An operational brain
your agents trust
ModusBrain compiles your policies and runbooks into approved operational skills that AI agents execute against — with version control, confidence gating, and a full audit trail.
ModusBrainExample workspace — not live data
Skills
FilterSortOptions
Skill
Confidence
Compiled By
Risk Tier
Status
Runs/Mo
Docs
Category
Lead Reviewer
Runs/Day
Runbooks
Added
R
Refund Handler95%
JC
Jane CooperHigh Stakes
Approved
12,400
refund-handler
Finance Ops
JC
Jane Cooper412
R
Refund EscalationJul 1, 2026
U
User Provisioner88%
AK
Alex KimHigh Stakes
Pending Approval
8,200
user-provisioner
Identity & Access
MT
Maria Torres274
A
Access ReviewJul 3, 2026
L
Lead Scorer78%
DP
Devon ParkLow Stakes
Approved
31,800
lead-scorer
Revenue Ops
PN
Priya Nair1,060
Q
Qualification RunJul 5, 2026
C
Compliance Auditor92%
API
API - Key nameInformational
Pending Approval
5,600
compliance-auditor
Compliance
SR
Sam Reyes187
S
SOC2 AuditJul 8, 2026
I
Invoice Processor94%
WF
Workflow nameHigh Stakes
Approved
19,100
invoice-processor
Finance Ops
LC
Leo Chen637
AP
AP ApprovalP
PO MatchJul 12, 2026
S
Support Triage91%
NW
Nora WhitfieldLow Stakes
Approved
9,300
support-triage
Customer Support
EB
Ethan Brooks310
E
Escalation PathJul 14, 2026
D
Data Enricher89%
RM
Ravi MalhotraInformational
Approved
47,800
data-enricher
Data Ops
CL
Casey Lin1,593
E
Enrich RunJul 15, 2026
C
Contract Reviewer86%
JL
Jordan LeeLow Stakes
Approved
18,000
contract-reviewer
Legal Ops
JL
Jordan Lee600
M
MSA ReviewJul 17, 2026
D
Deployment Monitor97%
TV
Taylor VanceHigh Stakes
Pending Approval
64,000
deployment-monitor
DevOps
TV
Taylor Vance2,133
A
Alert TriageJul 20, 2026
E
Email Drafter93%
MW
Morgan WestLow Stakes
Approved
22,400
email-drafter
Comms Ops
MW
Morgan West747
O
Outbound CampaignJul 21, 2026
R
Report Builder85%
CL
Casey LopezInformational
Pending Approval
11,250
report-builder
Analytics
RW
Robin Wu375
W
Weekly DigestJul 23, 2026
R
Risk Classifier84%
RM
Reese MillerHigh Stakes
Approved
33,800
risk-classifier
Security
PL
Parker Lopez1,127
T
Threat ScanJul 24, 2026
P
Policy Enforcer96%
SYS
SystemLow Stakes
Approved
7,900
policy-enforcer
Governance
PW
Peyton Ward263
P
Policy SyncJul 25, 2026
O
Onboarding Agent90%
SP
Sunny PatelInformational
Pending Approval
55,200
onboarding-agent
Platform Ops
SP
Sunny Patel1,840
U
User JourneyS
Seat ActivationT
Trial ConversionJul 1, 2026 2:25 pm
Calculate
...with AI that executes consistently
Approve skills, audit executions, and resolve conflicts with a knowledge layer that gives your AI agents consistent, trustworthy behaviour across every team.
