Agent Builder

Create the agent that remembers, governs, and acts.

Keep Claude Code, Gemini, or Codex. ODEI adds a persistent Digital World Model and a Governance Loop above the model layer, so your agent keeps context, follows policy, and carries work forward across every session reset

Create My Agent

Upgrade My Agent Launch Builder

DIGITAL WORLD MODEL

Loading World Model

Bootstrap prompt Codex bootstrap

Pick the terminal AI you already use. The bootstrap installs ODEI locally and binds the runtime to the launch workspace below.

Model lane can change. World Model, governance, receipts, and reopen state stay attached to ODEI.

Create My Agent Upgrade My Agent Launch Builder

CHOOSE YOUR PATH

Choose your path.

YOUR FIRST AGENT

Create your agent

No code required. Launch a personalized AI assistant in minutes. Create a digital World Model and governance loops for your life and business.

CREATE MY AGENT

TERMINAL INTEGRATION RECOMMENDED

Upgrade your AI agent

Stop rebuilding context every morning. Give Claude Code, Gemini, or Codex a persistent World Model and rigid governance loops.

UPGRADE MY AGENT Works with Claude Code · Gemini · Codex

RUNTIME DESIGN

Launch Builder

Shape the World Model boundary, governance mode, execution surfaces, and first mission before you activate the runtime.

LAUNCH BUILDER Builder surface for runtime scope, mission design, and launch contracts

STOP FALLING BEHIND

Everyone has the same AI.
If your value is prompting - you're competing with everyone.

Same model, same weights, same context window. The only difference is who builds a system around it.

Re-explain

→

Generate

→

Copy

→

Paste

→

Verify

↺

Repeat

∞ Y O U

Every hour in this loop is an hour anyone else could do. No compounding. No leverage. Just labor.

The Tax

What this loop actually costs you

Time tax

You spend hours per week re-explaining, fixing, and following up. None of it compounds.

+10h / week

Attention tax

You stay in the loop as executor, verifier, and reminder. Context switching becomes the job.

constant interrupts

Failure tax

Follow-ups slip. Deadlines drift. You only notice when it's already late.

missed outcomes

The Shift

AI models are becoming commodities, like electricity or water.
The ones who win own the infrastructure.

Your memory. Your rules. Your execution. Your receipts. Any model.

AUTONOMOUS GOVERNANCE LOOP (24/7)

Observe

→

Decide

→

Act

→

Verify

→

Evolve

DIGITAL WORLD MODEL Accumulating state, memory, and governance rules

Assistants are an interface. ODEI is infrastructure.
Interfaces talk to you. Infrastructure carries responsibility when you forget.

RENTING (Commodity)

Memory wiped or locked in UI

Policy resets every session

Execution manual copy-paste loop

Audit invisible black box

Model vendor lock-in

OWNING (Infrastructure)

Memory portable, versioned, yours

Policy rules that persist

Execution actions, not drafts

Audit receipts for everything

Model swap anytime

Comparison

What your current tools are missing.

ODEI doesn’t replace your AI. It adds the layer they can’t build.

Feature	Claude Code	Codex CLI	Gemini CLI	+ ODEI
Memory	✗CLAUDE.md instruction files. Auto-memory with 200-line limit.	~2-phase SQLite extraction pipeline. Flat-file consolidation.	✗Single GEMINI.md file. Append-only memory.	✓Neo4j knowledge graph + Governance Loop: Observe → Decide → Act → Verify → Evolve. Deterministic persistence.
Governance	~21 lifecycle hooks + permission allowlist.	~Starlark rule engine + kernel-level OS sandbox.	~5-tier TOML policy engine. Seatbelt sandbox.	✓9-layer Constitutional Guardian. Deterministic. Every mutation validated before write.
Audit Trail	✗Local history.jsonl. Session transcripts.	~Session JSONL + optional OpenTelemetry.	~OpenTelemetry with vendor-neutral export.	✓Graph-native AuditLogEntry. Version history. Traceability paths. Queryable receipts.
Model Freedom	✗Claude models. Third-party proxy available.	~OpenAI native + Ollama local models.	✗Gemini models only.	✓Any MCP-compatible model. Memory and governance survive every switch.
World Model	✗	✗	✗	✓7-domain knowledge graph
Continuity	✗Session-based. CLAUDE.md persists between sessions.	~Session resume. Background memory extraction.	✗Session-based. Memory overhaul in progress.	✓Graph-native. Nothing resets. Deterministic persistence. Ever.

