing has to.

Fit is simple. Choose Coze when your goal is to build and operate bots yourself and you want a flexible construction surface. Choose Hedy when you want to hire an AI employee that shows up governed on day one—Lark and Slack native, self-hosted, audit-clean—and have one hire cover the output of a whole team rather than adding seats to a chat channel.

Questions

What is the difference between Hedy and Coze?
Coze is a platform for building bots and workflows yourself—you design flows and wire nodes. Hedy is a finished AI employee you hire, self-hosted on your own infrastructure, with governance built in: append-only audit, L0/L1/L2 approvals, deny-by-default writes, and per-asker ACL retrieval. Coze gives you building blocks; Hedy gives you output.
Can I self-host instead of using a cloud bot platform?
Yes. Hedy runs entirely on your own infrastructure via Docker or Kubernetes, including air-gapped environments, deployable in about 30 minutes with Docker Compose. It has no sub-processors, uses offline Ed25519 licensing, and lets you bring your own model keys including local vLLM or Ollama—so data and inference never have to leave your perimeter.
Do I have to build the governance and approvals myself?
No. On a build-your-own platform, controls are yours to add and maintain. Hedy ships governance as part of the runtime: write actions are deny-by-default with allowlists, approvals run in L0/L1/L2 tiers, retrieval is filtered by each asker's ACL, an evidence gate forces verbatim source citations, and the audit log is append-only with no delete path.
Does Hedy work with Lark and Slack?
Yes. Hedy treats Lark (Feishu) as a first-class member and also supports Slack. Rather than adding another bot seat to a channel, Hedy joins as an employee that takes on work and returns finished output—the aim is for one Hedy to cover a team's worth of output, not to add another assistant to your chat.

Related

hedy.one

See Hedy on your own infrastructure.

Book a demo