ModusBrainExample workspace — not live data
Skills
FilterSortOptions
Skill
Confidence
Compiled By
Risk Tier
Status
Runs/Mo
Docs
Category
Lead Reviewer
Runs/Day
Runbooks
Added
R
Refund Handler95%
JC
Jane CooperHigh Stakes
Approved
12,400
refund-handler
Finance Ops
JC
Jane Cooper412
R
Refund EscalationJul 1, 2026
U
User Provisioner88%
AK
Alex KimHigh Stakes
Pending Approval
8,200
user-provisioner
Identity & Access
MT
Maria Torres274
A
Access ReviewJul 3, 2026
L
Lead Scorer78%
DP
Devon ParkLow Stakes
Approved
31,800
lead-scorer
Revenue Ops
PN
Priya Nair1,060
Q
Qualification RunJul 5, 2026
C
Compliance Auditor92%
API
API - Key nameInformational
Pending Approval
5,600
compliance-auditor
Compliance
SR
Sam Reyes187
S
SOC2 AuditJul 8, 2026
I
Invoice Processor94%
WF
Workflow nameHigh Stakes
Approved
19,100
invoice-processor
Finance Ops
LC
Leo Chen637
AP
AP ApprovalP
PO MatchJul 12, 2026
S
Support Triage91%
NW
Nora WhitfieldLow Stakes
Approved
9,300
support-triage
Customer Support
EB
Ethan Brooks310
E
Escalation PathJul 14, 2026
D
Data Enricher89%
RM
Ravi MalhotraInformational
Approved
47,800
data-enricher
Data Ops
CL
Casey Lin1,593
E
Enrich RunJul 15, 2026
C
Contract Reviewer86%
JL
Jordan LeeLow Stakes
Approved
18,000
contract-reviewer
Legal Ops
JL
Jordan Lee600
M
MSA ReviewJul 17, 2026
D
Deployment Monitor97%
TV
Taylor VanceHigh Stakes
Pending Approval
64,000
deployment-monitor
DevOps
TV
Taylor Vance2,133
A
Alert TriageJul 20, 2026
E
Email Drafter93%
MW
Morgan WestLow Stakes
Approved
22,400
email-drafter
Comms Ops
MW
Morgan West747
O
Outbound CampaignJul 21, 2026
R
Report Builder85%
CL
Casey LopezInformational
Pending Approval
11,250
report-builder
Analytics
RW
Robin Wu375
W
Weekly DigestJul 23, 2026
R
Risk Classifier84%
RM
Reese MillerHigh Stakes
Approved
33,800
risk-classifier
Security
PL
Parker Lopez1,127
T
Threat ScanJul 24, 2026
P
Policy Enforcer96%
SYS
SystemLow Stakes
Approved
7,900
policy-enforcer
Governance
PW
Peyton Ward263
P
Policy SyncJul 25, 2026
O
Onboarding Agent90%
SP
Sunny PatelInformational
Pending Approval
55,200
onboarding-agent
Platform Ops
SP
Sunny Patel1,840
U
User JourneyS
Seat ActivationT
Trial ConversionJul 1, 2026 2:25 pm
Calculate
An operational brain
your agents trust
ModusBrain compiles your policies and runbooks into approved operational skills that AI agents execute against — with version control, confidence gating, and a full audit trail.
ModusBrainExample workspace — not live data
Skills
FilterSortOptions
Skill
Confidence
Compiled By
Risk Tier
Status
Runs/Mo
Docs
Category
Lead Reviewer
Runs/Day
Runbooks
Added
R
Refund Handler95%
JC
Jane CooperHigh Stakes
Approved
12,400
refund-handler
Finance Ops
JC
Jane Cooper412
R
Refund EscalationJul 1, 2026
U
User Provisioner88%
AK
Alex KimHigh Stakes
Pending Approval
8,200
user-provisioner
Identity & Access
MT
Maria Torres274
A
Access ReviewJul 3, 2026
L
Lead Scorer78%
DP
Devon ParkLow Stakes
Approved
31,800
lead-scorer
Revenue Ops
PN
Priya Nair1,060
Q
Qualification RunJul 5, 2026
C
Compliance Auditor92%
API
API - Key nameInformational
Pending Approval
5,600
compliance-auditor
Compliance
SR
Sam Reyes187
S
SOC2 AuditJul 8, 2026
I
Invoice Processor94%
WF
Workflow nameHigh Stakes
Approved
19,100
invoice-processor
Finance Ops
LC
Leo Chen637
AP
AP ApprovalP
PO MatchJul 12, 2026
S
Support Triage91%
NW
Nora WhitfieldLow Stakes
Approved
9,300
support-triage
Customer Support
EB
Ethan Brooks310
E
Escalation PathJul 14, 2026
D
Data Enricher89%
RM
Ravi MalhotraInformational
Approved
47,800
data-enricher
Data Ops
CL
Casey Lin1,593
E
Enrich RunJul 15, 2026
C
Contract Reviewer86%
JL
Jordan LeeLow Stakes
Approved
18,000
contract-reviewer
Legal Ops
JL
Jordan Lee600
