A surface is a product area such as Gateway runtime, Discord, or the macOS app. Each surface contains categories, and each category contains the capability-level checks that QA scenarios cover. Use the scorecard for release-level judgment; use this page to inspect the model underneath it.
M0PlannedDirection is known, but no supported user path exists.Promotion: Design issue, owner, and target surface exist.
M1ExperimentalImplemented behind caveats, flags, source builds, or maintainer-only flows.Promotion: Maintainer can run the scenario from current main.
M2AlphaReal users can try it, but breaking changes and incomplete UX are expected.Promotion: Documented setup, basic tests, known caveats, and at least one real-environment proof.
M3BetaPublic path exists and the main workflow is usable with bounded caveats.Promotion: Install/update docs, regression tests, support runbook, and successful scenario proof across the expected environment.
M4StableRecommended path for normal users. Failures are treated as regressions.Promotion: Release gate, doctor/troubleshooting path, broad docs, and repeated real-world proof.
M5ClawesomePolished, delightful, well-instrumented, and competitive with the best comparable workflow.Promotion: Stable plus user scorecard pass across representative users.
CLI - M4 Stable - 7 areas
Normal setup and repair paths are documented across install, CLI, and gateway docs. Platform-specific Windows paths are tracked in the Windows via WSL2 and Native Windows rows.
Coverage Experimental - 4%Quality Stable - 83%Completeness Stable - 90%Partial - 6
CLI Setup
6 capabilities / LTS-supported
Experimental17%
Stable89%
Stable90%
Onboarding and Auth Setup
5 capabilities / LTS-supported
Experimental0%
Beta75%
Stable89%
Plugin and Channel Setup
5 capabilities
Experimental0%
Beta75%
Stable89%
Gateway Service Management
5 capabilities / LTS-supported
Experimental14%
Stable87%
Stable90%
CLI Observability
5 capabilities / LTS-supported
Experimental0%
Stable89%
Stable90%
Doctor
10 capabilities / LTS-supported
Experimental0%
Stable89%
Stable90%
Updates and Upgrades
5 capabilities / LTS-supported
Experimental0%
Beta75%
Stable89%
Gateway runtime - M4 Stable - 13 areas
Core architecture, auth, pairing, protocol docs, daemon docs, and CLI runbooks are broad and current.
Coverage Experimental - 6%Quality Stable - 81%Completeness Stable - 89%Partial - 12
Approvals and Remote Execution
6 capabilities / LTS-supported
Experimental0%
Beta75%
Stable89%
HTTP APIs
4 capabilities / LTS-supported
Experimental25%
Stable90%
Stable90%
Hosted Web Surface
4 capabilities / LTS-supported
Experimental0%
Stable89%
Stable90%
Gateway RPC APIs and Events
20 capabilities / LTS-supported
Experimental9%
Stable90%
Stable90%
Device Auth and Pairing
10 capabilities / LTS-supported
Experimental0%
Beta75%
Stable89%
Network Access and Discovery
6 capabilities / LTS-supported
Experimental0%
Beta75%
Stable89%
Nodes and Remote Capabilities
8 capabilities
Experimental0%
Beta75%
Stable89%
Health, Diagnostics, and Repair
7 capabilities / LTS-supported
Experimental0%
Beta75%
Stable89%
Protocol Compatibility
7 capabilities / LTS-supported
Experimental0%
Beta75%
Stable89%
Roles and Permissions
5 capabilities / LTS-supported
Experimental0%
Beta75%
Stable89%
Gateway Lifecycle
7 capabilities / LTS-supported
Experimental33%
Stable90%
Stable90%
Security Controls
6 capabilities / LTS-supported
Experimental0%
Beta75%
Stable89%
WebSocket Connection
8 capabilities / LTS-supported
Experimental13%
Stable90%
Stable90%
Agent Runtime - M3 Beta - 9 areas
Main loop, models, provider routing, and tool streaming are first-class, but provider behavior shifts weekly and needs scenario proof per release.
Coverage Experimental - 33%Quality Beta - 78%Completeness Beta - 79%Partial - 6
Agent Turn Execution
3 capabilities / LTS-supported
Experimental29%
Beta79%
Beta79%
External Runtimes and Subagents
4 capabilities
Experimental30%
Beta79%
Beta79%
Hosted Provider Execution
5 capabilities / LTS-supported
Experimental20%
Beta79%
Beta79%
Local and Self-hosted Providers
5 capabilities
Experimental0%
Alpha68%
Beta79%
Model and Runtime Selection
4 capabilities / LTS-supported
Experimental25%
Beta79%
Beta79%
Provider Auth
10 capabilities / LTS-supported
Experimental24%
Beta79%
Beta79%
Streaming and Progress
2 capabilities
Alpha56%
Beta79%
Beta79%
Tool Calls and Response Handling
3 capabilities / LTS-supported
Alpha65%
Beta79%
Beta79%
Tool Execution Controls
6 capabilities / LTS-supported
Alpha50%
Beta79%
Beta79%
Session, memory, and context engine - M3 Beta - 9 areas
Strong docs and active implementation. Maturity depends on transcript durability, compaction quality, and cross-client parity.
