Skip to content
Open · vendor-neutral · multi-agent

The control plane for AI agents at work.

Open, vendor-neutral operations layer for multi-agent AI ecosystems. Govern Claude Code, OpenAI Agents, LangGraph, MCP servers, OpenClaw, and custom enterprise agents from one operational surface.

MIT licensed
Self-hosted
Vendor-neutral
AGT-compatible
MCP-native
Queryable audit trail
SSO / OIDC ready
Fail-secure kill switch
The operator gap

AI agents are spreading faster than the operator model.

The problem is rarely local experimentation. The problem is what shows up when the same agents reach into production, across teams, runtimes, and compliance boundaries — with no shared operational surface.

01

Fragmented runtimes

Claude Code, OpenAI Agents, LangGraph, internal workflows — disconnected operators, disconnected policy.

02

Untrusted MCP servers

No allow-listing, approval flow, or audit trail for the capabilities agents are actually reaching.

03

Shadow AI workflows

Autonomous agents touching production systems without governance — and without anyone tracking which.

04

No queryable evidence

Security and legal cannot reconstruct what an agent did. Logs are scattered, untyped, and inconsistent.

05

No containment path

Kill switches and approval flows are scattered across tools — or missing entirely when an incident hits.

Capabilities

Everything flows through policy, approval, audit, and response.

One operator model. One queryable event stream. One containment path. Built so the same surface that ships policy also shows runtime posture and the evidence behind every decision.

Multi-agent fleet inventory

Mixed-runtime view of every connected agent: where it runs, what version, which policy, last heartbeat.

Claude Code
47
OpenAI Agents
12
LangGraph
8
MCP servers
23
OpenClaw
4

Centralized policy engine

One operator model for permissions, tool scopes, approval thresholds, and audit depth — published once.

MCP governance console

Operator surface for the MCP catalog, approval queue, and audit query — layered on AGT's MCPGateway where present, ClawForge interception elsewhere.

Approval workflows

Operator approvals for tool scopes, MCP servers, policy changes, and shell access — routed and timed-out.

Audit & evidence pipeline

Append-only event store. Query by agent, runtime, policy decision, or operator. Export evidence packs.

Fail-secure kill switch

Heartbeat-bounded propagation with a local fail-secure fallback. Containment that does not require connectivity.

AGT-compatible policy layer

Translate ClawForge policy into Microsoft AGT primitives where the runtime supports it.

Risk signals & anomaly detection

Surface unusual tool-call patterns, policy denials, and approval-rate drift across the fleet.

Operational surfaces

One operational surface across multiple agent ecosystems.

Policy engagement, queryable audit, MCP governance, and incident response — all reading from the same fleet, all queryable across runtimes.

How it works

A layered architecture, vendor-neutral by design.

ClawForge meets each runtime where it lives — local enforcement where supported, MCP proxying where it isn't, and an append-only audit pipeline either way.

Layer 01Agents

Mixed runtimes — what your enterprise actually runs.

Claude CodeOpenAI AgentsLangGraphOpenClawMCP serversCustom enterprise agents
Layer 02Adapters & interception

Where ClawForge meets each runtime. Local enforcement where supported, proxy where not.

HooksMCP proxyAGT integrationSDK adapters
Layer 03Governance runtime

Substrate that enforces policy at agent-edge. Standalone or on top of Microsoft AGT.

ClawForge engineMicrosoft AGT compatibilitySandboxingIdentity & scopes
Layer 04Control plane

Operator surface. Vendor-neutral, self-hosted, append-only.

PolicyApprovalsAudit & evidenceIncidentsAdmin consoleMCP catalog & approvals
Vendor-neutral governance
Multi-runtime visibility
Local enforcement where supported
Append-only audit pipeline
Self-hosted-first deployment
Microsoft AGT compatibility

AGT is the enforcement substrate. ClawForge is the operations layer above it.

AGT enforces policy on every tool call at the runtime layer — including MCP traffic via its own MCPGateway. ClawForge does not duplicate that. It's the operator console, approval workflow, policy distribution, and cross-runtime audit federation that turns a fleet of AGT deployments into one operable thing.

Substrate · runtime

What AGT enforces

  • Sub-millisecond per-tool-call policy enforcement
  • MCPGateway and MCPSecurityScanner for MCP traffic
  • Adapters for 20+ runtimes (LangChain, AutoGen, CrewAI, Semantic Kernel, OpenAI Agents SDK, Google ADK)
  • Append-only, hash-chained audit log per deployment
  • Four-tier privilege ring model and kill switches
  • OWASP Agentic Top 10 coverage at the runtime layer
Operations layer · console

What ClawForge operates

  • Operator console across many AGT deployments and non-AGT runtimes
  • Approval queue, routing, SLA, and approver audit — the destination AGT's human-approval hook calls into
  • MCP catalog, allow-list, and pending-approval surface above AGT's gateway
  • Cross-runtime audit federation (AGT logs + Claude Code, OpenClaw, custom agents)
  • Policy authoring, versioning, and fleet-wide distribution
  • Incident response with mixed-runtime kill-switch posture
  • Evidence packaging for security, legal, and compliance
Open source

Open source by design.
Vendor-neutral by intent.

ClawForge is MIT licensed, inspectable, self-hosted, and forkable. The control plane runs in your environment, on your storage, governing whichever agent runtimes you already use. No runtime lock-in, no proprietary policy format.

License & postureREADME.md

license MIT

deployment self-hosted-first

runtime-lock none

policy-format open · versioned

audit-store customer-hosted Postgres

contributors community-driven

Who it is for

Built for the teams operating AI agents at production scale.

Platform engineering

Standardize agent rollout, policy, and runtime governance across teams without rebuilding operator tooling per runtime.

What they get
  • Audit query across runtimes
  • Policy publish + propagation
  • One operator on call instead of N

Security & compliance

Approval workflows, queryable audit evidence, and operational containment — for AI agents and the MCP servers they reach.

AI platform teams

Govern custom AGT and LangGraph agents alongside Claude Code and OpenAI Agents from one operational surface.

Operate it like infrastructure

Operate AI agents like production infrastructure.

Open, vendor-neutral, multi-agent operations for enterprise AI systems. Run it where your team already manages risk.