M
MSA ReviewJul 17, 2026
D
Deployment Monitor97%
TV
Taylor VanceHigh Stakes
Pending Approval
64,000
deployment-monitor
DevOps
TV
Taylor Vance2,133
A
Alert TriageJul 20, 2026
E
Email Drafter93%
MW
Morgan WestLow Stakes
Approved
22,400
email-drafter
Comms Ops
MW
Morgan West747
O
Outbound CampaignJul 21, 2026
R
Report Builder85%
CL
Casey LopezInformational
Pending Approval
11,250
report-builder
Analytics
RW
Robin Wu375
W
Weekly DigestJul 23, 2026
R
Risk Classifier84%
RM
Reese MillerHigh Stakes
Approved
33,800
risk-classifier
Security
PL
Parker Lopez1,127
T
Threat ScanJul 24, 2026
P
Policy Enforcer96%
SYS
SystemLow Stakes
Approved
7,900
policy-enforcer
Governance
PW
Peyton Ward263
P
Policy SyncJul 25, 2026
O
Onboarding Agent90%
SP
Sunny PatelInformational
Pending Approval
55,200
onboarding-agent
Platform Ops
SP
Sunny Patel1,840
U
User JourneyS
Seat ActivationT
Trial ConversionJul 1, 2026 2:25 pm
Calculate
...with AI that executes consistently
Approve skills, audit executions, and resolve conflicts with a knowledge layer that gives your AI agents consistent, trustworthy behaviour across every team.
ModusBrainExample workspace — not live data
Skills
FilterSortOptions
Skill
Confidence
Compiled By
Risk Tier
Status
Runs/Mo
Docs
Category
Lead Reviewer
Runs/Day
Runbooks
Added
R
Refund Handler95%
JC
Jane CooperHigh Stakes
Approved
12,400
refund-handler
Finance Ops
JC
Jane Cooper412
R
Refund EscalationJul 1, 2026
U
User Provisioner88%
AK
Alex KimHigh Stakes
Pending Approval
8,200
user-provisioner
Identity & Access
MT
Maria Torres274
A
Access ReviewJul 3, 2026
L
Lead Scorer78%
DP
Devon ParkLow Stakes
Approved
31,800
lead-scorer
Revenue Ops
PN
Priya Nair1,060
Q
Qualification RunJul 5, 2026
C
Compliance Auditor92%
API
API - Key nameInformational
Pending Approval
5,600
compliance-auditor
Compliance
SR
Sam Reyes187
S
SOC2 AuditJul 8, 2026
I
Invoice Processor94%
WF
Workflow nameHigh Stakes
Approved
19,100
invoice-processor
Finance Ops
LC
Leo Chen637
AP
AP ApprovalP
PO MatchJul 12, 2026
S
Support Triage91%
NW
Nora WhitfieldLow Stakes
Approved
9,300
support-triage
Customer Support
EB
Ethan Brooks310
E
Escalation PathJul 14, 2026
D
Data Enricher89%
RM
Ravi MalhotraInformational
Approved
47,800
data-enricher
Data Ops
CL
Casey Lin1,593
E
Enrich RunJul 15, 2026
C
Contract Reviewer86%
JL
Jordan LeeLow Stakes
Approved
18,000
contract-reviewer
Legal Ops
JL
Jordan Lee600
M
MSA ReviewJul 17, 2026
D
Deployment Monitor97%
TV
Taylor VanceHigh Stakes
Pending Approval
64,000
deployment-monitor
DevOps
TV
Taylor Vance2,133
A
Alert TriageJul 20, 2026
E
Email Drafter93%
MW
Morgan WestLow Stakes
Approved
22,400
email-drafter
Comms Ops
MW
Morgan West747
O
Outbound CampaignJul 21, 2026
R
Report Builder85%
CL
Casey LopezInformational
Pending Approval
11,250
report-builder
Analytics
RW
Robin Wu375
W
Weekly DigestJul 23, 2026
R
Risk Classifier84%
RM
Reese MillerHigh Stakes
Approved
33,800
risk-classifier
Security
PL
Parker Lopez1,127
T
Threat ScanJul 24, 2026
P
Policy Enforcer96%
SYS
SystemLow Stakes
Approved
7,900
policy-enforcer
Governance
PW
Peyton Ward263
P
Policy SyncJul 25, 2026
O
Onboarding Agent90%
SP
Sunny PatelInformational
Pending Approval
55,200
onboarding-agent
Platform Ops
SP
Sunny Patel1,840
U
User JourneyS
Seat ActivationT
Trial ConversionJul 1, 2026 2:25 pm
Calculate
used by






open source
Основные возможности
Всё, что вам нужно, из коробки
Дашборды /Execution telemetry
⌘K
Total Runs (YTD)1.2M12%
Avg confidence94%5%
Auto-execute rate84%3%
Executions by month
403020100
12
16
14
22
27
24
31
ЯнвФевМарАпрМайИюнИюл
Executions by status
140Итого
1/2
Gated
Queued
Reviewing
Telemetry & Auditing01 / 07
Метрики, которым реально можно доверять.
