Argy — the operating system for enterprise AI
One LLM Gateway, governed agents, and versioned An Argy module is a versioned workflow made of actions (nodes) and connections, with inputs/outputs schemas. It can behave like an agent with tools through its actions, including the Argy AI action (a module-specific subagent). (A golden path is a versioned module that is validated and approved by the organization. It captures best practices for governed self-service.) to industrialize AI and DevSecOps A workflow is an orchestrated sequence of actions (DAG). In Argy, workflows become versioned modules that can be governed and reused. with quotas, approvals, auditability, and compliance built in.
For CTO / VP Eng
Govern AI adoption, control spend, stay provider-independent.
For Platform / SRE
Publish golden paths, follow pipelines, measure DORA/SLO/drift/incidents.
For developers
Self‑service through modules: a clear schema, fewer tickets, faster execution.
Procurement-ready, enterprise by design
Give Security, Platform, and Procurement teams what they need to evaluate Argy quickly: governance boundaries, deployment modes, and evidence.
Currently in POCs with several large enterprise early adopters. References available under NDA.
If you have a security questionnaire, send it through the contact form: we reply with clear, auditable answers.
Argy — the operating system for enterprise AI
Argy sits between teams, models, and the Your toolchain is your set of tools (Git, CI/CD, cloud, IaC, security). Argy doesn’t replace them: it orchestrates them and standardizes the experience.: an LLM Gateway for every request, governed agents, and An Argy module is a versioned workflow made of actions (nodes) and connections, with inputs/outputs schemas. It can behave like an agent with tools through its actions, including the Argy AI action (a module-specific subagent). that industrialize A workflow is an orchestrated sequence of actions (DAG). In Argy, workflows become versioned modules that can be governed and reused..
Argy is the enterprise AI OS: standardize once, govern all AI usage, and ship safely across In Argy, a project groups an application/service and its environments (dev/staging/prod). It’s the unit where you apply modules, deployments, and policies. and environments.
From friction to autonomy—without losing control.
Argy turns workflows into modules: standardization, self‑service and governance become a system.
Before
Tickets for every need
After
Controlled self‑service via modules
Recurring requests become standardized capabilities.
Before
Snowflakes and one‑offs
After
Versioned golden paths
Standardize without friction: conventions + parameters.
Before
Late manual controls
After
Governance by design
Policies and guardrails embedded in delivery and run.
Make the business case in 60 seconds
Estimate potential savings using your assumptions (time reclaimed, reduced operational overhead). Indicative only.
Indicative only. Avoid double-counting and calibrate inputs to your baseline.
Start for freeEstimated annual savings
€0
Payback
n/a
Payback = monthly investment / estimated monthly savings.
What this model doesn't capture
- • Audit and compliance time saved
- • Incidents avoided through standardization
- • Faster onboarding and reduced attrition risk
- • AI cost control via quotas and routing
An operating system for enterprise AI
Industrialize AI and DevSecOps workflows without compromising security, governance, or sovereignty.
Centralize model access with multi-provider routing, quotas, audit logs, and security filters.
Deploy Argy Chat, Argy Code, and custom agents with policies, quotas, and full traceability through the LLM Gateway.
Ground answers on your indexed documents with tenant boundaries and access controls.
Package workflows into reusable, versioned modules (schema + actions + approvals) and publish golden paths.
Approval policies, audit logs, full traceability, and CSV exports.
EU SaaS, hybrid execution agents, or on‑prem LLM Gateway with keys in your perimeter.
A clear product journey—from creation to operations.
Argy structures the IDP experience: you publish capabilities, teams consume them in self‑service, governance follows.
Step 1
Configure the tenant
Set up SSO/SCIM, notification channels, LLM providers, quotas, and governance settings.
Step 2
Create a project
Create a project (service/application) and its environments (Dev/Staging/Prod).
Step 3
Pick a module
Select a module (golden path) and version from the catalog.
Step 4
Configure Dev / Staging / Prod
Configure inputs per environment. Apply approval policies where needed (e.g., production).
Step 5
Deploy
Argy orchestrates IaC and CI/CD to produce a consistent, traceable result.
Step 6
Observe
Follow runs with statuses, logs and outputs. Steer reliability with DORA metrics, SLOs, drift and incidents.
