Now in private beta

The Control Plane
for Enterprise AI

One layer between every human, agent, and model in your company. Full lineage. Per-action authorization. Auditable, always.

01Observability

A single ledger for every AI interaction

Every request, response, and downstream action — human or agentic — flows through one immutable log. Full lineage from prompt to tool call to outcome. Audit-ready from day one, across every model and every team.

modgud / ledger — live
streaming
TimeActorModelActionLat.Status
02Governance

Route every call. Enforce every policy.

Modgud intercepts every LLM call before it reaches a model. Cedar policies define what each agent can request, which model tier it can use, and how fast. Traffic shifts automatically when capacity, cost, or compliance demands it.

modgud / policy-engine
Agent Request
data-agent-7
Identity Check
Biscuit token
Policy Eval
Cedar engine
Model Router
Cost + tier
Response
Delivered
Active Policies
Rate limit100 req/min per agent
Model tierTier-2 allowed
Tool scopequery_db ∈ allow-list
03Identity

Agents with scoped, delegated identity

Every agent gets a cryptographically-bound credential — what it can touch, on whose behalf, and for how long. Delegation chains are explicit and auditable. Biscuit tokens carry the proof. When a token expires or a scope is revoked, the agent stops immediately.

modgud / identity
A
code-agent-91
agt_k7m2n9p4xq
ACTIVE
Issued by
alice@acme.com
Role
Code Reviewer
Created
2 hours ago
Issuer
modgud-ca.acme.com
Token expires in01:00:00
Delegation Chain
alice@acme.comcode-agent-91
Permission Scopes
file:readGRANTED
file:writeGRANTED
database:readREAD-ONLY
database:writeDENIED
comms:emailDENIED
vault:secretsDENIED
api:githubGRANTED
api:deployREAD-ONLY
04Economics

See what AI is actually producing

Real spend, real risk, real return — per agent, per team, per month. Know which agents are generating leverage and which are burning budget. Throttle high-risk agents automatically. Give your CFO an answer when they ask what AI costs and what it earns.

modgud / economics — May 2026
Total AI Spend
$124,820
+12% MoM
Avg Risk Score
2.4 / 10
−0.3 MoM
Blended ROI
318%
+28pp MoM
Active Agents
47
+5 this week
Top Agents by Spend
AgentSpendROIRiskStatus
code-review-bot
$21,800412%1.2active
data-pipeline-ai
$18,400380%2.8active
report-agent
$14,200120%5.6throttled
ci-test-agent
$11,900590%1.1active
ml-trainer-3
$9,600290%3.4active
cleanup-agent
$4,10040%7.2suspended