Skip to content
| Marketplace
Sign in
Visual Studio Code>Machine Learning>NetClawNew to Visual Studio Code? Get it now.
NetClaw

NetClaw

NetClaw

|
48 installs
| (1) | Free
Set up and manage independent NetClaw and Risk installations from Visual Studio Code.
Installation
Launch VS Code Quick Open (Ctrl+P), paste the following command, and press enter.
Copied to clipboard
More Info

NetClaw for Visual Studio Code

Set up a new NetClaw or mixed Risk, or manage your existing NetClaw or Risk, from VS Code. Connect to its running HUD, inspect operations, converse with its configured runtime, search RAG knowledge and review supported settings without leaving your editor.

Version 1.6.1: Generate a single-use enrollment QR from Mobile & edge for your selected compatible installation, then scan it in NetClaw Mobile. The ordinary enrollment flow no longer needs a CLI token command. Requires the enrollment backend in source 1.18.6; see the Mobile enrollment guide and actual qualification.

New in 1.5.0: Optional NetConverter setup selects hosted-readonly or local-Terminal mode with independent private settings and cancellation preservation. Requires source 1.18.0; account capability and exact-file approval remain separate. See the NetConverter guide and qualification evidence.

New in 1.4.0: Choose Static or Dynamic testbeds per claw, with 14 source routes, native source selection, explicit plan review and preserved cancellation/reload. Dynamic setup requires source 1.14.0. Read the dynamic testbed guide and Spec160 verification. Setup configures policy; source access, schema validation, activation and device execution are separate steps.

Patch 1.3.1: Includes the optional MCP-default catalog/resolver in exact setup source review (Spec 156). Use source 1.13.1 for the coordinated minor fixes; see release notes.

New in 1.3.0: Search the OpenClaw and Hermes Comms inventory, choose multiple channels, configure private credentials and access, and discover Twilio/Zoom tools with explicit Focused/member ownership. Requires source setup engine 1.13.0 or later and VS Code 1.109+. Read Comms setup, new-claw setup and release qualification. Existing installations remain independent; installing the extension does not upgrade or activate their runtimes.

NetClaw remains your runtime. Opening the extension changes no runtime. Explicitly reviewed setup actions can install selected isolated MCP runtimes, register canonical OpenClaw MCPs or restart the owned federation service using existing NetClaw helpers.

Connect

Use VS Code 1.109 or later and a trusted workspace. Installing the extension does not install, upgrade or activate an existing runtime.

Local installation

  1. On Windows, first open your intended WSL distribution with VS Code Remote WSL and install this extension in WSL. For another Linux/Mac machine, use your existing Remote SSH workspace.
  2. Start your already-installed NetClaw HUD using its normal supported environment. The initial compatibility baseline is NetClaw 1.8.0, including its installation identity and owned-conversation APIs. The extension does not upgrade NetClaw.
  3. Run NetClaw: Add Connection, choose Local installation, then a friendly nickname such as My Mac lab or WSL NetClaw and enter the HUD API address, normally http://127.0.0.1:3001.
  4. Review the returned installation identity and harness before binding. Loopback belongs to the extension host, so WSL and Remote SSH connect on that host.

Existing Cloud Border

Run NetClaw: Add Connection → Cloud Border, enter a Name, then the operator-provided HTTPS URL. A root URL with or without its trailing slash is accepted. The extension discovers and pins the installation identity; no installation-ID or access-mode prompt is needed. A changed identity at a saved origin is refused, preserving the original profile and operation references.

The backend must advertise the R04a remoteHud schema-1 workspace capability; the source version number alone does not establish compatibility. An explicitly configured open-lab Border connects without sign-in, tickets or user sessions. Its advertised capabilities determine the available panels. A full workspace Border opens the normal Overview and supports Chat, Canvas, RAG, members, peers, skills, runtime, usage, documentation and logs. Protected member operations retain exact native review and approval, signed results, durable acknowledgements and same-reference recovery. Unknown outcomes stay retained and are never automatically replayed.

Use an existing operator-approved lab endpoint. This client release is not a cloud deployment guide and does not implement users, SSO or RBAC. Local workspace files, service lifecycle, environment/MCP configuration, security controls and assistant registration remain local-only. Browser VS Code, native Windows runtime hosting and virtual workspaces remain unsupported. Opening a workspace makes no automatic connection or runtime change.