Coverage Experimental - 30%Quality Beta - 77%Completeness Beta - 79%Partial - 6
CLI Session and Transcript Management
2 capabilities / LTS-supported
Experimental0%
Alpha68%
Beta79%
Token Management
3 capabilities / LTS-supported
Experimental20%
Beta79%
Beta79%
Context Engine
2 capabilities / LTS-supported
Alpha57%
Beta79%
Beta79%
Cross-client History and Session Parity
2 capabilities
Experimental40%
Beta79%
Beta79%
Diagnostics, Maintenance, and Recovery
3 capabilities
Experimental40%
Beta79%
Beta79%
Core Prompts and Context
2 capabilities / LTS-supported
Experimental38%
Beta79%
Beta79%
Memory
5 capabilities
Experimental46%
Beta79%
Beta79%
Session Routing
2 capabilities / LTS-supported
Experimental25%
Beta79%
Beta79%
Transcript Persistence
2 capabilities / LTS-supported
Experimental0%
Alpha68%
Beta79%
Channel framework - M3 Beta - 8 areas
Many channels share Gateway delivery and routing contracts, but channel behavior varies by upstream API and account-policy constraints.
Coverage Experimental - 13%Quality Beta - 76%Completeness Beta - 79%Partial - 5
Channel Actions Commands and Approvals
5 capabilities
Experimental0%
Beta79%
Beta79%
Channel Setup
5 capabilities / LTS-supported
Experimental14%
Beta79%
Beta79%
Group Thread and Ambient Room Behavior
5 capabilities
Experimental36%
Beta79%
Beta79%
Inbound Access and Identity Gates
5 capabilities / LTS-supported
Experimental0%
Alpha68%
Beta79%
Media Attachments and Rich Channel Data
4 capabilities
Experimental0%
Alpha68%
Beta79%
Outbound Delivery and Reply Pipeline
4 capabilities / LTS-supported
Experimental38%
Beta79%
Beta79%
Conversation Routing and Delivery
10 capabilities / LTS-supported
Experimental19%
Beta79%
Beta79%
Status Health and Operator Controls
4 capabilities / LTS-supported
Experimental0%
Beta79%
Beta79%
Observability - M3 Beta - 5 areas
OTel, Prometheus, logging, and diagnostics docs exist. Needs a public "what operators should look at first" maturity pass.
Coverage Experimental - 18%Quality Beta - 75%Completeness Beta - 79%Partial - 3
Health and Repair
12 capabilities / LTS-supported
Experimental28%
Beta79%
Beta79%
Logging
5 capabilities / LTS-supported
Experimental0%
Alpha68%
Beta79%
Diagnostic Collection
8 capabilities
Experimental30%
Beta79%
Beta79%
Telemetry Export
13 capabilities
Experimental33%
Beta79%
Beta79%
Session Diagnostics
4 capabilities / LTS-supported
Experimental0%
Alpha68%
Beta79%
Gateway Web App - M3 Beta - 6 areas
Web UI is documented with pairing, chat, PWA, Talk, push, and remote Gateway flows. Promote after cross-browser and mobile-PWA scorecards.
Coverage Experimental - 4%Quality Beta - 74%Completeness Beta - 79%None
Browser Realtime Talk
5 capabilities
Experimental0%
Alpha68%
Beta79%
Browser Access and Trust
5 capabilities
Experimental0%
Alpha68%
Beta79%
Configuration
5 capabilities
Experimental0%
Alpha68%
Beta79%
Browser UI
10 capabilities
Experimental8%
Beta79%
Beta79%
WebChat Conversations
15 capabilities
Experimental10%
Beta79%
Beta79%
Operator Console
10 capabilities
Experimental8%
Beta79%
Beta79%
Plugins - M3 Beta - 9 areas
Broad docs and strong internal runtime evidence exist across manifests, discovery, loading, provider/tool architecture, and approval boundaries. Keep the row at beta until public SDK API/subpaths and external distribution proof are stronger.
Coverage Experimental - 12%Quality Beta - 72%Completeness Beta - 79%Partial - 7
Authoring and Packaging plugins
8 capabilities / LTS-supported
Experimental0%
Alpha68%
Beta79%
Bundled plugins
5 capabilities / LTS-supported
Experimental0%
Alpha68%
Beta79%
Canvas plugin
6 capabilities
Experimental0%
Alpha68%
Beta79%
Installing and running plugins
6 capabilities / LTS-supported
Experimental35%
Beta79%
Beta79%
Channel plugins
5 capabilities / LTS-supported
Experimental0%
Alpha68%
Beta79%
Provider and tool plugins
6 capabilities / LTS-supported
Experimental43%
Beta79%
Beta79%
Plugin approvals
6 capabilities / LTS-supported
Experimental0%
Alpha68%
Beta79%
Publishing plugins
6 capabilities / LTS-supported
Experimental0%
Alpha68%
Beta79%
Testing plugins
6 capabilities
Experimental27%
Beta79%
Beta79%
Security, auth, pairing, and secrets - M3 Beta - 6 areas
Good docs and hardening surfaces exist. Promote after regular upgrade/security scenario runs prove no setup regressions.