Build custom dashboards from live execution data. Aggregate anything — skill runs, human overrides, agent activity — into charts your team actually reads.
Виджеты агрегации, столбчатые, линейные и круговые диаграммы
Filtered metrics from any skill or agent
Real-time run telemetry
Timeline
Tasks
Notes
Files
Emails
Calendar
К СДЕЛАНО3
Добавить задачу
Approve high-value refundVerify Stripe transaction history before approval token release.
Jul 22, 2026
Félix Malfait
Resolve policy conflictRoute conflict between refund_policy.md and user_sla.md.
Jul 24, 2026
Félix Malfait
Verify new skill versionReview compiled rules for route_support_ticket (v1.2.0).
Jul 26, 2026
Félix Malfait
ГОТОВО1
Audit security overrideVerify manual token release for admin operation.
Jul 18, 2026
Félix Malfait
Approval Tasks02 / 07
Human-in-the-loop oversight.
Approve held actions with one click
Assign review ownership and custom SLA times
Rich execution context attached to every task
Timeline
Tasks
Notes
Files
Emails
Calendar
Входящие4Написать
Audit: refund_policy.md UpdateSkill compiled successfully. Version 2.4.0 is ready for staging review.
Jun 24, 2026Token: human-approval GatedAction block triggered: refund request $450 from user_9213 requires human approval token.
Jun 23, 2026Conflict: policy_conflict FoundConflict detected between 'sla_policy.md' and 'escalation_runbook.md' in section 4. Please resolve.
Jun 20, 2026Feedback: skill_refinement AutoHigh number of manual corrections on skill 'route_support_ticket' triggered auto-recompilation recommendation.
Jun 18, 2026Channel Integration03 / 07
Every execution, in the right context.
Connect Slack, Discord, or custom APIs
Decisions and overrides logged to your audit trail
Full interaction history in one central feed
All Skills· 9
Skills
Trigger Type
Created By
Source Policy
Skill Owner
Gated
Executions
Domain
R
Refund HandlerStripe API
refund_policy.md
True
500
Billing
U
User ProvisioningOkta API
iam_policy.md
False
1,200
Identity
I
Incident EscalatorSlack Webhook
oncall_rotation.md
True
2,300
Operations
K
KB IndexerNotion Sync
API - Key name
wiki_sync.md
False
750
Knowledge
T
Token GaterOAuth Flow
Workflow name
security_gate.md
True
3,500
Security
C
CI Run CompilerGitHub Actions
ci_pipeline.md
True
900
DevOps
C
Customer RouterIntercom CRM
support_sla.md
False
1,800
Support
I
Invoice GeneratorStripe Billing
billing_runbook.md
True
4,200
Billing
D
Deploy TriggerVercel Webhook
G
Guillermo Rauchdeploy_guide.md
G
Guillermo RauchTrue
620
DevOps
Knowledge & Policies04 / 07
Your operational brain, fully mapped.
Custom skills and versioned policies
Unified timeline (agent actions, approvals, notes, files)
Full source provenance for every agent decision
By Status· 5
Gated2
Review1
Executed2
G
Github PR Auto-merge92% Conf.
System
Jan 25, 2026 9:26 PM
G
GitHub IntegrationN
Notion runbook sync84% Conf.
Feb 18, 2026 3:14 PM
N
Notion WorkspaceNew
R
Refund booking95% Conf.
Mar 10, 2026 9:26 PM
A
Airbnb APINew
F
Figma Token Export78% Conf.