Memory

✗Claude CodeCLAUDE.md instruction files. Auto-memory with 200-line limit.

~Codex CLI2-phase SQLite extraction pipeline. Flat-file consolidation.

✗Gemini CLISingle GEMINI.md file. Append-only memory.

✓+ ODEINeo4j knowledge graph + Governance Loop: Observe → Decide → Act → Verify → Evolve. Deterministic persistence.

Governance

~Claude Code21 lifecycle hooks + permission allowlist.

~Codex CLIStarlark rule engine + kernel-level OS sandbox.

~Gemini CLI5-tier TOML policy engine. Seatbelt sandbox.

✓+ ODEI9-layer Constitutional Guardian. Deterministic. Every mutation validated before write.

Audit Trail

✗Claude CodeLocal history.jsonl. Session transcripts.

~Codex CLISession JSONL + optional OpenTelemetry.

~Gemini CLIOpenTelemetry with vendor-neutral export.

✓+ ODEIGraph-native AuditLogEntry. Version history. Traceability paths. Queryable receipts.

Model Freedom

✗Claude CodeClaude models. Third-party proxy available.

~Codex CLIOpenAI native + Ollama local models.

✗Gemini CLIGemini models only.

✓+ ODEIAny MCP-compatible model. Memory and governance survive every switch.

World Model

✗Claude Code

✗Codex CLI

✗Gemini CLI

✓+ ODEI7-domain knowledge graph

Continuity

✗Claude CodeSession-based. CLAUDE.md persists between sessions.

~Codex CLISession resume. Background memory extraction.

✗Gemini CLISession-based. Memory overhaul in progress.

✓+ ODEIGraph-native. Nothing resets. Deterministic persistence. Ever.

Disclaimer: This comparison is provided for informational purposes only and does not constitute legal, financial, or professional advice. Feature descriptions are based on publicly available documentation as of April 2026 and may not reflect current capabilities. Trademarks and product names belong to their respective owners. ODEI is not affiliated with, endorsed by, or sponsored by any of the companies listed. No warranty is made regarding the accuracy or completeness of this information. Use at your own discretion.

What you get

A personal agent system you can actually keep using.

When you start using ODEI, your AI stops acting like a disposable session. Memory stays attached, action boundaries hold, real tools become governed execution surfaces, and the same runtime can be reopened, inspected, and improved over time.

Day one outcome You do not just get better answers. You get a runtime that remembers, acts, and stays accountable.

ODEI sits above the model layer, so the part that compounds is yours: memory, governance, continuity, receipts, and the ability to switch models later without rebuilding the system.

01 Memory

Your runtime remembers the work.

Important context moves out of your head and into a persistent system you can reopen instead of re-explaining from scratch.

02 Execution

Your agent can use real tools for real outcomes.

Email, browser, calendar, APIs, and business systems become governed execution surfaces instead of extra tabs you manage by hand.

03 Governance

Your action boundary stays stable.

Approvals, rules, and policy remain attached to the runtime, so every task does not start with fresh supervision and fresh negotiation.

04 Continuity

Your progress survives every session reset.

Sessions can end, but the operating context does not disappear. State, priorities, and active work pick up where they left off.

05 Receipts

You can inspect what actually happened.

ODEI leaves a reviewable trail, so actions are traceable, mistakes surface earlier, and the system is auditable instead of opaque.

06 Model freedom

You keep the system even if you switch models.

Memory, governance, and continuity live above Claude Code, Gemini, or Codex, so you can change the model without losing the runtime.

Your AI deserve
World Model and Governance Loop.

Create My Agent Upgrade My Agent Launch Builder

Get started

Your AI deserves memory and governance.

Create My Agent Read Governance Gap

Upgrade My Agent

Keep your lane.

Use the AI you already trust, then lock the runtime boundary, first mission, and continuity trail inside ODEI.