Coverage Experimental - 16%Quality Beta - 72%Completeness Beta - 79%Partial - 5
Approval Policy and Tool Safeguards
2 capabilities / LTS-supported
Alpha50%
Beta79%
Beta79%
Gateway Auth and Remote Access
9 capabilities / LTS-supported
Experimental0%
Alpha68%
Beta79%
Index,
Exposure Runbook,
Trusted Proxy Auth,
Tailscale,
Remote,
Configuration Reference,
Gateway,
Doctor,
Control Ui,
Browser Control,
Audit Checks
Channel Access Control
3 capabilities / LTS-supported
Experimental0%
Alpha68%
Beta79%
Device and Node Pairing
11 capabilities / LTS-supported
Experimental0%
Alpha68%
Beta79%
Plugin Trust
2 capabilities
Experimental0%
Alpha68%
Beta79%
Credential and Secret Hygiene
5 capabilities / LTS-supported
Experimental46%
Beta79%
Beta79%
Automation: cron, hooks, tasks, polling - M3 Beta - 6 areas
Documented and usable, but scenario proof should cover unattended delivery, retries, and failure visibility.
Coverage Experimental - 2%Quality Beta - 72%Completeness Beta - 79%None
Cron Jobs
15 capabilities
Experimental0%
Beta79%
Beta79%
Event Ingress
15 capabilities
Experimental0%
Alpha68%
Beta79%
Automation Hooks
11 capabilities
Experimental0%
Alpha68%
Beta79%
Background Tasks and Flows
10 capabilities
Experimental0%
Alpha68%
Beta79%
Heartbeat
5 capabilities
Experimental14%
Beta79%
Beta79%
Polling Controls
10 capabilities
Experimental0%
Alpha68%
Beta79%
Media understanding and media generation - M2 Alpha - 6 areas
Broad capability surface exists, but provider variance, file limits, and node/app parity make this not stable yet.
Coverage Experimental - 2%Quality Alpha - 64%Completeness Alpha - 68%None
Media Intake and Access
8 capabilities
Experimental0%
Alpha61%
Alpha68%
Channel Media Handling
5 capabilities
Experimental0%
Alpha61%
Alpha68%
Media Configuration
1 capabilities
Experimental0%
Alpha61%
Alpha68%
Text-to-Speech Delivery
2 capabilities
Experimental0%
Alpha61%
Alpha68%
Media Understanding
12 capabilities
Experimental7%
Alpha69%
Alpha69%
Media Generation
17 capabilities
Experimental5%
Alpha69%
Alpha69%
Voice and realtime talk - M2 Alpha - 6 areas
Multiple implementations exist across Control UI, apps, and providers. Needs latency, failure-mode, and setup scorecards before beta.
Coverage Experimental - 0%Quality Alpha - 61%Completeness Alpha - 68%None
Talk Providers
7 capabilities
Experimental0%
Alpha61%
Alpha68%
Realtime Talk Sessions
11 capabilities
Experimental0%
Alpha61%
Alpha68%
Speech and Transcription
5 capabilities
Experimental0%
Alpha61%
Alpha68%
Native App Talk
4 capabilities
Experimental0%
Alpha61%
Alpha68%
Voice Wake and Routing
4 capabilities
Experimental0%
Alpha61%
Alpha68%
Talk Observability
5 capabilities
Experimental0%
Alpha61%
Alpha68%
TUI - M2 Alpha - 5 areas
Present in docs and source, but less visible as a primary user workflow. Needs explicit scenario definition.
Coverage Experimental - 0%Quality Alpha - 59%Completeness Alpha - 66%None
Runtime Modes
14 capabilities
Experimental0%
Alpha59%
Alpha66%
Input and Commands
8 capabilities
Experimental0%
Alpha59%
Alpha66%
Session Management
3 capabilities
Experimental0%
Alpha59%
Alpha66%
Local Shell Execution
4 capabilities
Experimental0%
Alpha59%
Alpha66%
Rendering and Output Safety
4 capabilities
Experimental0%
Alpha59%
Alpha66%
ClawHub - M2 Alpha - 4 areas
Public docs and ecosystem concept exist. Needs install, trust, update, rollback, and compatibility scorecards.
Coverage Experimental - 0%Quality Alpha - 58%Completeness Alpha - 62%None
Publishing
7 capabilities
Experimental0%
Alpha54%
Alpha55%
Catalog Discovery
5 capabilities
Experimental0%
Alpha61%
Alpha68%
Compatibility and Trust
12 capabilities
Experimental0%
Alpha55%
Alpha56%
Plugin Lifecycle and Health
26 capabilities
Experimental0%
Alpha61%
Alpha68%
OpenClaw App SDK - M2 Alpha - 6 areas
OpenClaw App SDK is a distinct external app contract separate from Gateway runtime and Plugin SDK. Current scoring shows a real @openclaw/sdk path with gaps around public packaging, auto-discovery, approvals, helpers, and compatibility.
Coverage Experimental - 3%Quality Alpha - 54%Completeness Alpha - 53%None
Client API
4 capabilities
Experimental0%
Alpha51%
Alpha50%
Gateway Access
5 capabilities
Experimental0%
Alpha53%
Alpha54%
Agent Conversations
6 capabilities
Experimental0%
Alpha52%
Alpha52%
Events and Approvals
5 capabilities
Experimental0%
Alpha52%
Alpha52%
Resource Helpers
5 capabilities
Experimental17%
Alpha62%
Alpha53%
Compatibility
5 capabilities
Experimental0%
Alpha54%
Alpha55%
Linux Gateway host - M4 Stable - 5 areas
Node runtime is recommended, systemd user service is documented, and VPS/container guidance is broad.
