See EctoLedger in action

Watch how AI actions become provable audit evidence

EctoLedger records every AI decision, blocks unsafe actions before execution, and produces tamper-proof certificates you can verify offline.

Before you start

What this demo shows in under 10 minutes

How agent actions are captured in a tamper-evident timeline.
How guardrails and Tripwire block unsafe operations before execution.
How evidence is exported for independent verification.

Security Leads Compliance Teams Engineering Managers Auditors

Demo mode is optimized for fast evaluation. For production use, configure guard, policy, backend, and webhook settings explicitly.

Before you run demo

Prerequisites

What you need depends on how you run the demo. At minimum, choose one path below.

Rust 1.94+ — All native launcher and CLI demos (rustup recommended).
Docker — Only for the Docker demo (docker-compose.demo.yml). Not required for --demo launcher mode or SQLite.
LLM backend — At least one: Ollama (local), OpenAI, or Anthropic. For audit and orchestrate the primary LLM must be reachable; the Guard uses GUARD_LLM_BACKEND / GUARD_LLM_MODEL when GUARD_REQUIRED=true.
Node.js 20+ and npm — Only if you build or run the Tauri 2 desktop GUI (gui/). The Docker demo exposes the REST API and Observer only; no GUI.

How to use demo mode

Different ways to run the demo

You can try EctoLedger with zero config (embedded Postgres, auto LLM detection) or use Docker for a fully containerized stack.

Demo defaults prioritize fast evaluation. Before production rollout, explicitly configure guard, policy, backend mode, and webhook settings.

1. Launcher with `--demo` (zero config)

The native launcher starts an isolated embedded PostgreSQL instance on a separate port, auto-detects your LLM (OpenAI / Anthropic / Ollama), and sets ECTO_DEMO_MODE=true so the backend uses a separate demo database. No manual DB or API key setup required.

# macOS
./ectoledger-mac --demo

# Linux
./ectoledger-linux --demo

# Windows (PowerShell)
.\ectoledger-win.ps1 -demo

First run: pg-embed Postgres (~30 MB) and optionally Ollama + qwen2.5:0.5b (~500 MB) download once. Data lives in ~/.local/share/ectoledger/postgres-demo (Linux) or ~/Library/Application Support/ectoledger/postgres-demo (macOS). Use --reset-db --demo to wipe demo data.

2. Launcher without `--demo` (default stack)

Run the normal stack: backend + Tauri GUI. Uses your configured DATABASE_URL (or default Docker Postgres) and LLM. Good for development and real audits.

./ectoledger-mac    # or ectoledger-linux / ectoledger-win.ps1

3. Docker demo (no Rust or Node)

One command pulls the pre-built image and starts PostgreSQL 17, Ollama, and EctoLedger. Open http://localhost:3000 for the Observer dashboard. No Tauri GUI in Docker — use the launcher with --demo for the full desktop experience.

docker compose -f docker-compose.demo.yml up

To reset: docker compose -f docker-compose.demo.yml down -v

4. SQLite + `serve` (no Docker)

For a minimal local dashboard with no external database, set DATABASE_URL=sqlite://ledger.db and run cargo run -- serve. SQLite mode does not support audit, orchestrate, or anchor-session; use it for viewing sessions and exporting reports from existing data.

Full details: Zero-Config Demo and Demo Readme on GitHub.

Troubleshooting