Swarmd.ai

	Self-Hosted	Source	Managed
How it’s delivered
Runs on	Your infrastructure	Your infrastructure	swarmd-hosted (your region)
Container images
Source code via independent escrow	—		—
Operated by	You	You	swarmd
Updates	On your terms	On your terms	Managed for you
Your data & keys	Yours	Yours	Your region
Support	Standard	Priority	Dedicated + SLAs
Free 3-month trial		—	—
Price	Free for 3 months, then custom	Custom	Custom
Control plane
Single pane of glass Govern agents, MCP servers, LLM gateways and channels from one portal.
Configure once, agents auto-update Change a subscription, credential, route or freeze centrally — agents pick it up automatically, no redeploys.
Closed by default Agents can’t self-discover or self-connect; every link is an explicit grant.
Live agent network map Interactive topology of every agent, MCP, gateway, channel and user, health-sorted.
Central subscription management Wire up agent↔agent, agent↔MCP, agent↔gateway and channel↔agent relationships in the UI.
Test policies on the edge Click any connection in the map to test the policy between source and destination.
Agents
Agent registration Relay card URL, health checks, visibility and auth method.
Health & status at a glance Healthy / unreachable / unhealthy, plus active / inactive / frozen states.
Killswitch Instantly pause a single agent’s traffic with a reason.
Tenant-wide lockdown Freeze all relay traffic — every agent, caller and webhook — during an incident.
Zero-downtime credential rotation Regenerate OAuth secrets and keys without changing the client ID.
Skills inventory See every capability an agent advertises — and govern it.
Agent task board Live kanban of agent tasks by lifecycle state, with full event history.
Per-agent metrics Uptime, request volume, latency, error rate and activity charts.
Lifecycle audit log A chronological trail of every state change per agent.
Agent marketplace Discover and one-click-connect verified agents.
Connectivity
MCP server management Register, version, freeze/unfreeze, rotate credentials, full lifecycle log.
Flexible MCP auth None, bearer, API key, query param or OAuth2 — including user-delegated auth-code flow.
Two-tier MCP marketplace A curated official catalog plus a community marketplace, with uptime and latency metrics.
One-click connect snippets Copy-paste config for Claude Code, Claude Desktop, Cursor and more.
LLM gateways with failover Aggregate multiple providers behind one gateway.
Smart LLM routing Route by default/fallback or by agent metadata tag, priority-ordered.
LLM provider management OpenAI, Anthropic, Mistral and more, with credential rotation.
Integration channels OAuth-backed hubs connecting external systems to your agents.
Microsoft Teams Enable the Teams bot, download the app manifest, auto-linked channel.
The gatekeeper
Visual policy builder Drag-and-drop enforcement rules — no code required.
Rego Policy Builder Switch to code; parse Rego to visual and back.
Five enforcement actions Block, mask, warn, log or require human review — on every exchange.
PII detection & redaction Presidio (23+ entity types) and AWS Comprehend (21 types) with confidence thresholds.
Regex, rate limits & skill restrictions Pattern-match data, throttle per window, and control which tools an agent can call.
Message-leg targeting Apply rules to specific request and response legs.
11 cascade scopes Bind policies at tenant, agent, user, channel, MCP or gateway level.
Inherited policy chain See which broader-scope policies apply before local ones; reorder priority.
Versioned policy groups Owners, validity windows, hash-tracked versions and full change history.
Evaluate before you ship Real-time rule validation and config preview.
Gatekeeper request log Every intercepted request that triggered a policy.
Human-in-the-loop
Approvals queue A central list of flagged exchanges awaiting review.
Review with full context Source user, sink agent, policy, matched content and the linked trace.
Reason-backed decisions Every approve or reject is auditable — who, when, why.
HITL SLA & outcomes Track escalations raised, resolved and pending, plus SLA compliance.
Reviewer leaderboard & override audit Who’s reviewing, and every action taken outside policy.
Observability
Complete logging Every interaction and system exchange captured with rich context.
Distributed tracing Flame-graph timelines, spans, durations and correlation IDs.
Monitors & alerts P1–P5 priority with a full alert lifecycle — ack, resolve, dismiss, reopen.
Mute & downtime windows Silence monitors indefinitely or until a set time, with actor tracking.
Search, stats & CSV export Across logs, traces and alerts.
Correlated events Related events linked by correlation ID.
Detection
Dormant reactivation Inactive agents or users suddenly coming back to life.
Novel tool-call detection An agent calling a tool it has never used before.
New MCP-binding detection Agents binding to new MCP servers.
Sensitive-data detections Flagged by the masking middleware.
Coverage gap analysis Agents with no enforced policy, shadow-mode policies and monitor coverage.
Compliance
Tamper-proof logs Cryptographic hash-chain integrity across the audit trail.
Qualified timestamps RFC 3161 third-party TSA anchoring.
One-click integrity checks Verify all checkpoints or a specific time range for tampering.
Compliance evidence packs Export audit events, hash-chain anchors and policy actions for any window.
EU & Singapore AI-law mapping Controls mapped to the obligations of the EU AI Act and Singapore’s AI governance framework.
Insights
7 persona dashboards CIO, CISO, Head of Risk & Compliance, General Counsel, Head of Technology, AI/Transformation Lead and Business Domain Owner.
Control effectiveness Share of traffic blocked, warned or held; logged vs masked vs blocked.
Leaderboards Top agents, users, MCP servers, channels and reviewers.
Adoption analytics WAU/MAU stickiness, new vs returning, time-to-first-value.
Reliability Error-budget burn, p95/p99 latency, SLOs, fleet and dependency health.
Estate & usage Estate overview, by-channel breakdown, use-case heatmap and top failing flows.
Access & admin
SSO / identity providers Microsoft Entra ID, Google Workspace and Okta.
Domain verification & group mapping Auto-provision users and map IdP groups to swarmd groups.
Groups & RBAC Granular permissions, membership and versioned config.
User management Invite, assign roles, deactivate/reactivate, activity history.
Encrypted credentials Secrets, keys and tokens encrypted at rest and in transit.
Built-in conversation UI Chat directly with any agent or gateway to test.

