2ok.ai
OPEN-SOURCE / AGENT GOVERNANCE / EXPERIMENTAL

Agents can propose.Authority lives elsewhere.

2ok is a domain-neutral Rust foundation for making an agent's proposed work reviewable, authorizable and independently enforceable. The resource—not the agent—makes the final decision to act.

Understand the architecture ↗What is actually implemented ↗View source ↗

Early-stage software. Two experimental Rust foundations; no live protected-execution service, authenticated approvals or production security guarantee.

TRUST BOUNDARY / REFERENCE MODELDESIGN / NOT LIVE
  1. 01
    Propose

    An agent drafts an intent and an exact, reviewable change.

  2. 02
    Verify

    Independent evidence is checked against the intended revision.

  3. 03
    Authorize

    A qualified actor and policy grant narrowly scoped permission.

  4. 04
    Enforceindependent authority

    An independent resource verifies permission and produces a receipt.

Separation is a requirement of the proposed system, not a property granted by this website.

INTENT

Agents suggest changes

Not trusted just because a model generated them.

AUTHORITY

Independent systems decide

Approval records and policies cannot replace enforcement.

EVIDENCE

Outcomes must be observed

A trace or simulation alone is never a verified effect.

// components

Composable governance. Explicit trust boundaries.

Implement a small foundation before claiming a complete platform. Status reflects reviewed public work, not unfinished branches.

Full roadmap ↗
01 / MODULEExperimental crate

Identity & delegation

Validated principal records and narrowing delegation scopes; no credential issuer, hosted identity provider or runtime authorization.

02 / MODULEExperimental crate

Evidence & digests

Bounded evidence records, providers and versioned digests; does not establish truth, approval or protected execution.

03 / MODULEPlanned service

Specifications

Immutable reviewed revisions, exact change proposals and versioned contracts. Work outside main does not advance public status.

04 / MODULEPlanned service

Approval & policy

Exact-resource decisions, independent policy and verifiable human approvals. No operational approval service is exposed.

05 / MODULEPlanned service

Protected execution

One-use resource-scoped leases, resource-side re-verification, receipts and uncertain-outcome recovery.

06 / MODULEPlanned service

Review checkpoints

Durable task pause, independent review and safe resume; queuing a task never grants execution authority.

// security and ergonomics

Distinct profiles, explicit authority.

Development / YOLO

Normal local agent edits, builds and tests remain fast. Shadow policy is advisory; unrestricted agents on one host are not contained.

Commissioning / engineer-directed

Time-limited, target-scoped engineer sessions support rapid iteration. Engineer access never automatically delegates credentials to agents.

Managed / production

Independently controlled endpoints own credentials, verify execution leases, reject replay and record receipts. Approval is not functional safety.

// modular deployment

One architecture, three placements.

Proposed deployment patterns, not currently shipped services. Split processes only for an actual trust or operational boundary.

Local Windows + WSL2 + Docker

Proposed APIs, identity, PostgreSQL, policy and workers in containers; native connector where needed. One laptop cannot resist full host compromise.

Customer on-premises

Same interfaces with locally managed identity and audit, independently administered connector host and segmented protected-resource network.

Cloud + on-premises edge

Core governance in the cloud when useful; protected credentials, connectivity and authoritative execution stay behind the customer-controlled edge.

// independently owned core roadmap

Prove one portable end-to-end slice.

No second standalone platform or copied consumer backlog. Start with a synthetic resource and validate strong enforcement at the resource, not the agent prompt.

  1. 01

    Now

    Standalone Rust identity/delegation and evidence slices; explicit publication and boundary tests.

  2. 02

    MVP

    Synthetic proposal → independent verification → exact engineer approval → trusted dummy connector → receipt; reject replay/mismatch/uncertain effects.

  3. 03

    Next

    Immutable specification revisions and small event-backed policy/transaction API, reusing mature policy/identity/storage components.

  4. 04

    Then

    Passkey-backed approval and durable task pause/resume, with authoritative verification outside the agent.

  5. 05

    Proof

    Move connector onto independently managed hardware without changing the versioned protocol.

Core-owned roadmap ↗Proposed service interfaces ↗Public roadmap page ↗
// machine-readable / read-only

Help agents discover the design, not execute it.

7 public, domain-independent topics share one manifest for standalone HTML, Markdown, llms indexes, sitemap and discovery catalog. Compatible browsers may expose optional read-only WebMCP tools for search, capabilities, roadmap, profiles and site map. The website never approves transactions, receives credentials, opens local resources or starts remote execution.

agents · currentFor agents2ok is reusable, domain-independent governance building blocks; a website is not an approval server.architecture · designArchitecture and contract boundariesIntent → Verify → Authorize → Execute → Observe → Record; decision, enforcement and evidence are separate.roadmap · mixedImplementation roadmapImplemented identity/evidence foundations; planned immutable specs, independent policy, approvals, transactions, leases, orchestration.deployment · designDeployment topologiesOne versioned API across laptop, on-prem and cloud/edge placements, with candid trust assumptions.security · designOperating profiles and ergonomicsDevelopment speed, engineer-supervised sessions and managed enforcement are distinct modes.architecture · designInterfaces and reuse decisionsAdopt proven policy, identity and database infrastructure; keep speculative tools behind adapters.status · experimentalCurrent implementation statusExperimental Rust crates and illustrative browser demo; no production authorization or isolated execution.
Agent entry point/for-agents/Machine-oriented Markdown/for-agents.mdCompact index/llms.txtExpanded public context/llms-full.txtDiscovery catalog/.well-known/ai-catalog.jsonHTML site map/sitemap.xml
// build with us

Source first. Claims second.

Inspect the standalone Rust foundations and their tests. Operational APIs, real human approvals and protected execution are future work and require separately controlled infrastructure.

git clone https://github.com/x2ot/2ok.git
cd 2ok
cargo test --workspace
node scripts/check-boundaries.mjs
cd site && npm ci && npm test && npm run build
Open repository ↗Public documentation ↗Implementation status ↗