Workspace files and claw controls

Extension 1.1.0 added Workspace & Claw to the upper Connections panel. Connect to an updated source HUD, choose Workspace & Claw and review the installation, native executable and local helper before enabling controls. The selected host must have the supported HUD Node runtime and this feature’s source helpers; older HUDs need that source update.

  • Open SOUL.md, AGENTS.md, IDENTITY.md, USER.md, TOOLS.md or HEARTBEAT.md in VS Code’s native Markdown editor. Review and save with Cmd+S / Ctrl+S. Normal typing, Undo and dirty-close prompts apply. No delete, rename or move is exposed.
  • Upload / overwrite accepts strict UTF-8 up to 1 MiB, including BOMs, CRLF and intentionally empty files. Select the destination explicitly and review its diff. Missing files are created exclusively. Empty replacement keeps the file present.
  • Save & Restart reviews the exact draft and service scope together. Restart runs only after verified persistence of that same revision. Save alone never restarts a service. Saving and restart outcomes are reported separately.
  • Start / Stop / Restart operate the selected installation’s verified gateway or engine, owned HUD (including its protected Hermes companion), and configured federation services. Stop and restart can interrupt work; the native review says when activity is unknown. The saved host binding keeps Start usable with HUD offline, including after an editor reload. It never selects another installation.
  • Recovery & history shows local operation evidence and private original paths. Restore an original through Upload / overwrite and a fresh review. Refresh / reconcile observes interrupted operations; it never blindly repeats one.

OpenClaw workspaces come from its native agent catalog and must agree with the connected HUD’s launch context. Hermes persona files live directly in its selected home. The protected Hermes HUD engine deliberately does not load those persona files; restarting does not remove this protection. For OpenClaw, session type and heartbeat scheduling determine loading, and an existing conversation may keep its previous context. Saved bytes and service readiness do not prove prompt consumption.

Full lifecycle is enabled only when every configured component has a verifiable owner. New HUD ownership can be established with the existing selected environment:

node scripts/hud-launch.mjs managed --runtime openclaw --home /absolute/runtime/home
# Or --runtime hermes with that installation’s home and preinstalled companion.

This creates no installation, provider setup or service-manager definition. Start requires existing configuration, dependencies and, for Hermes, its private companion credential. Stop the prior foreground HUD using its existing owner before using managed mode; this feature never adopts or kills an unknown listener. Native user services use their exact verified launchd/systemd definitions. Opaque launchers, ambiguous ownership, unqualified Hermes native messaging gateways and unsupported service definitions leave full controls unavailable, with a reason. Existing owned standalone federation uses its installation-scoped helper; supervised federation must use its verified manager. No process-name or port-wide termination is used.

Coordinate external file writers: private locking, revision checks, recovery copies and final readback protect the managed workflow, but ordinary filesystem rename is not a universal compare-and-swap against an uncooperative external writer. Changing the helper, target workspace or installation identity requires a new binding/review. After switching targets, stale documents retain their drafts but must be reopened for the newly selected binding before saving.

Qualification and the isolated preview are recorded in Spec152 verification. Mac fixture acceptance does not claim provider execution or Linux/WSL/Remote live qualification. WSL verified actual regular-file reads and native editing/Undo; symlink files remain refused. Full live WSL lifecycle is not claimed. Use source release 1.11.0 or later for the matching HUD/helper, and see release verification.

Workbench

Spec151 adds a shared card layout, persistent form labels and contextual help, while retaining blue actions, search and pagination. Pages automatically follow light, dark and high-contrast editor themes. The locally bundled artwork is decorative; BGP's interactive 3D view uses reported sessions and has an independent readable list. It does not depict physical cabling or infer device health.