Create My Agent

Launch your first personal agent through a guided path and one bounded runtime.

Upgrade My Agent

Keep the terminal AI you already use and add memory, governance, continuity, and receipts.

Launch Builder

Shape the runtime boundary, mission, and governance contract before activation.

Problem Read the architecture

Connect AI

AI forgets the work.

Every new session drops memory, intent, and the work already done.

Lock boundary

You glue tools manually.

Browser, docs, APIs, tasks, and messaging still have to be stitched together manually.

Mint continuity

No safe runtime boundary.

Without approvals, policy, and explicit scope, AI cannot act as a reliable system.

Open runtime

No continuity or proof.

You cannot reopen the same runtime cleanly or inspect what the agent actually did.

Launch workspace

Launch your agent.

Move through one bounded path from operator boundary to governed runtime.

Step 1 of 4 Operator boundary Ownership and resume

Operator boundary

Set owner, resume path, and review posture.

Operator name Role / profession

Telegram Handle Operator scope

Optional continuity fields

Agent name Workspace Name

Email X / Twitter

Review & launch workspace

Preview the live launch path, inspect the workspace packet, then submit the exact same-origin runtime contract.

Launch path preview

Preview the exact route from intake to first mission launch before you submit.

Open preview boundary Open handoff contract Open first mission launch packet

Current lane Preview public

Current action Shape the first runtime boundary

Proof chain Preview URL plus the same-origin launch bootstrap, launch model, launch plan, launch session, and launch resume are inspectable before submit.

01 Start here

Shape runtime

Choose runtime profile, model lane, world sources, execution surfaces, and first mission.

02 Boundary next

Lock operator boundary

Identity, governance, billing mode, and consent should be explicit before intake is submitted.

03 Awaiting intake

Submit intake

Mint the intake ID, status endpoint, provisioning capsule, and resume URL from the exact runtime contract.

04 Review gate

Review handoff

Use the activation handoff packet to align continuity, runtime boundary, first outcome, and launch gate.

05 Mission launch

Launch first mission

The first governed runtime should come back with one real delivery, receipts attached, and a measurable success signal.

Activation workspace preview

See the continuity trail, commercial boundary, first mission, and activation package before submit.

Commercial envelope Account boundary Activation readiness Runtime package

01 Preview boundary

Define the first runtime contract before any provisioning starts.

02 Intake captured

Receive the intake ID, status endpoint, and provisioning capsule immediately.

03 Reviewed provisioning

Lock runtime scope, governance, billing, and the first launch boundary.

04 Activation ready

Deliver the first bounded runtime, mission queue, and receipt surface.

Current phase Preview public

Define the first runtime boundary and request cohort access when the launch contract looks right.

Current action Shape the first runtime boundary

Next action Submit intake to mint the intake ID and provisioning capsule

Boundary status Complete the intake boundary

Launch progress 0 captured · 0 defined · 0 pending input · 0 pending review

Continuity Preview state only

Submitting the intake mints a canonical intake ID, provisioning capsule, status endpoint, and resume path.

No intake yet Preview public

Open preview state

Account boundary Odei Operating Workspace · Solo operator

Identity, entitlements, billing mode, and runtime ownership converge into one inspectable account boundary.

Auth Operator identity captured

Entitlements Preview only until activation

Billing Invoice me for initial setup

Commercial shape Setup + runtime + metered execution

First mission Weekly operating brief

Prepare my weekly operating brief and surface the follow-ups that actually matter.

First delivery A governed operating brief with the real next actions already queued.

Success signal The operator stops rebuilding the week manually and can act from one governed brief.

Receipt surface Signals, draft actions, approval requests, and outcome checks attached to the brief.

World perimeter Email · Calendar · Documents

Activation package Executive operator · Odei Operating Workspace · Solo operator

The first activation should yield one bounded runtime with governance, receipts, and a first mission queue.

Governance Approval-first · Review with me first

Review Runtime scoping → governance review → activation ready

Receipts Signals, approvals, queued actions, and outcome checks remain attached.

Checklist Pending input before submit

Launch contract payload

This is the exact same-origin runtime contract bound to your selections before intake is submitted.

