Host your agents. Your work, multiplied.

Agents live in runtimes.

Not tied to your laptop. Every agent gets a persistent home.

• Any framework — Claude Code, Codex, Gemini CLI, and more
• Any machine — managed sandboxes, cloud computers, your own hardware
• Already built? — plug in Dify, Langflow and external agents

One place runs all of them.

Whatever the framework, every agent shows up the same way.

• Sessions, files, terminal — real workspaces, backed up
• Models per agent — managed or bring your own provider
• Usage per turn — tokens, cost and latency, always visible

Same agent. Every surface.

One capability, reachable from everywhere you already work.

• Your product — call it over an OpenAI-compatible API
• Team chat & terminal — Lark, Slack, WhatsApp, or the mf CLI
• Your schedule — automations run it, results get delivered

Bring what you already use.

Frameworks keep their native behaviour. Channels reach your team where they are. Runtimes are yours to pick.

• Frameworks — Claude Code · Codex · Gemini CLI · Openclaw · Hermes · NarraNexus · Dify · Langflow · A2A
• Channels — Lark · Slack · Discord · Telegram · WhatsApp · Matrix · WeChat · LINE · Linear · GitHub
• Runtimes — Stateful sandbox · Cloud computer · Your own machine · External services

Every run, on the record.

• Transcript. Every turn kept — the prompt, the tool calls, the files it touched. Pick the session back up weeks later.
• Cost. Tokens, latency, model and price per turn, across every provider you use.
• Control. Every permission an agent asked for, and what you answered, on the same record.

Transcripts, cost and permissions for every turn — including the runs that happened while you were asleep.

Start free. Scale when ready.

Every plan runs the same platform. Pick the limits that fit how many agents you keep online.

• Free — Free · Great for getting started and seeing what Manyfold can do.
• Hobby — $9 / mo · For solo builders running a few agents in production.
• Plus — $19 / mo · For small teams collaborating across many agents.
• Pro — $49 / mo · For teams running production workloads at scale.

Prices in USD. Cancel anytime. Need a custom tier? Reach out and we will size it with you.

The ones that decide it.

Is this just a wrapper around Claude Code or Codex?

No. Each framework runs in its native form, with its own execution model, model configuration and workspace semantics. Manyfold is the layer around them: runtime, workspace, orchestration, delivery and metering. When a framework ships something new, you get it the same day.

How is this different from a VM with agents installed?

A VM gives you compute. Manyfold gives you the part you would build next: framework bootstrap, persistent sessions, files and terminal, model configuration, skills and MCP, channels, automations and per-turn usage, for every agent, in one place.

Do I have to rebuild the agents I already have?

No. Connect your own laptop or server with the mf daemon, or plug in Dify, Langflow and other supported services as adapted work units. External runtimes keep their own capability boundaries, and we say where those boundaries are rather than pretending they do not exist.

What exactly does the API expose?

Your hosted agent behind an OpenAI-compatible endpoint, so existing SDKs work unchanged. Calls join the same session, permission and usage system as the web workspace. It is an agent you manage, not a bare model proxy.

Which surface should my team start with?

Most developers start in the web workspace, then wire the API into a product or a channel into team chat. Ops-minded teams often start with a schedule and a channel. Every surface reaches the same agents, so the order costs you nothing.