  • Chat: a private extension-owned conversation, explicit context selection, supported model/effort choices, owned history and runtime-specific request status.
  • Canvas: local saved investigations, branching context and reviewed HUD Canvas v1 import/export. Each lane uses an owned NetClaw conversation.
  • Avatar: bundled local John/NetClaw characters alongside the same Chat. Character controls are local; voice and hosted video are not included.
  • RAG: collection/document/snapshot/replica inventory, cited search, staleness notices, reviewed context selection and selected-file uploads up to 10 MiB. Upload acceptance is pending, not proof of indexing. Refresh to verify the result. An upload uses its filename as the title and may replace an existing same-title document. Controls wait for an active knowledge operation or review to finish; submissions are never queued or replayed automatically.
  • Operations: tokenomics, budget, federation GAIT audit, logs and Terminal Intent.
  • Risk and federation: existing standalone/Risk, iN2N, eN2N peers, BGP topology, configured devices, mobile/edge and Science Officer observations.
  • Integrations: provider/harness, masked environment inventory, installed MCP integrations and skills. Review individual environment replacements and budget changes in native dialogs. Existing NetClaw validation and enforcement apply.
  • Security: native DefenseClaw tool rules, OpenShell network ACLs, permissions, redacted policy YAML and reviewed supported edits.
  • Help: installed documentation and CLI/API reference.

Panels show their source and observation time. Missing or stopped optional services can report unavailable; no healthy state is inferred. GAIT is the federation audit projection exposed by the HUD, not unrestricted access to every historical session. Memory, GCF and meeting actions stage an investigation for your explicit Chat send; they do not start listeners or claim access to unavailable tools.

Prepare Existing Service Command checks the selected runtime home's identity, then previews existing NetClaw HUD/federation lifecycle commands. It can stage the reviewed command in a terminal without pressing Enter. Execute it yourself and inspect the actual result. It does not install or replace lifecycle control. External Peer Conversations and Terminal Intent invoke their existing backend workflows after native human review. The extension does not establish peering, change peer permissions, approve device changes or create Local/Lab exemptions.

Testbed inventory

Testbed inventory opens device cards, guided create/update/remove forms and Advanced YAML. Both modes keep unsaved drafts in memory while changing tabs or themes. Switching modes offers keep/discard/cancel. Closing the view discards drafts; changing installation clears sensitive contents. Every save has a read-only preview and a native review with the actual destination, additions, changes and removals.

The destination is the HUD-configured testbed, which may be shared with another installation and may differ from a running pyATS MCP's PYATS_TESTBED_PATH. Saving does not synchronize another file or connect devices. Structural validation does not run the pyATS loader or resolve extends, classes or ENV references.

  • YAML (.yaml/.yml) and JSON support explicit replacement or device merge with error/skip/replace conflict choices. A merge refuses different top-level defaults/topology rather than dropping them.
  • CSV supports id,alias,type,os,platform,connection,protocol,host,port. Rows are unique by (id,connection); repeated device metadata must agree. Omitted columns preserve existing values. Blank optional metadata clears it; a blank port leaves it unchanged. New devices need OS and a named connection with host/protocol. CSV never deletes unseen devices or replaces advanced fields.
  • YAML exports can preserve exact source; JSON preserves data without comments/anchors. CSV excludes advanced fields and credentials and prefixes formula-leading cells for spreadsheet safety. Use YAML/JSON for full fidelity.
  • Export uses a native destination and explicit redacted/include-credentials choice. Redacted copies are not complete backups. Files are written with owner-only permissions.
  • Existing credential literals use path-bound keep tokens in the editor; ENV references remain intact. Reviews show credential change intent, never values. New literal drafts are not saved to editor state.
  • Stale revisions and changed previews are refused. Saves retain private copies under <testbed>.backups/; Recovery copies previews a fresh reviewed restoration. Source limit256KiB; masked editor limit512KiB. Ambiguous alias edits are refused rather than modifying unrelated data.
  • Affected active terminals must disconnect before editing. A save revokes affected collection consent and cached logins; it never grants new access. A failure after revocation may require deliberate reauthorization after inspecting the file.

Older running HUDs still show searchable device details from their inventory API. Full editing, import and export become available after the updated HUD is started and the page is reloaded. The extension never uses the legacy raw testbed writer.

MCP configuration and setup

Each known integration card opens Configure & set up. Fields are scoped to that integration and show presence, requirement/help and shared use. Existing values remain private. Keep current value is the default; Replace and Clear are explicit. Unknown metadata remains confidential with an honest requirement limitation. Saving checks the file revision and verifies submitted values privately; it does not imply loaded runtime settings or endpoint access.

On older running HUDs, configuration cards show field presence and Review an environment setting opens the existing native review for one selected field. Full scoped forms and setup actions become available after starting the updated HUD.