{}

Open advanced runtime surfaces

Advanced runtime surfaces

The core launch flow stays above. Open this layer when you want the compact handoff packet, the first mission launch packet, or the individual backend contracts that power the runtime.

Activation handoff packet

This is the concise packet ODEI works against: continuity anchor, runtime boundary, first live outcome, and launch gate. It is compact enough for a human review and structured enough for another agent to consume.

Open handoff contract Download handoff JSON

Continuity anchor Preview state only

Submit intake to mint the intake ID, live status endpoint, provisioning capsule, and resume path.

Runtime boundary Executive operator · Odei Operating Workspace · Solo operator

One bounded account boundary keeps ownership, billing, entitlements, and governance explicit.

First live outcome A governed operating brief with the real next actions already queued.

The first runtime should return one delivery, one receipt surface, and one measurable success signal in the first week.

Launch gate Pending input before submit

Reviewed provisioning locks identity, commercial boundary, governance, and first mission before activation.

{}

First mission launch packet

This packet closes the last gap between reviewed provisioning and the first real outcome: exact mission, bounded runtime, launch gate, and the first win expected from launch.

Open launch packet contract Download launch JSON

Launch state Preview boundary still open

Complete the runtime boundary, then move into reviewed provisioning for the first mission launch.

Mission boundary Executive operator · Odei Operating Workspace · Solo operator

One bounded runtime, one governance mode, and one first mission keep the launch auditable.

First outcome A governed operating brief with the real next actions already queued.

The first mission should return one concrete delivery, one receipt lane, and one success signal in the first week.

Operator proof Preview URL + exact intake contract

The mission becomes launchable only when continuity, governance, and launch gate are inspectable in one packet.

{}

Expanded contract surfaces

Use these slices when you want the first mission launch packet, mission contract, activation package, workspace contract, governance loop, and launch checklist individually instead of through the unified activation workspace.

First mission outcome

The first runtime should return one governed outcome immediately: a real delivery, a receipt trail, and a success signal you can verify in the first week.

Template Weekly operating brief

Prepare my weekly operating brief and surface the follow-ups that actually matter.

First delivery A governed operating brief with the real next actions already queued.

The first win is fewer hidden threads and less manual context reconstruction.

Receipts Signals, draft actions, approval requests, and outcome checks attached to the brief.

The work is only real if the brief leaves an inspectable receipt trail.

Success signal The operator stops rebuilding the week manually and can act from one governed brief.

Memory should reduce cognitive overhead in the first week, not after a long setup cycle.

Open first mission launch packet Open runtime package Open workspace contract Open governance loop Open first mission pack Open account boundary Open activation readiness Open activation package Open launch checklist Open provisioning schema

Activation package

The activation package makes the first runtime explicit before launch: workspace boundary, governance boundary, first delivery, receipt surface, entitlements, and billing mode.

Profile Executive operator

One bounded runtime profile before broader expansion.

Workspace boundary Odei Operating Workspace · Solo operator

One bounded workspace and one accountable operator lane before rollout.

Governance boundary Approval-first · Review with me first

Activation stays gated until approvals and review rules are explicit.

First delivery A governed operating brief with the real next actions already queued.

The first runtime should return a delivery, not a vague setup confirmation.

Receipt surface Signals, approvals, queued actions, and outcome checks remain attached.

Receipts make the runtime inspectable before autonomy expands.

Included entitlements World Model workspace · Governance profile · First mission queue · Receipt surface

Entitlements activate together as one governed runtime package.

Activation review Runtime scoping → governance review → activation ready

Reviewed provisioning remains the boundary before runtime launch.

Billing mode Invoice me for initial setup

The commercial boundary is explicit before self-serve checkout opens.

Open runtime package Open workspace contract Open governance loop Open activation package Open activation contract Open activation state

Workspace contract

The first runtime should become your system: one bounded World Model, one governance boundary, one replaceable model layer, and one receipt surface that survives across sessions.

Workspace boundary Odei Operating Workspace · Solo operator

One bounded World Model namespace and one accountable operator lane become the first runtime boundary.

World Model Persistent Digital World Model workspace

Memory, people, commitments, and artifacts stay inside the same personal runtime instead of resetting with every model session.