Coverage Experimental - 0%Quality Beta - 75%Completeness Stable - 89%Partial - 4
Host Setup and Updates
4 capabilities / LTS-supported
Experimental0%
Beta75%
Stable89%
Gateway Runtime and Service Control
6 capabilities / LTS-supported
Experimental0%
Beta75%
Stable89%
Remote Access and Security
6 capabilities / LTS-supported
Experimental0%
Beta75%
Stable89%
Diagnostics and Repair
4 capabilities / LTS-supported
Experimental0%
Beta75%
Stable89%
Deployment Targets
3 capabilities
Experimental0%
Beta75%
Stable89%
macOS Gateway host - M4 Stable - 7 areas
LaunchAgent service path, local/remote Gateway modes, CLI install, and app integration are documented.
Coverage Experimental - 0%Quality Beta - 74%Completeness Stable - 88%None
CLI Setup
4 capabilities
Experimental0%
Beta74%
Stable88%
Local Gateway Integration
9 capabilities
Experimental0%
Beta74%
Stable88%
Remote Gateway Mode
5 capabilities
Experimental0%
Beta74%
Stable88%
Gateway Service Lifecycle
10 capabilities
Experimental0%
Beta74%
Stable88%
Diagnostics and Observability
4 capabilities
Experimental0%
Beta74%
Stable88%
Permissions and Native Capabilities
4 capabilities
Experimental0%
Beta74%
Stable88%
Profiles and Isolation
5 capabilities
Experimental0%
Beta74%
Stable88%
Android app - M4 Stable - 7 areas
Official Google Play distribution exists, source build/run docs are maintained, and the Android app is documented as a normal companion node for users.
Coverage Experimental - 0%Quality Stable - 80%Completeness Stable - 80%None
Media Capture
1 capabilities
Experimental0%
Stable80%
Stable80%
Mobile Chat
1 capabilities
Experimental0%
Stable80%
Stable80%
Connection Setup
1 capabilities
Experimental0%
Stable80%
Stable80%
Distribution
3 capabilities
Experimental0%
Stable80%
Stable80%
Settings
1 capabilities
Experimental0%
Stable80%
Stable80%
Voice
1 capabilities
Experimental0%
Stable80%
Stable80%
Device Runtime
2 capabilities
Experimental0%
Stable80%
Stable80%
iOS app - M4 Stable - 8 areas
Official App Store distribution exists, relay-backed push is documented, and the iOS app is documented as a normal companion node for users.
Coverage Experimental - 0%Quality Stable - 80%Completeness Stable - 80%None
Media and Sharing
1 capabilities
Experimental0%
Stable80%
Stable80%
Canvas and Screen
1 capabilities
Experimental0%
Stable80%
Stable80%
Chat and Sessions
1 capabilities
Experimental0%
Stable80%
Stable80%
Gateway Setup and Diagnostics
7 capabilities
Experimental0%
Stable80%
Stable80%
Distribution
1 capabilities
Experimental0%
Stable80%
Stable80%
Device Commands
2 capabilities
Experimental0%
Stable80%
Stable80%
Notifications and Background
1 capabilities
Experimental0%
Stable80%
Stable80%
Voice
1 capabilities
Experimental0%
Stable80%
Stable80%
Docker and Podman hosting - M3 Beta - 4 areas
Install docs exist and are common deployment paths. Promote after recurring release smoke captures upgrade and volume behavior.
Coverage Experimental - 7%Quality Beta - 71%Completeness Beta - 79%None
Container Setup
6 capabilities
Experimental0%
Alpha68%
Beta79%
Container Operations
11 capabilities
Experimental0%
Alpha68%
Beta79%
Image Release and Validation
5 capabilities
Experimental29%
Beta79%
Beta79%
Agent Sandbox and Tooling
3 capabilities
Experimental0%
Alpha68%
Beta79%
Windows via WSL2 - M3 Beta - 6 areas
Recommended Windows path with systemd/user-service guidance and boot-chain docs. Promote after repeated install/update scorecards.
Coverage Experimental - 6%Quality Alpha - 69%Completeness Beta - 79%Partial - 5
WSL Setup
6 capabilities / LTS-supported
Experimental0%
Alpha67%
Beta79%
CLI
8 capabilities / LTS-supported
Experimental0%
Alpha67%
Beta79%
Gateway Service Lifecycle
10 capabilities / LTS-supported
Experimental0%
Alpha67%
Beta79%
Gateway Access and Exposure
11 capabilities / LTS-supported
Experimental0%
Alpha67%
Beta79%
Diagnostics and Repair
6 capabilities / LTS-supported
Experimental38%
Beta79%
Beta79%
Browser and Control UI
6 capabilities
Experimental0%
Alpha67%
Beta79%
Raspberry Pi and small Linux devices - M3 Beta - 4 areas
Platform docs exist and Gateway path is Linux-based. Needs hardware-specific release smoke proof to move higher.
