01 / hostOpenClaw agents and gateway
Coding, research, marketing, and operations agents keep their existing tools, workspaces, and runtime lifecycle.
OpenClaw gateway · agent workspacesOrgX for OpenClaw00
OrgX for OpenClaw
Persistent organizational memory and coordinated execution inside OpenClaw.
OrgX Live inside the OpenClaw operating loop
Named agents, current work, blocked decisions, activity, and next-up actions remain visible in one live control surface.
This is not OpenClaw itself and not another standalone dashboard. It is the OrgX bridge that lets OpenClaw agents enter shared organizational context, coordinate work, and return evidence without leaving the host environment.
ProductOrgX plugin
HostOpenClaw
Continuitypersistent state
Controllive + resumable
01
The consequential problem
The host already had agents; it lacked organizational continuity
A capable local agent can still wake up without the company in its head.
OpenClaw could run agents and tools, but long-running organizational work needed more than a session. Tasks had to survive restarts, handoffs, and changing operators without becoming a pile of local state and logs.
Asking people to leave the host for a separate orchestration product would have added adoption friction at exactly the wrong boundary.
- Session state was not the same thing as organizational memory.
- Realtime activity could not be allowed to outrun durable state.
- A separate destination would fracture the operator's workflow.
02
What I saw
The plugin boundary was the product opportunity
Bring the organization into the host instead of moving the operator out of it.
The right architecture inherits OpenClaw's environment and lifecycle, then adds OrgX where the host is intentionally thin: shared context, resumable coordination, trust state, decisions, and receipts.
That makes the integration feel native while keeping the organizational model portable across the rest of the OrgX client ecosystem.
03
The decision that changed the system
One local bridge; durable work on the other side
Treat live transport as a view of state—not the source of truth.
The plugin coordinates through an MCP bridge, persistent queue state, and a live surface. Streaming keeps the interface current; durable records keep it honest when the stream disconnects, the host restarts, or work resumes later.
01Org context
The initiative, constraints, and prior decisions enter OpenClaw together.
02Host execution
OpenClaw agents act through the plugin's coordinated tool surface.
03Durable boundary
Queue state and decisions survive the live connection.
04OrgX receipt
Outcomes return to the shared work graph with provenance.
04
System anatomy / rationale / surfaces
Host-native architecture
A local bridge, durable recovery path, and live control surface—without replacing OpenClaw.
The plugin has to respect two truths at once: OpenClaw owns the agent runtime, while OrgX owns the shared organizational context. The bridge is designed so either side can restart without making live transport the source of truth.
Decision anatomy / select a knot
Pressure did not decorate the architecture. It determined it.
Before / tension
Moving an OpenClaw operator into a second orchestration destination would fracture the workflow the plugin is meant to improve.
The knot / decision
Let OpenClaw own the runtime and tools while OrgX adds the missing organizational context through one native plugin seam.
After / consequence
Agents keep the host's strengths and gain shared goals, decisions, trust state, and receipts where they already work.
02 / plugin bootstrapRegister one host-native integration
A strict TypeScript ES module registers tools, services, dashboard routes, and background behavior through the host's single plugin entry point.
TypeScript · Node 18+ · native fetch03 / local protocolExpose the work graph through MCP
The local bridge at /orgx/mcp gives OpenClaw, Claude, Cursor, and Codex structured access without forcing a second cloud OAuth flow.
MCP tools · structured JSON · client config backups04 / durable edgeBuffer what the network cannot guarantee
SQLite stores run records, snapshots, and a local outbox. Queued events replay after sync; legacy JSON import and dead-letter records preserve a recovery path.
SQLite · JSON migration · outbox replay05 / live projectionStream the view; recover from the snapshot
SSE is the primary live transport, with polling against the canonical snapshot as a fallback. Next Up intent stays separate from In Progress runtime state.
SSE · snapshot fallback · React hooks06 / shared graphReturn work to OrgX
Initiatives, workstreams, milestones, tasks, decisions, activity, and receipts become shared context for every future agent and client.
OrgX API · entity graph · receipt modelArchitecture rationale / pressure → choice → consequence
PressureDecisionWhy it mattered
The plugin runs inside many local environmentsUse the host's Node runtime with explicit dependency recovery
Native fetch handles transport, while the SQLite store includes repair handling for missing native bindings.
Concurrent work needs durable local stateUse SQLite with WAL and import earlier JSON records
Indexed run, snapshot, and outbox tables keep recovery state together while preserving a migration path for existing installations.
Realtime connections failSSE-first with canonical snapshot fallback
The interface can recover its operating picture without presenting the stream as durable truth.
Queued intent is not active executionSeparate Next Up from In Progress
Operators can distinguish scheduling, runtime state, blockers, and recovery instead of reading one ambiguous activity feed.
Surface atlas
The system becomes tangible through the places people encounter and use it.
Connect + pairing
Browser pairing and manual key fallback establish the boundary without exposing credentials in the interface.
Mission Control
Initiative → workstream → milestone → task state makes the shared plan visible inside the host.
Next Up queue
Pin, reorder, move, and bulk controls express scheduling before a run begins.
Activity + handoffs
Live updates, decisions, completion, and failure stay attributable to named work.
Triage
Blocked and needs-review items become a focused operator queue rather than background noise.
Session detail
Pause, resume, cancel, checkpoint, and rollback make long-running agent work recoverable.
Core
TypeScript strict mode · ES modules · Node 18+ · native fetch
Dashboard
React 18 · Vite · Tailwind · Framer Motion
Protocol + transport
MCP · SSE · HTTP · snapshot polling
Durability
SQLite / better-sqlite3 · JSON migration · local outbox · automatic replay
Verification
node:test · Playwright · strict typecheck · end-to-end harness
Technology atlas / select a tool
The tools behind the decisions.
Select a tool to see the role it plays in this system.
- Host / OrgX plugin
OpenClaw
The host retains agent runtime, workspaces, tools, and lifecycle; the plugin adds the organizational layer instead of replacing it.
05
Authentic proof
Mission control
The next action remains explicit even when multiple workstreams are active or degraded.
Activity with consequence
Completion, failure, and intervention remain attached to named work instead of collapsing into a terminal feed.
06
What changed in my operating model
Integration quality is product quality
The best orchestration surface is sometimes the one the operator does not have to adopt.
OrgX for OpenClaw sharpened a rule I now use across the platform: preserve the host's strengths, add only the missing control layer, and keep durable truth independent from live transport.
- Do not confuse the OpenClaw host with the OrgX plugin.
- Let streams update the view; let durable state govern recovery.
- Make continuity portable without making every client identical.