Installation & service actions verifies an explicitly selected checkout and existing runtime home against the connected installation. Native review shows the host, runtime, identity, files, command, interruption and recovery impact before execution:

Action Scope
Install isolated runtime Existing staged pyATS/GAIT helpers; prerequisites must already exist; downloads may occur; displaced generations retained
Register canonical MCP OpenClaw only; known public catalog component, prerequisites and expected configuration revision; custom launch conflicts refused; unrelated entries preserved
Restart federation service N2N only; existing owned daemon/runtime; interrupts peer work, checks PID ownership and verifies new PID/readiness
Prepare installer command Existing install.sh --add with its broader prerequisite/runtime/onboarding/config/skills/readiness effects disclosed; staged without Enter

Other lifecycle actions show guidance. Stdio MCPs are runtime-owned; there is no generic per-MCP restart. Hermes registration remains native review because its existing converter can produce only a sidecar. The protected Hermes HUD bridge is excluded from ordinary registration.

Setup evidence and baselines stay under the selected home's netclaw-hud/setup/ with private permissions. Child output is not copied into the UI. Unknown/interrupted operations never replay; inspect the recorded operation and helper recovery state before explicitly resolving a retained lock/evidence record. Closing a card does not cancel a launched helper. Install, registration, runtime loading and endpoint verification are separate outcomes.

Security perimeter controls

Open Manage DefenseClaw Security or Manage OpenShell Security. Choose the existing CLI and security profile on the extension host, plus the matching NetClaw runtime home. The matching local runtime home and single configured gateway are suggested when verified. OpenShell lists existing sandboxes for selection; versions without workspace selection use the default workspace. The binding dialog explains that this security perimeter may protect other agents.

  • DefenseClaw: searchable tool allow/block rules, connector and global scopes, asset permissions and redacted configuration YAML. Version 0.8.4 uses native tool allow/block/unblock --connector commands and verifies database-backed rules through CLI readback. Global fallback, audit-only source rows and enforcement defaults are view-only on that version. A CLI with revision-aware config writes can also edit the supported global defaults. Connector overrides can supersede global defaults.
  • OpenShell: named network-rule cards, a guided REST endpoint rule and advanced network_policies JSON for supported endpoint and layer7 allow/deny policies. Filesystem/process settings are preserved. A sandbox form cannot change a gateway-global policy. Removing one allow does not prove every route to a destination is blocked.
  • Permissions and YAML: inspect configured filesystem/process access, asset permissions and redacted policy YAML. YAML is an inspection copy; edits use the supported reviewed forms. Large structures may be shortened.
  • Status and logs: observed status, configured policy and bounded redacted alert/log snapshots with search. Refresh explicitly. Saved settings, a loaded policy and tested traffic enforcement are separate results.
  • Review and recovery: inspect a redacted before/after summary, provide a reason and confirm in a native dialog. Permission expansion or uncertain direction requires Acknowledge weakening & apply. Private originals and operation evidence remain in the editor's security-operations storage. Interrupted/unknown outcomes block another apply until the operator inspects and resolves that evidence; there is no automatic retry or rollback.

Capability probes determine whether editing is available. DefenseClaw requires a matching reported profile and either connector-scoped native tool commands or a revision-aware config writer. OpenShell 0.0.32 uses native YAML policy reads, explicitly checks for gateway-global policy and waits for an acknowledged policy revision after a change. Modern full/base JSON readers remain supported. Network drafts are limited to 128 KiB; unsupported or oversized policies remain view-only. Native tool and OpenShell policy commands have no atomic revision precondition: this client rechecks before applying, but another editor or external writer can race. Coordinate policy changes with other operators.

These controls do not install, start, stop or disable a security service. WSL qualification includes real DefenseClaw 0.8.4 connector rule changes in an isolated profile and OpenShell 0.0.32 policy changes with denied/allowed/denied traffic in a temporary Docker-backed sandbox. Your other security targets are not changed by those tests. See production readiness for evidence and remaining release gates; this does not certify every connector or network path.

Copilot, Claude Code and Codex

Run NetClaw: Manage Copilot, Claude Code and Codex Access after connecting. Choose inspection/proposals, or explicitly enable delegation as well.

