ACE Monorepo

Agent Certification Engine

---

Table of Contents

• About ACE
• Documentation
• Submodules
• Agents
  • Agents in agents/
  • Using CrewAI with a single agent
• Getting the Code
• Quick Start (Kubernetes)
  • 1. Prerequisites
  • 2. Run the setup wizard
  • 3. Services
  • 4. Day-to-day operations
  • 📚 Detailed setup guides (docs/setup/)
• Local Development (host processes)
• Certifier API service (Dockerized)
• Certifier Dev Tools
  • Dump a Langfuse trace into pipeline-compatible JSON
  • Run the full certification end-to-end
  • Render a certification report to PDF
• Admin Actions
  • Build Docker images locally
• Community & Contributing
• License

---

About ACE

ACE stands for Agent Certification Engine — a platform for evaluating, fault-injecting, and certifying autonomous agents under controlled chaos conditions. This monorepo aggregates every component required to run the platform end-to-end.

• Purpose. Produce reproducible certification reports that quantify how an agent behaves under faults, with evidence (traces, metrics, ground truth) preserved at every phase.
• Architecture. A GraphQL control plane (AgentCert) drives chaos experiments on Kubernetes; the certifier consumes the resulting Langfuse traces and emits a multi-phase certification artifact (JSON + PDF).
• Pipeline. Phase 0 (trace ingest) → Phase 1 (fault bucketing) → Phase 2 (statistical aggregation) → Phase 3 (certificate build).
• Local stack. MongoDB for persistence, Langfuse for OTEL trace storage, LiteLLM as the unified LLM gateway in front of Azure OpenAI.
• Layout. Each concern lives in its own submodule (see Submodules) so components can be versioned, built, and released independently.

---

Pipeline in action

Click the GIF to open the interactive version on the docs site.

---

Documentation

All project documentation lives in docs/:

Area	Where	What's inside
Setup & operations	docs/setup/	One-command bring-up, the three cluster routes, configuration & port reference, and the full experiment walkthrough. Start here to run the platform.
Architecture	docs/architecture.md	End-to-end system architecture of the control plane + certifier.
Workflow animation	docs/animated_archiecture/	Self-contained HTML animation of the AgentCert workflow (open in a browser).
Methodology	docs/Methodologies/	The certification methodology: introduction, experiment design, metrics, pipeline, certification, observations.
API	docs/api.md · docs/api-changes-features-api-fixes.md ·

New to the platform? Go straight to docs/setup/ and the Quick Start below.

---

Submodules

Module	Description
AgentCert	Core AgentCert platform — GraphQL control plane, auth, web UI
app-charts	Application Helm charts (e.g. sock-shop) + the install-app image
agent-charts	Agent Helm charts + the install-agent image
certifier	Certification engine (FastAPI pipeline → JSON + PDF report)
flash-agent	Flash agent implementation (the agent under test)
agent-sidecar	Sidecar that proxies the agent's LLM/MCP traffic
agentcert-stack	Full-stack deployment assets (LiteLLM setup, etc.)
chaos-charts	Chaos experiment & fault definitions (tracks master)
litmus-go	Litmus chaos experiment executors (Go)

---

Agents

Agents in agents/

agents/ collects every agent implementation considered or exercised while certifying an open-weight model against ACE's chaos/compliance scenarios — one place to find "what agent, from where, running on what framework."

This is the beginning of the README. Read the rest at the original. Read the full README ↗