Step 7
Improve
Iterate safely: publish new versions, deprecate old ones, and refine governance and observability.
LLM Gateway — the entry point of the AI OS
A single, secure entry point for all your AI requests, with quotas, audit, and filtering.
Argy's LLM Gateway centralizes all calls to LLM providers (OpenAI, Anthropic, Mistral, xAI, Google, Azure OpenAI) with complete governance, and powers tenant-aware RAG (Retrieval-Augmented Generation) augments prompts with passages retrieved from your documents to deliver grounded, context-aware responses. and governed agents.
Multi-Providers
OpenAI, Anthropic, Mistral, xAI, Google, Azure OpenAI.
Quotas & budgets
Monthly token allocation by plan, quotas per org/team, and alert thresholds.
Intelligent Routing
Task-type routing, fallback chains, sovereignty policies, and cost-aware choices.
Security Filters
PII redaction, secret detection, prompt injection defense, forbidden topics, output masking.
Tenant-aware RAG
Embeddings + document indexing to ground answers on internal knowledge with tenant boundaries and access controls.
Complete Audit
Traceability per request (user/model/tenant), correlation IDs, retention and exports.
OpenAI-Compatible API
Seamless integration with your existing tools through an OpenAI-style API.
/v1/chat/completionsChat completions/v1/embeddingsEmbeddings (RAG (Retrieval-Augmented Generation) augments prompts with passages retrieved from your documents to deliver grounded, context-aware responses.)/v1/agent/stepsStructured agent steps/v1/modelsAvailable modelsExample Request
# Pick a model id from GET /v1/models
curl -X POST https://<your-llm-gateway>/v1/chat/completions \
-H "Authorization: Bearer <token>" \
-H "x-tenant-id: <tenant-id>" \
-H "x-org-id: <org-id>" \
-H "Content-Type: application/json" \
-d '{
"model": "<model-id>",
"messages": [{"role": "user", "content": "Hello!"}]
}'Argy Code — AI agent in the terminal
Interactive (TUI) and autonomous (argy run) modes for developers.
Argy Code is Argy’s developer CLI agent. Use interactive mode with human confirmations, or run autonomously in CI/CD with deterministic exit codes.
Interactive + autonomous
TUI for day‑to‑day work with confirmations, or argy run for non‑interactive automation.
Built-in tools
Bash execution, filesystem read/write, code search, and Git operations.
MCP integrations
Connect tools through Model Context Protocol (MCP).
Agent system
Build, Explore, and custom agents, with sub‑agent delegation (max depth 3).
Multi-channel distribution
Install via npm, Docker, or Homebrew.
Enterprise-ready auth
Authenticate using Device Flow (RFC 8628) and Personal Access Tokens (PAT).
Capabilities
Filesystem
- Read/write files
- Search code
- Parse AST
Git
- Status and diff
- Repository operations
Execution
- Run Bash commands
- Script automation
Integrations
- MCP servers
- Tool calling via MCP
Execution modes
Designed for daily dev work and non-interactive automation.
Autonomous runs return deterministic exit codes for CI/CD.
Flexible Deployment Options
Choose the model that fits your security, compliance, and sovereignty needs.
SaaS (Managed Cloud)
Argy runs on managed Azure infrastructure in the EU, with agents managed by Argy.
- Azure Kubernetes Service (AKS) — EU region: West Europe
- Agents managed by Argy
- 99.9% availability SLA
- Support included based on your plan
Hybrid (Self-Hosted Agent)
SaaS control plane + agents deployed in your infrastructure for sensitive actions.
- SaaS control plane (EU hosted)
- Execution agents deployed on your infrastructure
- Execute actions on internal resources without moving them
- Available from the Growth plan
On‑Premises (Kubernetes + LLM Gateway)
Deploy Argy on your Kubernetes environment, with a local LLM Gateway for strict sovereignty needs.
- Kubernetes deployment in your environment
- Local LLM Gateway (Enterprise + add-on)
- Designed for regulated and air‑gapped environments
- Helm charts available for deployment
SaaS architecture (high level)
Argy provides interfaces (portal/chat/CLI), an API gateway, and microservices, with an execution layer that can run in SaaS, hybrid, or on‑prem setups.
Security & Compliance
A platform built for regulated environments.
