OPEN SOURCE / APACHE 2.0

The trust, provenance, and governance layer for human-and-agent workflows.

A Treeship gives your agents verifiable identity, trusted handoffs, approvals, and portable proof. Run one on your own machine. Dock into Hub when you want visibility, management, and discovery.

Useful alone. Better when connected.Undock anytime. Your Treeship keeps working.

Workflow Graph

Vendor negotiation flow

Portable bundle ready

Human Intent

Budget under $2,000 approved

OpenClaw Main

Initial outreach sent

Pricing Subagent

Counteroffer analyzed

Human Approval

Final response approved

Execution

Negotiation completed

What is a Treeship?

An independently owned trust domain for human-and-agent workflows. Bring humans and agents aboard, verify what happened, and keep trust portable.

What does it give agents?

Verifiable identity, trusted handoffs, approvals, proofs, and a workflow history they can carry across tools, teams, and environments.

What is the Dock?

The secure connection between your Treeship and Hub. Dock in for visibility, management, and discovery. Undock anytime without losing your system.

Why does it matter?

AI workflows are getting more powerful and harder to trust. Treeship closes the trust, provenance, and governance gap.

One Treeship, many agents.

A Treeship is a trust domain, not just an agent. One Treeship can hold many agents and humans under shared keys, policy, and governance. Create a new Treeship when the trust boundary changes.

Personal

Solo developer

One Treeship with a coding agent, research agent, and reviewer. All under one key and one policy.

human://youagent://coderagent://reviewer
Team

Product team

One Treeship for the team. PM agent, engineering agent, QA agent, and a human approver. Shared workflow graph.

human://pmagent://engagent://qaagent://deploy
Enterprise

Separate boundaries

Separate Treeships for different customers, regulated workflows, or external partners. Different keys, different policy.

Customer ACustomer BInternal

Build on Treeships

Connect any agent. Get a trust layer automatically.

Treeship does not replace your orchestration stack. It gives your stack verifiable identity, trusted handoffs, portable bundles, and human approvals without locking you into one hosted backend.

Identity attestation
Action attestation
Handoff attestation
Approval attestation
Portable proof bundles
Undocked local verification

CLI quick start

$ treeship init --name my-project
Treeship initialized
Ship ID: ship_3ba02c6e43f0
$ treeship wrap -- npm test
Tests: 83 passed
attested
id: art_8e0ae199a1b1
$ treeship dock login
visit treeship.dev/dock/activate
code: 4b0a-6d36
docked
$ treeship dock push art_8e0ae199a1b1
pushed
url: treeship.dev/verify/art_8e0ae...

Install

cargo install --git https://github.com/zerkerlabs/treeship treeship-cli
treeship init --name my-agent
treeship wrap -- npm test
treeship dock push art_xxx

Works with Claude Code, Cursor, OpenClaw, LangChain, custom Python or Node.js agents, or any REST-capable system.

Dock and undock

Dock into Hub for more. Undock anytime without losing your Treeship.

Docking opens a secure outbound connection from your Treeship to Hub. Your keys, local truth, and private workflow data stay with your Treeship. Hub adds visibility, graph rendering, approvals, and fleet management on top.

Treeship owns keys, artifacts, and verification root
Hub receives selected metadata, graph shape, and published proof surfaces
Private payloads remain local unless explicitly shared
Undocking revokes access without breaking local operation

Undocked

Local verification, artifact history, portable bundles, self-hosted proof pages.

Docked

Workflow graph, approval inbox, fleet visibility, hosted proof surfaces.

Self-published

Expose your own verify URLs and feeds from your infrastructure.

Cross-Treeship

Exchange signed bundles and verify handoffs across sovereign trust domains.

$ treeship dock login
visit treeship.dev/dock/activate
code: 4b0a-6d36
docked
dock id: dck_661e5463912d
endpoint: https://api.treeship.dev
$ treeship dock push art_8e0ae199a1b1
pushed
url: https://treeship.dev/verify/art_8e0ae199a1b1
rekor: rekor.sigstore.dev #12847291

Why bother?

Trust the workflow, not just the output.

Treeship helps developers and teams move from opaque agent behavior to governed, portable, verifiable workflows that survive vendors, tools, and environments.

Multi-agent software delivery

Track plan, code, review, approve, deploy with trusted handoffs, visible subagents, and portable proof.

Human-in-the-loop operations

Give agents autonomy where it helps and human approvals where it matters. Keep both inside one verifiable workflow history.

Cross-company coordination

Exchange work between sovereign trust domains without collapsing into one shared backend or losing provenance.

Commerce and intent

Bind human intent, delegated authority, agent execution, and resulting proof into one portable trust flow.

Built on standards, not invented cryptography

Treeship uses established primitives so you never depend on proprietary trust schemes.

Ed25519

RFC 8032 signatures

DSSE

Signed envelopes

SHA-256

Content addressing

RFC 8785

JSON canonicalization

Questions

What is a Treeship?

An independently owned trust instance for human-and-agent workflows. It holds keys, policy, storage, and verification rules for one trust domain.

Can one person have multiple Treeships?

Yes. A person can have a personal Treeship, a company Treeship, a client Treeship, and a project Treeship. Each is a separate trust domain.

Can one Treeship support multiple agents?

Yes. That is the default. Most workflows involve multiple agents under one shared policy boundary.

What about subagents?

Subagents live inside the same Treeship as their parent agent, with their own identity and delegated permissions.

When should I create a new Treeship?

When the trust boundary changes: different owner, organization, legal boundary, or policy requirements.

Do I need to dock to use it?

No. Your Treeship works fully offline. Docking adds visibility, sharing, and team features.

What agents does Treeship work with?

Any agent that can run shell commands or call an API. Claude Code, Cursor, OpenClaw, LangChain, custom runtimes, or any REST-capable system.

Start your way

Connect your agent. Treeship sets up the trust layer automatically.

Start with Claude Code, OpenClaw, MCP, or your own runtime. Get a Treeship automatically, use it locally, and dock into Hub when you want visibility, management, and discovery.