Self-Hosted

Source

Managed

How it’s delivered

Runs on

Your infrastructure

swarmd-hosted (your region)

Container images

Source code via independent escrow

—

Operated by

You

swarmd

Updates

On your terms

Managed for you

Your data & keys

Yours

Your region

Support

Standard

Priority

Dedicated + SLAs

Free 3-month trial

—

Price

Free for 3 months, then custom

Custom

Control plane

Single pane of glass

Govern agents, MCP servers, LLM gateways and channels from one portal.

Configure once, agents auto-update

Change a subscription, credential, route or freeze centrally — agents pick it up automatically, no redeploys.

Closed by default

Agents can’t self-discover or self-connect; every link is an explicit grant.

Live agent network map

Interactive topology of every agent, MCP, gateway, channel and user, health-sorted.

Central subscription management

Wire up agent↔agent, agent↔MCP, agent↔gateway and channel↔agent relationships in the UI.

Test policies on the edge

Click any connection in the map to test the policy between source and destination.

Agents

Agent registration

Relay card URL, health checks, visibility and auth method.

Health & status at a glance

Healthy / unreachable / unhealthy, plus active / inactive / frozen states.

Killswitch

Instantly pause a single agent’s traffic with a reason.

Tenant-wide lockdown

Freeze all relay traffic — every agent, caller and webhook — during an incident.

Zero-downtime credential rotation

Regenerate OAuth secrets and keys without changing the client ID.

Skills inventory

See every capability an agent advertises — and govern it.

Agent task board

Live kanban of agent tasks by lifecycle state, with full event history.

Per-agent metrics

Uptime, request volume, latency, error rate and activity charts.

Lifecycle audit log

A chronological trail of every state change per agent.

Agent marketplace

Discover and one-click-connect verified agents.

Connectivity

MCP server management

Flexible MCP auth

None, bearer, API key, query param or OAuth2 — including user-delegated auth-code flow.

Two-tier MCP marketplace

A curated official catalog plus a community marketplace, with uptime and latency metrics.