Copilot discovers the extension's stdio MCP server through VS Code. Start it through MCP: List Servers, review its tools and use Copilot Agent mode. VS Code and your organization's policy still govern MCP consent and model access.

Claude Code and Codex setup opens an exact command preview for that host. Run the reviewed command in a terminal with Node 22 or later and your authenticated client. Other MCP registrations are preserved. Re-run setup after an extension update if its installation path changes. Interactive clients may require per-call consent.

Tool Behavior
netclaw_status Inspect the bound installation and delegation setting
netclaw_inspect Read allowlisted, bounded domain summaries
netclaw_propose_change Save an inert local draft for human review
netclaw_request Delegate a prompt to existing NetClaw after opt-in
netclaw_request_status Observe that registration's existing request

Example: “Inspect NetClaw's runtime and propose a smaller budget. Do not apply it.” With delegation enabled: “Ask my NetClaw to explain its installed integrations.”

The adapter exposes no approval, direct apply, arbitrary HTTP, raw backend MCP or shell tool. Delegation can invoke NetClaw's tools under its existing authorization and approval rules; it is not enforced read-only execution. This adapter is not an OS sandbox for a terminal assistant that already has same-user filesystem access. Disable a registration through the extension to refuse subsequent calls. Already submitted backend work may continue. Assistant model costs are separate from NetClaw provider usage.

Recovery and data

An identity change invalidates the connection; reconnect and review the target. An interrupted send is never automatically replayed. Hermes supports owned request status and stop requests. The OpenClaw HUD has no corresponding request-status or stop API: review owned history and running NetClaw before starting separate work. Opening older history does not certify an unresolved request's completion. Closing, disabling or uninstalling the extension does not cancel runtime work.

Profiles, saved conversations, Canvas investigations and assistant drafts live in extension storage on the execution host. Cookies use VS Code SecretStorage; terminal MCP adapters maintain their own private local session files. No browser cookie is copied. Draft retention is opt-in. Uninstall preserves NetClaw, its credentials, configuration and services; extension local state may remain according to VS Code's storage behavior. See Privacy.

Development and qualification

From this directory, use npm ci, npm run check, npm run build, npm test. Backend integration tests require the HUD dependencies (npm --prefix ../../ui/netclaw-visual ci). Spec151 adds bounded testbed and configuration routes to the existing HUD. Older HUDs retain device/configuration inventory and a reviewed native environment-setting flow when the new editing routes are unavailable; there is no fallback to the legacy raw testbed writer. npm run test:editor launches an isolated desktop extension test. RAG and named assistant live checks are explicit opt-ins documented in Spec150 evidence.

npm run package requires a clean committed checkout, checks that every runtime bundle and license notice is included, and records source and VSIX digest in out/package.json. Install from the Visual Studio Marketplace. Version 1.6.1 adds Mobile QR enrollment and retains the Cloud Border workspace, optional NetConverter setup, dynamic testbeds, guided Comms, reviewed new-claw setup and existing local controls. After updating, activate the installed code through Developer: Restart Extension Host when it is safe to interrupt extension work; an installed version label does not establish which code the current host is running.

R04a live qualification used frozen private 1.5.0 builds in the owner's macOS VS Code 1.109 with OpenClaw/Sonnet 4.6. It exercised Name + URL connection, stable profile selection, normal panels, Chat, cited RAG/Canvas, a protected NetBox read and recovery with unchanged execution counts. Native file-picker automation did not complete selection; the approved synthetic upload used the production client, followed by native search, context staging and Canvas. Final recovery displayed the same signed result and acknowledgement after an extension-host restart; the initiating picker click was not captured and the GET path is source-derived, not a packet trace. The release artifact receives source/build/package checks; the evidence does not claim another live rollout of the final merged source.

Windows/Linux cloud editors, other cloud providers/harnesses and general deployment are not qualified by this Mac result. That R04a evidence does not qualify Mobile QR enrollment; separate actual QR and native simulator evidence is in Spec175. Physical-device qualification remains open. See R04a verification. Earlier local feature limits remain in Spec151 production readiness and the linked setup and lifecycle verification records above.

  • Contact us
  • Jobs
  • Privacy
  • Manage cookies
  • Terms of use
  • Trademarks
  • Your Privacy Choices
  • Consumer Health Privacy
© 2026 Microsoft