System
Jan 15, 2026 9:27 PM
F
Figma IntegrationS
Stripe invoice dispute99% Conf.
System
Feb 2, 2026 11:02 AM
S
Stripe BillingNew
Skill Management05 / 07
Actions that execute themselves.
Custom approval stages for your skills
Drag-and-drop executions between gating tiers
Track confidence score and execution status
Timeline
Tasks
Notes
Files
Emails
Calendar
All4Add file
refund_policy.md
Jul 1, 2026
escalation_matrix.pdf
Jul 12, 2026
compliance_audit_2026.xlsx
Jul 18, 2026
mcp_config.json
Jul 20, 2026
Source Materials06 / 07
Policy reference without the chaos.
Multi-document compilation for skills
Upload, preview, and update policy files
Full text search across all policy sources
Импортированные данныеModusBrain fields
Policy Titleпример: Refund Policy
Skill Name
Action Scopeпример: stripe.refunds.create
Allowed APIs
Risk Tierпример: high-stakes
Gating Level
Policy Ownerпример: compliance-leads
Reviewer Token
Policy Import07 / 07
From text to executable skills in minutes.
Automated runbook import flow
Policy-to-rule mapping (including relations)
Export active skills as JSON anytime
Хватит мириться с компромиссами.
A modern knowledge layer with an intuitive interface
Built for latency
Compile policies and update safety gates instantly with a low-latency embedded database.
Live executions
Monitor agent executions as they run. View confidence scores and safety overrides in real time.
Single-pane control
Review safety gates, execution status, and compiled skill runbooks in one integrated interface.
01
02
03
Configuration
Full control with no extra engineering
Update a policy, change a risk tier, add an approval step. No engineering ticket required.
Knowledge model
Map sources and compile skills
Approval gates
Create a gating workflow
Audit view
Review execution logs and skill versions
Policies· 840
Domain
Навыки
22 поля
Навыки· 120
Source Policy
Executions
39 поля
Skill Versions· 48
Parent Skill
Policy Snapshot
8 поля
Executions· 64
Skill Version
Agent Context
11 поля
Approvals· 45
Skill
Execution
6 поля
Триггер
Skill is Triggered
Действие
Evaluate Risk Tier
Действие
Match Confidence
Действие
AI-агент
Действие
Log Telemetry
Действие
Request Override Token
Действие
Commit Audit Trail
Общие
URLrefund.ops.internal
Skill Owner
Dario Amodei
Source Policyrefund_policy.md
Gated✓ True
Executions500
Рабочее пространство
Навыки
Agents
Executions
Approvals
Audit Notes
Telemetry
Rule Chains▾
Rule Chains
Execution Runs
Rule Versions
+ New skill✧ Evaluate✎ Edit rules
Поля
Интерфейс (layout)
Общие
ОбщиеГотово
Skill Owner·Связь
Executions·Число
Дополнительно
Gated·Булево
Добавить секцию
Другое
Version·Число
Source Policy·Text
Activation date·Дата и время
Новые поля·Позиция/видимость по умолчанию для поля…
Добавить секцию
Give your agents a brain they can trust.
Open-source, self-hosted, and running in minutes.
Yes. ModusBrain is a self-hosted, source-available tool. A developer can install it, initialize a brain, and run the full compile → approve → execute → audit workflow locally or on their own infrastructure.
Install in minutes with Bun. Run `npm install -g @genthropic/modusbrain`, then `modusbrain init` to get a zero-config embedded database up and running. Your first operational skill can be compiled in under an hour.
ModusBrain reads wiki pages, policy documents, support tickets, runbooks, and any text-based knowledge source. You point it at your existing material and it drafts the skill from there.
When an agent goes to execute a skill, ModusBrain scores how confident it is that the skill applies to the current context. Low-confidence or high-stakes executions are held for human approval before any action is taken.
Yes. ModusBrain connects to your agents via MCP (Model Context Protocol) with OAuth-based access. Your agents call a skill by name and ModusBrain handles the versioning, gating, and logging.
The conflict is routed to a named owner instead of silently picking one answer. Teams can configure whether to serve the last-approved version or block execution entirely until the conflict is resolved.
The self-hosted open-source tier is free — full CLI, embedded database, and the complete operational-skills workflow. A hosted team tier with shared approval workflows and OAuth agent access is on the roadmap.