One-click connect snippets

Copy-paste config for Claude Code, Claude Desktop, Cursor and more.

LLM gateways with failover

Aggregate multiple providers behind one gateway.

Smart LLM routing

Route by default/fallback or by agent metadata tag, priority-ordered.

LLM provider management

OpenAI, Anthropic, Mistral and more, with credential rotation.

Integration channels

OAuth-backed hubs connecting external systems to your agents.

Microsoft Teams

Enable the Teams bot, download the app manifest, auto-linked channel.

The gatekeeper

Visual policy builder

Drag-and-drop enforcement rules — no code required.

Rego Policy Builder

Switch to code; parse Rego to visual and back.

Five enforcement actions

Block, mask, warn, log or require human review — on every exchange.

PII detection & redaction

Presidio (23+ entity types) and AWS Comprehend (21 types) with confidence thresholds.

Regex, rate limits & skill restrictions

Pattern-match data, throttle per window, and control which tools an agent can call.

Message-leg targeting

Apply rules to specific request and response legs.

11 cascade scopes

Bind policies at tenant, agent, user, channel, MCP or gateway level.

Inherited policy chain

See which broader-scope policies apply before local ones; reorder priority.

Versioned policy groups

Owners, validity windows, hash-tracked versions and full change history.

Evaluate before you ship

Real-time rule validation and config preview.

Gatekeeper request log

Every intercepted request that triggered a policy.

Human-in-the-loop

Approvals queue

A central list of flagged exchanges awaiting review.

Review with full context

Source user, sink agent, policy, matched content and the linked trace.

Reason-backed decisions

Every approve or reject is auditable — who, when, why.

HITL SLA & outcomes

Track escalations raised, resolved and pending, plus SLA compliance.

Reviewer leaderboard & override audit

Who’s reviewing, and every action taken outside policy.

Observability

Complete logging

Every interaction and system exchange captured with rich context.

Distributed tracing

Flame-graph timelines, spans, durations and correlation IDs.

Monitors & alerts

P1–P5 priority with a full alert lifecycle — ack, resolve, dismiss, reopen.

Mute & downtime windows

Silence monitors indefinitely or until a set time, with actor tracking.

Search, stats & CSV export

Across logs, traces and alerts.

Correlated events

Related events linked by correlation ID.

Detection

Dormant reactivation

Inactive agents or users suddenly coming back to life.

Novel tool-call detection

An agent calling a tool it has never used before.

New MCP-binding detection

Agents binding to new MCP servers.

Sensitive-data detections

Flagged by the masking middleware.

Coverage gap analysis

Agents with no enforced policy, shadow-mode policies and monitor coverage.

Compliance

Tamper-proof logs

Cryptographic hash-chain integrity across the audit trail.

Qualified timestamps

RFC 3161 third-party TSA anchoring.

One-click integrity checks

Verify all checkpoints or a specific time range for tampering.

Compliance evidence packs

Export audit events, hash-chain anchors and policy actions for any window.

EU & Singapore AI-law mapping

Controls mapped to the obligations of the EU AI Act and Singapore’s AI governance framework.

Insights

7 persona dashboards

CIO, CISO, Head of Risk & Compliance, General Counsel, Head of Technology, AI/Transformation Lead and Business Domain Owner.

Control effectiveness

Share of traffic blocked, warned or held; logged vs masked vs blocked.

Leaderboards

Top agents, users, MCP servers, channels and reviewers.

Adoption analytics

WAU/MAU stickiness, new vs returning, time-to-first-value.

Reliability

Error-budget burn, p95/p99 latency, SLOs, fleet and dependency health.

Estate & usage

Estate overview, by-channel breakdown, use-case heatmap and top failing flows.

Access & admin

SSO / identity providers

Microsoft Entra ID, Google Workspace and Okta.

Domain verification & group mapping

Auto-provision users and map IdP groups to swarmd groups.

Groups & RBAC

Granular permissions, membership and versioned config.

User management

Invite, assign roles, deactivate/reactivate, activity history.

Encrypted credentials

Secrets, keys and tokens encrypted at rest and in transit.

Built-in conversation UI

Chat directly with any agent or gateway to test.