Preloop - The Open-Source AI Agent Control Plane

Preloop is the open-source AI agent control plane. It unifies an MCP firewall for tool access, an AI model gateway for cost, safety and attribution, policy-as-code with human approvals, runtime session observability, and audit trails - in a single self-hostable platform.

Use Preloop to onboard existing agents with one command, and to deploy event-driven agentic automations with governed tools and budgets.

Works with OpenClaw, Claude Code, Codex CLI, Cursor, Gemini CLI, Hermes, OpenCode, Windsurf, and any MCP-compatible agent or managed runtime.

Run preloop agents discover and Preloop will find local agent configs, import representable MCP servers and model metadata, and transparently rewrite those agents to route tool calls through the Preloop MCP Firewall and model traffic through the Preloop Gateway. No SDK changes and no agent code changes required.

Build automations with templates like the Pull Request Reviewer, or write your own.

Official documentation: Full guides and tutorials at docs.preloop.ai.

# Install the standalone CLI
curl -fsSL https://preloop.ai/install/cli | sh

What is Preloop?

Preloop is a single open-source platform that covers the five jobs teams otherwise buy from four different vendors:

All shipped as Apache 2.0 software that runs on your infrastructure.

Why Preloop?

AI agents like Claude Code, Cursor, and OpenClaw are transforming how we work. But agents now deploy code, touch production data, change infrastructure, and spend money — and traditional IAM, prompt rules, and manual review were never built for that.

• Accidental deletions. One wrong command and your production database is gone.

• Leaked secrets. API keys pushed to public repos before anyone notices.

• Runaway costs. Agents spinning up expensive cloud resources without limits.

• Breaking changes. Untested deployments to production at 3am.

Most teams face an impossible choice: give AI full access and move fast (but dangerously), or lock everything down and lose the productivity gains.

Preloop solves this. Govern what agents are allowed to do, route risky actions to the right human, attribute model spend to the right team, and keep a searchable record of every important decision — without rebuilding your stack or instrumenting SDKs.

AI Agent → Preloop → [Policy check] → Allow / Deny / Require Approval → Execute
                   → [Gateway]       → Budget + attribution             → Model

Core Capabilities

Managed Agent Onboarding (preloop agents discover)

One command discovers and enrolls existing local agents into your control plane.

preloop agents discover

Preloop inspects local configurations for Claude Code, Codex CLI, Cursor, Gemini CLI, Hermes, OpenClaw, OpenCode, and other MCP-compatible runtimes, imports representable MCP servers and model metadata into your account, mints a durable credential, backs up the existing config, and rewrites the local agent to use Preloop-managed endpoints. Legacy and current config locations are supported, JSON5/YAML parsing included. No SDK. No agent code changes.

Access Policies & Approval Workflows

Define fine-grained access controls for any AI tool or operation. Tools support multiple ordered access rules that evaluate in priority order. When an AI attempts a protected operation, Preloop pauses and notifies you:

• Instant notifications via mobile app, email, Slack, Mattermost, or custom webhook.

• One-tap approvals from your phone, watch, or desktop.

• Async approval mode lets the agent poll for status instead of blocking network hooks.

• Per-tool justification — require (or optionally request) the agent to explain why a tool is being called.

• Full Audit Trail — every action is logged with full context: what was attempted, the matched policy, execution duration, and who approved it.

Policy-as-Code

Define policies in YAML and manage via CLI or API to version-control your safeguards alongside your infrastructure:

# Example: Require approval for production deployments
version: "1.0"
metadata:
  name: "Production Safeguards"
  description: "Require approval before deploying"

approval_workflows:
  - name: "deploy-approval"
    timeout_seconds: 600
    required_approvals: 1
    async_approval: true

tools:
  - name: "bash"
    source: mcp
    approval_workflow: "deploy-approval"
    justification: required
    conditions:
      - expression: "args.command.contains('deploy') && args.command.contains('production')"
        action: require_approval

AI Model Gateway

Preloop safely routes model traffic on behalf of managed runtimes instead of handing provider credentials to potentially vulnerable agent containers.

• OpenAI-compatible (/openai/v1/models, /openai/v1/chat/completions, /openai/v1/responses) and Anthropic-compatible (/anthropic/v1/messages) endpoints with SSE streaming.

• Budget enforcement at account, flow, and subject scopes using configurable cost tracking limits.

• Allowed-model lists per account, flow, API key, or managed agent.

• Usage accounting persisted as a canonical ApiUsage ledger — token usage, estimated cost, runtime-principal attribution, and provider-neutral conversation previews.

• Secret custody — provider API keys stay with Preloop; runtimes receive short-lived gateway tokens instead of raw credentials.

Runtime Session Observability

A durable RuntimeSession layer gives you one timeline per managed runtime — flow executions today, and any onboarded CLI/desktop agent session going forward. Operator-scoped endpoints expose recent sessions plus captured gateway interactions so the console can drill from aggregate usage into a single session timeline. Operators can end a session explicitly; doing so updates runtime state, emits audit events, and refreshes managed-agent summaries.

Getting Started

Choose the path that matches what you want to evaluate:

• Fast public trial: deploy the self-contained Railway trial template. This gives you a public Preloop URL without manually provisioning a VM.

• Local laptop: install the OSS stack with the install script.

• Kubernetes/prod-like: use the Helm chart in helm/preloop.

Try Preloop OSS in 5 minutes

The Railway trial runs Preloop Console, API/gateway, worker/scheduler, Postgres with pgvector, and NATS in one Railway project. The default template is self-contained and does not depend on external managed databases or queues. It is intended for evaluation, not hardened production.

Until the public Railway template code is published, the button opens the checked-in template guide and service map in deploy/railway. After publishing, replace the link target with the Railway template URL.

Install locally

# Install the standalone CLI
curl -fsSL https://preloop.ai/install/cli | sh

# Install the OSS platform stack
curl -fsSL https://preloop.ai/install/oss | sh

Release smoke test for hosted trials

Before promoting a hosted trial template, verify that the public URL loads the console, /api/v1/health responds, first-user sign-in or sign-up works, preloop agents discover can target the public URL, one gateway model call appears in the UI, and one MCP policy event appears in the audit timeline.

For extended details detailing comprehensive Docker builds, Kubernetes Helm topologies, GraphQL configuration, WebSocket streaming channels, and deep .env definitions, refer to the Preloop Documentation Hub.

Production requirement: The SECRET_KEY environment variable is required in production. Without it, the application will refuse to start. In development, a default key is used with a warning. Generate a secure key with: python -c "import secrets; print(secrets.token_urlsafe(32))"

The Open-Source Alternative to AWS Bedrock AgentCore

Preloop covers the same core jobs as AWS Bedrock AgentCore (runtime, gateway, identity, observability, policy) but is open source, self-hostable, MCP-native, and vendor-neutral. Many teams adopt Preloop specifically as an open-source alternative to AWS Bedrock AgentCore when they want to avoid hyperscaler lock-in or need to run governance inside their own VPC or on-prem.

How Preloop Compares to Other Categories

Enterprise Features

Preloop Enterprise Edition extends the core open-source components with centralized RBAC capabilities:

Contact sales@preloop.ai for Enterprise Edition licensing requests.

Contributing

Contributions are welcome! Please see our Contributing Guidelines for details on how to get started.

License

Preloop is open source software licensed under the Apache License 2.0. Copyright (c) 2026 Spacecode AI Inc.