Coverage Experimental - 0%Quality Alpha - 67%Completeness Beta - 79%None
Setup and Compatibility
12 capabilities
Experimental0%
Alpha67%
Beta79%
Remote Access and Auth
9 capabilities
Experimental0%
Alpha67%
Beta79%
Gateway Runtime
10 capabilities
Experimental0%
Alpha67%
Beta79%
Performance and Diagnostics
5 capabilities
Experimental0%
Alpha67%
Beta79%
macOS companion app - M3 Beta - 8 areas
Rich menu bar app, permissions, node mode, Canvas, voice wake, WebChat, and remote mode exist. Still fast-moving enough to avoid Stable.
Coverage Experimental - 0%Quality Alpha - 66%Completeness Beta - 78%None
Canvas
4 capabilities
Experimental0%
Alpha66%
Beta78%
Local Setup
7 capabilities
Experimental0%
Alpha66%
Beta78%
Status and Settings
5 capabilities
Experimental0%
Alpha66%
Beta78%
Native Capabilities
5 capabilities
Experimental0%
Alpha66%
Beta78%
Remote Connections
3 capabilities
Experimental0%
Alpha66%
Beta78%
Voice and Talk
3 capabilities
Experimental0%
Alpha66%
Beta78%
WebChat
3 capabilities
Experimental0%
Alpha66%
Beta78%
Remote WebChat
5 capabilities
Experimental0%
Alpha66%
Beta78%
Native Windows - M2 Alpha - 4 areas
Core CLI/Gateway flows work, but docs still recommend WSL2 for the full experience and list native caveats.
Coverage Experimental - 0%Quality Alpha - 58%Completeness Alpha - 66%Partial - 1
CLI
9 capabilities / LTS-supported
Experimental0%
Alpha54%
Alpha64%
Gateway Management
11 capabilities
Experimental0%
Alpha59%
Alpha66%
Networking
4 capabilities
Experimental0%
Alpha59%
Alpha66%
Updates
4 capabilities
Experimental0%
Alpha59%
Alpha66%
Kubernetes hosting - M2 Alpha - 4 areas
Kubernetes hosting is a distinct Kustomize-based cluster deployment path. Current scoring shows a real minimal deployment path with gaps around Kubernetes-specific CI, ingress/TLS/NetworkPolicy packaging, backup/restore, and production exposure hardening.
Coverage Experimental - 0%Quality Alpha - 55%Completeness Alpha - 61%None
Deployment Setup
5 capabilities
Experimental0%
Alpha55%
Alpha61%
Configuration and Secrets
5 capabilities
Experimental0%
Alpha55%
Alpha61%
Access and Exposure
5 capabilities
Experimental0%
Alpha55%
Alpha61%
Cluster Lifecycle
5 capabilities
Experimental0%
Alpha55%
Alpha61%
Nix install path - M1 Experimental - 5 areas
Optional install flow. Needs clearer support promise before alpha/beta promotion.
Coverage Experimental - 0%Quality Experimental - 41%Completeness Experimental - 44%None
Install Handoff
4 capabilities
Experimental0%
Experimental41%
Experimental44%
Plugin Lifecycle
4 capabilities
Experimental0%
Experimental41%
Experimental44%
Activation and App UX
7 capabilities
Experimental0%
Experimental41%
Experimental44%
Config and State
7 capabilities
Experimental0%
Experimental41%
Experimental44%
Service Runtime and Guards
8 capabilities
Experimental0%
Experimental41%
Experimental44%
watchOS companion surfaces - M1 Experimental - 5 areas
Source has Watch app/extension surfaces; public docs do not yet present this as a user feature.
Coverage Experimental - 0%Quality Experimental - 41%Completeness Experimental - 44%None
Delivery and Recovery
7 capabilities
Experimental0%
Experimental41%
Experimental44%
Exec Approvals
3 capabilities
Experimental0%
Experimental41%
Experimental44%
Distribution and Support
6 capabilities
Experimental0%
Experimental41%
Experimental44%
Notifications and Replies
7 capabilities
Experimental0%
Experimental41%
Experimental44%
Watch App UI
3 capabilities
Experimental0%
Experimental41%
Experimental44%
Linux companion app - M0 Planned - 5 areas
Docs say native Linux companion apps are planned; Gateway is the supported Linux path today.
Coverage Experimental - 0%Quality Experimental - 19%Completeness Experimental - 21%None
App Distribution
3 capabilities
Experimental0%
Experimental19%
Experimental21%
Gateway Connectivity
4 capabilities
Experimental0%
Experimental19%
Experimental21%
Chat and Sessions
3 capabilities
Experimental0%
Experimental19%
Experimental21%
Desktop Capabilities
9 capabilities
Experimental0%
Experimental19%
Experimental21%
Status and Diagnostics
7 capabilities
Experimental0%
Experimental19%
Experimental21%
Native Windows companion app - M0 Planned - 5 areas
Planned only.
