midas

MIDAS

Authority governance engine for autonomous decisions.

MIDAS determines whether an automated agent is within authority to perform a consequential action. Every evaluation produces exactly one outcome and one tamper-evident audit envelope — capturing what was requested, what authority was resolved, and why the outcome was reached.

Explorer

When MIDAS starts in memory mode, an interactive developer sandbox is available immediately:

http://localhost:8080/explorer

Open it in a browser. Demo scenarios (accept, escalate, reject, request clarification) are pre-loaded and ready to run — no configuration, no curl commands, no auth required in default mode.

Explorer runs on an isolated in-memory store. Requests sent through it never touch the configured backend. It is a developer tool only — do not expose it in production.

Quick Start

Memory mode (no dependencies)

go run ./cmd/midas

Then open http://localhost:8080/explorer.

Docker Compose (Postgres)

docker compose up

Starts Postgres 16 and MIDAS together. Schema applied automatically on startup.

⚠️ The default compose file sets MIDAS_AUTH_MODE=open for local convenience. Before exposing MIDAS to a network, set MIDAS_AUTH_MODE=required and configure MIDAS_AUTH_TOKENS. See Authentication.

First API evaluation

curl -s -X POST http://localhost:8080/v1/evaluate \
  -H "Content-Type: application/json" \
  -d '{
    "surface_id":     "surf-loan-auto-approval",
    "agent_id":       "agent-credit-001",
    "confidence":     0.91,
    "consequence":    {"type": "monetary", "amount": 4500, "currency": "GBP"},
    "context":        {"customer_id": "C-8821", "risk_band": "low"},
    "request_id":     "req-demo-001",
    "request_source": "lending-service"
  }' | jq .

Expected response:

{
  "outcome":     "accept",
  "reason":      "WITHIN_AUTHORITY",
  "envelope_id": "...",
  "policy_mode": "noop"
}

Retrieve the full governance record:

curl http://localhost:8080/v1/decisions/request/req-demo-001?source=lending-service | jq .

Authority Model

Authority flows in one direction:

DecisionSurface → AuthorityProfile → AuthorityGrant → Agent

Surface — what is governed (a business decision boundary). Carries name, domain, owner, required context keys. Does not carry thresholds.

Profile — how much authority is permitted on a surface. Carries confidence threshold, consequence limit, escalation mode, policy reference.

Grant — thin link from an agent to a profile. No governance semantics of its own.

Agent — any autonomous actor: AI model, automated service, or human operator.

See docs/core/authority-model.md.

Integrity Guarantee

Every evaluation is atomic, deterministic, and produces a tamper-evident audit chain. The envelope — outcome, authority evidence, audit events — is written in a single database transaction. Either everything commits or nothing does.

Audit events are hash-chained in sequence. Each event's SHA-256 hash is derived from the previous event's hash. The final event hash is anchored in the envelope's Integrity section. If any event is modified, deleted, or inserted after the fact, the chain breaks at that point.

Verification requires only the stored event hashes and the anchored final hash on the envelope — not access to application secrets. See docs/core/envelope-integrity.md.

Configuration

Database

The schema is applied automatically at startup (internal/store/postgres/schema.sql). No separate migration step is needed.

Authentication

Generate tokens with openssl rand -base64 32, then:

export MIDAS_AUTH_TOKENS="<token>|svc:deploy|platform.operator;<token2>|user:alice|platform.admin,governance.approver"

Roles: platform.admin, platform.operator, platform.viewer, governance.approver, governance.reviewer.

Key environment variables

Full variable reference: docs/operations/deployment.md.

Documentation

License

Apache License 2.0