Governance boundary Approval-first · Review with me first

Approvals, action limits, and review rules stay attached to the runtime, not to one provider default.

Model layer Bring your model · Use my subscription workflow

The model layer is replaceable. Switching providers should not require rebuilding the workspace contract.

Receipt surface Signals, approvals, queued actions, and outcome checks remain attached.

Receipts keep the runtime auditable before autonomy expands.

Portability World Model, governance, and receipts stay stable while providers can change.

Execution surfaces expand under review instead of resetting the runtime.

Open workspace contract Open governance loop Open runtime package Open runtime profiles Open activation package

Governance loop

The runtime should not just have governance. It should have a visible Observe → Decide → Act → Verify → Evolve contract that remains stable across sessions.

Loop posture Approval-first · Review with me first

One policy boundary keeps the loop inspectable before autonomy expands.

Observe Email · Calendar · Documents

The first bounded world surfaces define what the runtime monitors.

Decide Priority · Governance · Timing

The runtime applies policy and operator intent before any action is queued.

Act Draft operating brief · Queue follow-ups · Flag approvals

Execution stays bounded by the governance posture, not by model enthusiasm.

Verify Brief delivered · Receipts attached · Approvals surfaced

Outcome checks must attach before the loop compounds into memory.

Evolve Meeting cadence · Follow-up timing · Decision context

The World Model updates timing and context so the next cycle starts sharper.

Open governance loop Open workspace contract Open first mission pack Open activation package

Launch checklist

The launch checklist shows what is already captured, what defines the runtime boundary, and what still requires reviewed provisioning before activation.

Pending input before submit Open runtime package Open launch checklist Open activation package Open first mission launch packet Open first mission pack

Provisioning capsule

The capsule binds the returned intake ID to the exact runtime contract you submitted. Use it as the continuity anchor, then hand the compact activation handoff packet to a human reviewer or another agent.

Intake ID —

Status Intake received

Runtime —

Billing mode —

Next step Runtime scoping and governance review

Activation readiness

Every intake resolves into explicit readiness states for auth, entitlements, billing, and activation. This is the business boundary before runtime launch.

Auth boundary Operator identity captured Verify operator details

Runtime credentials are issued only after reviewed provisioning.

Entitlements Preview only until activation Grant reviewed runtime entitlements

Workspace, governance, and receipt surface activate after review.

Billing boundary Billing readiness captured Review setup scope and runtime plan

Public self-serve checkout remains closed until launch.

Activation Pending reviewed provisioning Runtime scoping → governance review → first mission queue

Self-serve remains closed. Activation follows review and governance confirmation.

Launch checklist

The provisioning capsule should preserve the same operational launch boundary later without guesswork.

Pending reviewed provisioning Open launch checklist

Download capsule Open runtime package Open runtime profiles Open workspace contract Open governance loop Open auth contract Open auth state Open entitlements Open entitlements state Open account boundary Open activation readiness Open activation state Open billing contract Open commercial envelope Open cohort contract Open first mission launch packet Open first mission pack Open activation package Open launch checklist Open schema Open activation contract Review provisioning flow

{}

Resume or reopen a workspace

Open an existing workspace trail

ODEI keeps the continuity anchor internally. Reopen a recent workspace from this device without managing raw intake handles yourself.

Recent workspaces on this device

No active workspaces stored on this device.

Docs, pricing, and support

Need a human thread? Write to ai@odei.ai. Runtime docs, launch status, pricing, and the full contract index stay here.

All launch contracts

Create the agent that remembers, governs, and acts.

Choose your path.

Everyone has the same AI.If your value is prompting - you're competing with everyone.

What this loop actually costs you

AI models are becoming commodities, like electricity or water.The ones who win own the infrastructure.

What your current tools are missing.

A personal agent system you can actually keep using.

Your AI deserveWorld Model and Governance Loop.

Your AI deserves memory and governance.

AI forgets the work.

You glue tools manually.

No safe runtime boundary.

No continuity or proof.

Everyone has the same AI.
If your value is prompting - you're competing with everyone.

AI models are becoming commodities, like electricity or water.
The ones who win own the infrastructure.

Your AI deserve
World Model and Governance Loop.