Coverage Experimental - 0%Quality Experimental - 19%Completeness Experimental - 21%None
Installation and Updates
4 capabilities
Experimental0%
Experimental19%
Experimental21%
Gateway Connection
3 capabilities
Experimental0%
Experimental19%
Experimental21%
Chat Sessions
2 capabilities
Experimental0%
Experimental19%
Experimental21%
Status and Repair
5 capabilities
Experimental0%
Experimental19%
Experimental21%
Desktop Tools and Permissions
10 capabilities
Experimental0%
Experimental19%
Experimental21%
Discord - M4 Stable - 6 areas
Deep docs and broad feature coverage. Voice/delegation paths should stay separately scored as beta/alpha.
Coverage Experimental - 0%Quality Beta - 73%Completeness Stable - 87%Partial - 4
Channel Setup and Operations
10 capabilities / LTS-supported
Experimental0%
Beta73%
Stable87%
Access and Identity
6 capabilities / LTS-supported
Experimental0%
Beta73%
Stable87%
Conversation Routing and Delivery
12 capabilities / LTS-supported
Experimental0%
Beta73%
Stable87%
Media and Rich Content
1 capabilities / LTS-supported
Experimental0%
Beta73%
Stable87%
Native Controls and Approvals
5 capabilities
Experimental0%
Beta73%
Stable87%
Realtime Voice and Calls
5 capabilities
Experimental0%
Beta73%
Stable87%
Telegram - M3 Beta - 5 areas
Core channel is mature enough for regular use, but high-variance UX and media edge cases need recurring scenario proof.
Coverage Experimental - 0%Quality Alpha - 68%Completeness Beta - 78%Full - 5
Channel Setup and Operations
10 capabilities / LTS-supported
Experimental0%
Alpha66%
Beta78%
Access and Identity
10 capabilities / LTS-supported
Experimental0%
Alpha66%
Beta78%
Conversation Routing and Delivery
1 capabilities / LTS-supported
Experimental0%
Alpha66%
Beta78%
Media and Rich Content
1 capabilities / LTS-supported
Experimental0%
Alpha66%
Beta78%
Native Controls and Approvals
9 capabilities / LTS-supported
Experimental0%
Beta77%
Beta79%
Slack - M3 Beta - 5 areas
First-class channel docs and routing surface. Needs workspace install/admin scenario scorecards.
Coverage Experimental - 0%Quality Alpha - 66%Completeness Beta - 78%Full - 5
Channel Setup and Operations
10 capabilities / LTS-supported
Experimental0%
Alpha66%
Beta78%
Access and Identity
1 capabilities / LTS-supported
Experimental0%
Alpha66%
Beta78%
Conversation Routing and Delivery
5 capabilities / LTS-supported
Experimental0%
Alpha66%
Beta78%
Media and Rich Content
1 capabilities / LTS-supported
Experimental0%
Alpha66%
Beta78%
Native Controls and Approvals
8 capabilities / LTS-supported
Experimental0%
Alpha66%
Beta78%
iMessage and BlueBubbles - M3 Beta - 5 areas
Supported iMessage runs through imsg on a signed-in macOS Messages host; legacy BlueBubbles configs require migration. Keep macOS permissions, SSH wrapper, SIP/private API, and migration caveats visible.
Coverage Experimental - 0%Quality Alpha - 66%Completeness Beta - 78%None
Channel Setup and Operations
11 capabilities
Experimental0%
Alpha66%
Beta78%
Access and Identity
6 capabilities
Experimental0%
Alpha66%
Beta78%
Conversation Routing and Delivery
4 capabilities
Experimental0%
Alpha66%
Beta78%
Media and Rich Content
7 capabilities
Experimental0%
Alpha66%
Beta78%
Native Controls and Approvals
3 capabilities
Experimental0%
Alpha66%
Beta78%
WhatsApp - M3 Beta - 5 areas
Core path is important and documented; upstream Baileys/session volatility keeps it below Stable.
Coverage Experimental - 0%Quality Alpha - 66%Completeness Beta - 78%None
Channel Setup and Operations
5 capabilities
Experimental0%
Alpha66%
Beta78%
Access and Identity
7 capabilities
Experimental0%
Alpha66%
Beta78%
Conversation Routing and Delivery
4 capabilities
Experimental0%
Alpha66%
Beta78%
Media and Rich Content
2 capabilities
Experimental0%
Alpha66%
Beta78%
Native Controls and Approvals
2 capabilities
Experimental0%
Alpha66%
Beta78%
Matrix - M2 Alpha - 6 areas
Supported via bundled plugin. Needs bridge, auth, and room lifecycle scorecards.
Coverage Experimental - 0%Quality Alpha - 60%Completeness Alpha - 67%None
Channel Setup and Operations
5 capabilities
Experimental0%
Alpha60%
Alpha67%
Access and Identity
7 capabilities
Experimental0%
Alpha60%
Alpha67%
Conversation Routing and Delivery
1 capabilities
Experimental0%
Alpha60%
Alpha67%
Media and Rich Content
1 capabilities
Experimental0%
Alpha60%
Alpha67%
Native Controls and Approvals
6 capabilities
Experimental0%
Alpha60%
Alpha67%
Encryption and Verification
3 capabilities
Experimental0%
Alpha60%
Alpha67%
Google Chat - M2 Alpha - 5 areas
Documented channel, but enterprise/admin setup raises maturity risk.
