Open-source AI Governance Platform
The control plane for enterprise AI systems.
The platform governs the AI agents, workflows, and decisions your teams operate across frameworks and model providers. Doesn't replace your AI stack. It makes AI change versioned, governed, explainable, auditable and replayable.
Keep your AI runtime. Add governance.
01
AI Agents & Applications
HR Agent · Support Copilot
02
Workflows & Frameworks
Orchestration Runtime
03
Models & Providers
Your chosen model stack
AI GOVERNANCE
governance control plane
Governance evidence connects to every stage; execution remains yours.
Make every AI action
legible before it lands.
The control plane turns AI execution activity into governed, explainable records as the system operates.
Execution Record
A flight deck for every execution.
Every execution becomes a live decision surface where signals, policies, evidence and outcomes remain connected.
Hover a layer to bring its decision stream forward.
01 / Replay
Replay the evidence, not the incident.
The control plane turns a past execution into a governed reproduction. The original remains intact; the replay becomes new evidence with explicit lineage.
02 / Ontology
Lineage stays alive.
Governed assets are not isolated records. Their versions, evidence, policies, and decisions remain connected in a graph you can inspect at any time.
Nodes glow. Edges light. Evidence stays connected.
03 / Evaluation
Measure what the system is becoming.
Live evaluation turns model behavior into metrics you can compare, review, and attach to governance decisions before a regression becomes production reality.
Onboarding
Choose the path that matches your role
AI Governance Platform is useful to different teams for different reasons. Start with the shortest path to a concrete outcome.
Developer
Integrate governed observations
Connect a runtime or service to the control plane through REST or MCP while keeping your execution stack in place.
Explore integrationML / AI engineer
Run a governed evaluation
Configure an evaluator, Runtime Connection, dataset, prompt, and model; then follow live progress and inspect item-level scores.
Follow the evaluation tutorialGovernance / risk
Author policy and review evidence
Create versioned governance rules, simulate their outcomes, and apply a consistent review process to decisions.
Explore policy controlsCTO / CEO
Assess the operating model
See what the control plane owns, how policy turns evidence into decisions, and what remains with your runtime and deployment systems.
Explore the architectureArchitecture
Process Flow
One control plane keeps governance, evaluation, replay, durable work, and lineage behind explicit boundaries.
Observe. Evaluate. Govern. Replay.
Hover a plane to trace its live exchange. White orbit: one complete execution.
Capabilities
Core Governance Building Blocks
Each subsystem is exposed through REST APIs and MCP tools.
Job Execution Control Plane
Record and execute long-running governance work — evaluations, experiments, replay, and drift analysis — with durable lifecycle tracking.
Evaluation Plane
Turn workflow outputs into evaluation results using pluggable providers. Providers sit behind contracts, not platform boundaries.
Governance Ontology
A semantic graph describing relationships between governed assets — prompts, models, datasets, decisions, and evidence.
Governance Decisions
Explainable, auditable outcomes generated from evidence and policy. Trace lineage from decision back to every supporting artifact.
MCP Server
Expose governed read and controlled-write operations to agents through auditable MCP tools, each delegating to one REST endpoint.
Settings Control Plane
Typed configuration with SYSTEM, ORGANIZATION and PROJECT scopes. Compare-and-set updates with versioned audit trails.
Audit & Replay
Capture workflow and node-level execution records. Reconstruct historical executions for investigation, debugging and governance review.
Drift Analysis
Compare evaluations over time, calculate drift and produce governance-oriented artifacts from historical data.
Replaceable Persistence
SQLite for local development, PostgreSQL for production, Snowflake for analytics. Repository contracts keep storage interchangeable.
Principles
Engineering Principles
AI Governance Platform is built to be operated in production. These constraints shape every interface.
Control Plane Ownership
AI Governance Platform owns governance state and decisions. It tracks assets, results, comparisons, rankings and recommendations — but never the live AI runtime or deployment system.
Explicit Contracts
Every boundary is visible in code. Repository interfaces, provider interfaces and framework-neutral APIs are all explicit contracts. Hidden cross-system contracts are avoided.
Immutable Artifacts
Governed records are immutable where possible. Mutable control flows create new records or versions instead of mutating historical facts.
Version Everything
Prompts, models, datasets and experiment-facing artifacts are versioned. Versioning is required for reproducibility, comparison, auditability and replay.
Replayability
If a governance decision cannot be reconstructed later, it is weak evidence. Replayability affects storage, versioning, immutability and API design.
Storage Independence
The platform does not depend on SQLite as a core architectural choice. Repository contracts preserve the ability to add PostgreSQL, Snowflake or other stores.
Provider Independence
Evaluation logic remains behind provider interfaces. TruLens is the current implementation, but the architecture should not require provider-specific knowledge.
Failure Isolation
Failures stop at the narrowest useful boundary. A provider failure should not silently mutate registry state. A transport adapter should not rerun ranking logic.
Interfaces
Evaluate Governance Decisions
The same governance operation is available over REST and as an auditable MCP tool. Every call is correlated and recorded.
POST /api/v1/decisions/evaluate
{
"subject_type": "agent_execution",
"subject_id": "execution-2048",
"policy_id": "production-ai-policy",
"evidence_ids": [
"eval-result-981",
"audit-event-477"
]
}
// 200 OK
{
"decision_id": "decision-991",
"outcome": "APPROVED",
"policy_version": "v1",
"reason": "All mandatory controls satisfied"
}Releases