Passwordless-first IAM
WebAuthn/Passkeys (primary), Magic Link (fallback), OIDC/SAML (Entra ID, Okta, Google Workspace), Device Flow for terminals, and SCIM provisioning.
Granular RBAC
Predefined roles (PLATFORM_ADMIN, PLATFORM_ENGINEER, PLATFORM_PM, PLATFORM_USER, COMPLIANCE_APPROVER) designed for least privilege and separation of duties.
Immutable Audit Trail
Complete audit trail of every action with correlation IDs, 90-day minimum retention, and CSV exports.
Multi-Tenant Isolation
PostgreSQL Row-Level Security (RLS), per-tenant Redis key prefixes, validated `x-tenant-id`/`x-org-id` headers, and per-tenant storage partitioning.
Secrets Management
Integrations with Vault, Azure Key Vault, and AWS Secrets Manager.
Approval policies
Approval workflows, governance rules, and audit logs for sensitive actions.
Compliance & standards
99.9%
Availability SLA
90d
Audit retention (min.)
TLS 1.2+
Transport security
Automations you can ship in self‑service.
A clear view of what teams can automate—delivery, security, run, and governance.
Cloud & IaC
Provision and configure infrastructure across AWS/Azure/GCP, Kubernetes, and on-prem.
CI/CD
Trigger and orchestrate CI/CD steps on top of your existing tools.
Security
Embed security controls and validations into workflows.
Observability
Instrument, monitor, and page teams with ready-to-use actions.
Notifications
Notify teams and systems at every key step.
Documentation
Generate and publish documentation automatically.
Use cases
Concrete scenarios, outcomes-first: speed, autonomy, governance and reliability.
Industrializing DevSecOps (first use case)
Security comes too late: checklists, exceptions, and end-of-cycle rework.
- • Less rework
- • Explicit decisions
- • Measurable maturity
Governing enterprise AI
POCs multiply, API keys sprawl, and costs and risks are hard to control.
- • Controlled AI adoption
- • Full traceability
- • Vendor independence
Building assistants and AI agents
Each team experiments with agents without a shared framework or data boundaries.
- • Faster production rollout
- • Reusable workflows
- • Preserved confidentiality
Simple, transparent pricing
Choose the plan that fits your needs. Scale as you grow.
Managed SaaS for all plans. Hybrid from Growth. On-prem LLM Gateway in Enterprise.
Free
- Full Argy Console
- Standard module catalog
- Git integrations (GitHub, GitLab)
Growth
- Everything in Starter +
- Unlimited Argy Code
- Argy Chat included
Enterprise
- Everything in Growth +
- On-premises LLM Gateway
- Argy Chat included
No credit card required • 15% discount on annual plans • Cancel anytime
FAQ
Common questions.
Does Argy replace your existing tools?⌃
No. Argy integrates with your stack (Git, CI/CD, cloud, Kubernetes, observability, identity). Argy’s role is to standardize, automate, and govern through versioned modules (golden paths).
What is an Argy 'module'?⌃
An Argy module is a versioned workflow made of actions (nodes) and connections (DAG), with inputs/outputs schemas. It can behave like an agent with tools through its actions, including the Argy AI action (a module-specific subagent).
What is a Golden Path?⌃
A Golden Path is a versioned module that is validated and approved by the organization. It captures best practices and enables self-service with governance.
How does Argy govern LLM usage?⌃
Through the LLM Gateway: multi-provider routing, fallback chains, quotas, security filters (PII/secrets/prompt injection/forbidden topics), and full request auditability.
What about compliance and traceability?⌃
Approval policies, exportable audit logs (CSV), 90-day minimum retention, correlation IDs, and multi-tenant isolation (PostgreSQL RLS, Redis key prefixes, validated x-tenant-id/x-org-id headers).
Is Argy suitable for large enterprises?⌃
Yes. Argy is built for demanding environments: passwordless-first IAM, RBAC, approval workflows, full auditability, SaaS/hybrid/on‑prem options, and EU sovereignty posture (EU hosting).
European SaaS
GDPR compliant & hosted in EU
No Lock-in
Built on open standards
API-First
Everything is automatable
Ready to get started with Argy?
Start with the Free plan. Upgrade when you're ready, or contact us for an enterprise rollout.