Coverage Experimental - 0%Quality Alpha - 59%Completeness Alpha - 66%None
Channel Setup and Operations
16 capabilities
Experimental0%
Alpha59%
Alpha66%
Access and Identity
11 capabilities
Experimental0%
Alpha59%
Alpha66%
Conversation Routing and Delivery
1 capabilities
Experimental0%
Alpha59%
Alpha66%
Media and Rich Content
1 capabilities
Experimental0%
Alpha59%
Alpha66%
Native Controls and Approvals
16 capabilities
Experimental0%
Alpha59%
Alpha66%
Microsoft Teams - M2 Alpha - 5 areas
Enterprise auth/admin flows need explicit scenario proof.
Coverage Experimental - 0%Quality Alpha - 59%Completeness Alpha - 66%None
Channel Setup and Operations
9 capabilities
Experimental0%
Alpha59%
Alpha66%
Access and Identity
9 capabilities
Experimental0%
Alpha59%
Alpha66%
Conversation Routing and Delivery
5 capabilities
Experimental0%
Alpha59%
Alpha66%
Media and Rich Content
5 capabilities
Experimental0%
Alpha59%
Alpha66%
Native Controls and Approvals
5 capabilities
Experimental0%
Alpha59%
Alpha66%
Signal - M2 Alpha - 5 areas
Supported channel docs exist; needs stronger install and reconnect proof.
Coverage Experimental - 0%Quality Alpha - 59%Completeness Alpha - 66%None
Channel Setup and Operations
7 capabilities
Experimental0%
Alpha59%
Alpha66%
Access and Identity
6 capabilities
Experimental0%
Alpha59%
Alpha66%
Conversation Routing and Delivery
1 capabilities
Experimental0%
Alpha59%
Alpha66%
Media and Rich Content
7 capabilities
Experimental0%
Alpha59%
Alpha66%
Native Controls and Approvals
3 capabilities
Experimental0%
Alpha59%
Alpha66%
Feishu, QQ Bot, WeChat, Yuanbao, Zalo, Zalo Personal, regional channels - M2 Alpha - 4 areas
Important regional coverage, but public support level should be calibrated per account type, upstream approval, and maintainer proof.
Coverage Experimental - 0%Quality Alpha - 55%Completeness Alpha - 58%None
Channel Setup and Operations
6 capabilities
Experimental0%
Alpha61%
Alpha68%
Access and Identity
1 capabilities
Experimental0%
Alpha53%
Alpha54%
No linked docs
Conversation Routing and Delivery
1 capabilities
Experimental0%
Alpha53%
Alpha54%
No linked docs
Media and Rich Content
1 capabilities
Experimental0%
Alpha53%
Alpha54%
No linked docs
Mattermost, LINE, IRC, Nextcloud Talk, Nostr, Twitch, Tlon, Synology Chat - M2 Alpha - 4 areas
Supported surfaces exist, but maturity likely varies by upstream and maintainer coverage. Score individually later.
Coverage Experimental - 0%Quality Alpha - 53%Completeness Alpha - 54%None
Channel Setup and Operations
1 capabilities
Experimental0%
Alpha53%
Alpha54%
No linked docs
Access and Identity
1 capabilities
Experimental0%
Alpha53%
Alpha54%
No linked docs
Conversation Routing and Delivery
1 capabilities
Experimental0%
Alpha53%
Alpha54%
No linked docs
Media and Rich Content
1 capabilities
Experimental0%
Alpha53%
Alpha54%
No linked docs
Voice Call channel - M1 Experimental - 5 areas
Optional/plugin path with complex realtime behavior. Needs scenario scorecard before public beta.
Coverage Experimental - 0%Quality Experimental - 41%Completeness Experimental - 44%None
Channel Setup and Operations
2 capabilities
Experimental0%
Experimental41%
Experimental44%
Access and Identity
1 capabilities
Experimental0%
Experimental41%
Experimental44%
Conversation Routing and Delivery
1 capabilities
Experimental0%
Experimental41%
Experimental44%
Media and Rich Content
2 capabilities
Experimental0%
Experimental41%
Experimental44%
Realtime Voice and Calls
2 capabilities
Experimental0%
Experimental41%
Experimental44%
Browser automation, exec, and sandbox tools - M3 Beta - 3 areas
Core tools are documented, but host security and permission UX should stay under active scorecard review.
Coverage Experimental - 21%Quality Beta - 75%Completeness Beta - 79%Partial - 2
Browser Automation
8 capabilities
Experimental13%
Beta79%
Beta79%
Tool Invocation and Execution
6 capabilities / LTS-supported
Alpha50%
Beta79%
Beta79%
Sandbox and Tool Policy
6 capabilities / LTS-supported
Experimental0%
Alpha68%
Beta79%
OpenAI and Codex provider path - M3 Beta - 5 areas
Deep docs, OAuth/subscription path, realtime voice, image, and compatibility behavior. Provider churn keeps this from Stable without release-scorecard proof.
Coverage Experimental - 26%Quality Beta - 74%Completeness Beta - 79%Partial - 3
Model and Auth
6 capabilities / LTS-supported
Experimental44%
Beta79%
Beta79%
Responses and Tool Compatibility
4 capabilities / LTS-supported
Experimental40%
Beta79%
Beta79%
Native Codex Harness
2 capabilities / LTS-supported
Experimental44%
Beta79%
Beta79%
Image and Multimodal Input
2 capabilities
Experimental0%
Alpha67%
Beta79%
Voice and Realtime Audio
2 capabilities
Experimental0%
Alpha67%
Beta79%
Web search tools - M3 Beta - 4 areas
Multiple providers and docs exist. Needs quota/error/SSRF proof per provider family.
Coverage Experimental - 9%Quality Beta - 74%Completeness Beta - 79%None
Search Providers
19 capabilities
Experimental11%
Beta79%
Beta79%
Web,
Brave Search,
Tavily,
Exa Search,
Firecrawl,
Perplexity Search,
Duckduckgo Search,
Searxng Search,
Gemini Search,
Grok Search,
Kimi Search,
Minimax Search,
Ollama Search,
Sdk Subpaths,
Sdk Overview,
Manifest
Setup and Diagnostics
9 capabilities
Experimental0%
Alpha68%
Beta79%
Network Safety
4 capabilities
Experimental0%
Alpha68%
Beta79%
Tool Availability and Fetch
11 capabilities
Experimental25%
Beta79%
Beta79%
Anthropic provider path - M3 Beta - 5 areas
First-class model provider. Needs recurring auth/catalog/tool-call scenario proof.
Coverage Experimental - 0%Quality Beta - 71%Completeness Beta - 78%None
Provider Auth and Recovery
9 capabilities
Experimental0%
Alpha66%
Beta78%
Model and Runtime Selection
10 capabilities
Experimental0%
Beta78%
Beta79%
Request Transport and Turn Semantics
10 capabilities
Experimental0%
Beta77%
Beta79%
Prompt Cache and Context
5 capabilities
Experimental0%
Alpha66%
Beta78%
Media Inputs
4 capabilities
Experimental0%
Alpha66%
Beta78%
Google provider path - M3 Beta - 5 areas
First-class provider with model and realtime surfaces. Needs separate Live/Talk scoring.
Coverage Experimental - 0%Quality Alpha - 66%Completeness Beta - 78%None
Provider Setup and Credentials
10 capabilities
Experimental0%
Alpha66%
Beta78%
Model Routing and Endpoints
10 capabilities
Experimental0%
Alpha66%
Beta78%
Direct Gemini Runtime
9 capabilities
Experimental0%
Alpha66%
Beta78%
Media, Search, and Realtime
10 capabilities
Experimental0%
Alpha66%
Beta78%
Prompt Caching
5 capabilities
Experimental0%
Alpha66%
Beta78%
OpenRouter provider path - M3 Beta - 4 areas
Unified provider path is documented and valuable, but model-specific behavior varies.
Coverage Experimental - 0%Quality Alpha - 66%Completeness Beta - 78%None
Provider Setup and Auth
14 capabilities
Experimental0%
Alpha66%
Beta78%
Chat Runtime and Normalization
15 capabilities
Experimental0%
Alpha66%
Beta78%
Provider Recovery and Diagnostics
5 capabilities
Experimental0%
Alpha66%
Beta78%
Media Generation and Speech
7 capabilities
Experimental0%
Alpha66%
Beta78%
Image, video, and music generation tools - M2 Alpha - 5 areas
Capability exists across providers, but quality, latency, and parameter compatibility vary too much for beta without per-provider proof.
Coverage Experimental - 0%Quality Alpha - 61%Completeness Alpha - 68%None
Media Routing and Discovery
4 capabilities
Experimental0%
Alpha61%
Alpha68%
Task Lifecycle and Delivery
12 capabilities
Experimental0%
Alpha61%
Alpha68%
Image Generation
9 capabilities
Experimental0%
Alpha61%
Alpha68%
Video Generation
11 capabilities
Experimental0%
Alpha61%
Alpha68%
Music Generation
6 capabilities
Experimental0%
Alpha61%
Alpha68%
Local model providers: Ollama, vLLM, SGLang, LM Studio - M2 Alpha - 5 areas
Useful and documented, but environment variance is high.
Coverage Experimental - 0%Quality Alpha - 61%Completeness Alpha - 68%None
Provider Setup, Lifecycle, and Diagnostics
12 capabilities
Experimental0%
Alpha61%
Alpha68%
Native Provider Plugins
10 capabilities
Experimental0%
Alpha61%
Alpha68%
OpenAI-Compatible Runtime Compatibility
8 capabilities
Experimental0%
Alpha61%
Alpha68%
Local Memory and Embeddings
5 capabilities
Experimental0%
Alpha61%
Alpha68%
Network Safety and Prompt Controls
2 capabilities
Experimental0%
Alpha61%
Alpha68%
Long-tail hosted providers - M2 Alpha - 3 areas
Many docs/reference pages exist; score should be generated from provider metadata plus live smoke coverage.
Coverage Experimental - 0%Quality Alpha - 61%Completeness Alpha - 68%None
Hosted LLM Providers
12 capabilities
Experimental0%
Alpha61%
Alpha68%
Hosted Media Providers
8 capabilities
Experimental0%
Alpha61%
Alpha68%
Provider Operations
12 capabilities
Experimental0%
Alpha61%
Alpha68%