eyeVesa eyeVesa Identity · Trust · Audit · [GitHub]
eyeVesa

The Gateway That Keeps
AI Agents in Check

eyeVesa gives autonomous AI agents cryptographic identity, enforces real-time authorization policies, and produces non-repudiable audit trails -- so enterprises can trust what their agents do.

[See How It Works]   [View on GitHub]

3Ed25519100%
Decision LayersCrypto IdentityAudit Integrity

The Problem

When AI agents access production systems, three questions have no good answer:

1. Who is this agent?
API keys can be stolen. JWTs can be leaked. There's no cryptographic proof tying an action to a specific agent identity.
2. Should this be allowed?
Static RBAC doesn't adapt. Either agents get full access (dangerous) or humans approve everything (slow). No middle ground.
3. Can we prove what happened?
When something goes wrong, logs can be tampered with. You need cryptographic proof of who did what, when, and why.

Core Capabilities

Every agent request passes through decision layers before reaching your production systems.

CapabilityDescription
Cryptographic Identity Every agent gets an Ed25519 keypair on registration. Requests are signed, verified, and non-repudiable. No more shared API keys.
Policy Engine & HITL OPA/Rego policies auto-allow low-risk actions, auto-deny dangerous ones, and route uncertain decisions to humans. Four layers of trust.
Trust Scoring Dynamic trust scores adapt in real-time. Good behavior earns trust (+0.01). Policy violations degrade it (-0.05). Low-trust agents get contained automatically.
Non-Repudiable Audit Every action is logged with an Ed25519 signature. Integrity verification is built-in. Tamper-proof evidence for compliance.
Agent Delegation Agents can delegate scoped, time-limited authority to sub-agents. Depth limits prevent unbounded chains. Every delegation is tracked.
mTLS + SPIRE Zero-trust networking with SPIFFE/SPIRE workload identity. Every service-to-service call is mutually authenticated via mTLS.

How It Works

Four layers decide every agent action in milliseconds:

1 AUTO-DENY -- Hard blocks, no override [DENY]
Bank transfers over $5,000. Trust below 0.1. Budget exceeded. Instantly denied. Trust -= 0.05
2 AUTO-ALLOW -- Low-risk, no human needed [ALLOW]
Trust > 0.8 + low-risk resource. Read-only operations. Scaling within limits. Trust += 0.01
3 HUMAN-IN-THE-LOOP -- Needs human judgment [HITL]
Production deployments. Bank transfers $100-$500. Restricted data with trust < 0.8. Pending until human approves.
4 ESCALATION -- Needs multiple approvals [ESCALATE]
Bank transfers over $1,000. Database schema changes. Requires 2+ separate sign-offs.

Trust Scoring

Trust is earned, not given. Agents start at 1.0 and adapt based on behavior.

OutcomeTrust ChangeEffect
Successful call+0.01Gradually earns more autonomy
Policy denied-0.05Restricted until recovered
Budget exceeded-0.10Severe restriction
Never-event violationBLOCKEDAuto-deny, no override

Trust Thresholds:

Use Cases

Where autonomous agents meet real consequences.

1. DevOps / SRE -- 3am Incident Response

Agent reads logs.......... [AUTO-ALLOW]
Scales up service......... [AUTO-ALLOW]
Deploys hotfix............ [HITL] -- 1 human tap

4 minutes total. Full audit trail. No 3am pages.

2. Finance / Banking -- Automated Transfers

$50 transfer............. [AUTO-ALLOW]
$300 transfer............ [HITL] -- manager approves
$6,000 transfer.......... [AUTO-DENY]

Hard limits enforced. Cryptographic audit for compliance.

3. Healthcare / Pharma -- PHI Access Control

Query public data........ [AUTO-ALLOW]
Access patient records... [HITL]
Bulk data export......... [AUTO-DENY]

HIPAA compliant. PHI access audit with proofs.

Architecture

Dual-protocol gateway: Rust core proxies to Go control plane for auth, registration, and crypto.

    +-------------------------------------------------------+
    |                     ENTERPRISE                        |
    |                                                       |
    |  +-------------+  +-------------+  +--------------+   |
    |  | K8s Adapter |  |  DB Adapter |  | Slack Adapter |   |
    |  |  (Go :8443) |  |  (Go :8443) |  |  (Go :8443)   |   |
    |  +------+------+  +------+------+  +------+-------+   |
    |         |                 |                |           |
    |         +--------+--------+----------------+           |
    |                  |                                     |
    |                  v                                     |
    |       +----------------------+                        |
    |       |   eyeVesa Gateway    |                        |
    |       |                      |                        |
    |       |  +----------------+ |                        |
    |       |  | Gateway Core   | |                        |
    |       |  | (Rust :9443)   | |                        |
    |       |  | mTLS, proxy,  | |                        |
    |       |  | crypto, MCP    | |                        |
    |       |  +----------------+ |                        |
    |       |                      |                        |
    |       |  +----------------+ |                        |
    |       |  | Control Plane  | |                        |
    |       |  | (Go :8080)     | |                        |
    |       |  | REST, gRPC,    | |                        |
    |       |  | HITL, audit    | |                        |
    |       |  +--------+-------+ |                        |
    |       +----------+----------+                        |
    |                  |                                     |
    |    +-------------+-------------+                     |
    |    |             |             |                     |
    |    v             v             v                     |
    | +----------+ +---------+ +---------+               |
    | |PostgreSQL| |  SPIRE  | |   OPA   |               |
    | |+pgvector | |Identity | | Policy  |               |
    | | :5432    | |:8081/90 | | :8181   |               |
    | +----------+ +---------+ +---------+               |
    |                                                       |
    | +-----------------------------------------------+   |
    | | Agent SDK (Rust)                               |   |
    | | connect() -> discover() -> invoke() -> delegate()|   |
    | +-----------------------------------------------+   |
    +-------------------------------------------------------+

Request Flow

From agent action to audit log in 12 steps:

     1. Agent registers            -> POST /v1/agents/register  -> PostgreSQL
     2. Resource registers         -> POST /v1/resources/register -> PostgreSQL
     3. Agent connects via SDK     -> mTLS to Gateway Core (:9443)
     4. Agent discovers tools      -> GET /v1/agents/{id}
     5. Agent invokes a tool       -> Ed25519-signed MCP request
     6. Gateway verifies signature
     7. Gateway checks policy       -> OPA evaluates Rego rules
     8. If HITL required            -> Write to hitl_approvals, notify human
     9. If allowed                  -> Proxy MCP request to Resource Adapter
    10. Result returns              -> Agent gets response + trust score
    11. Audit log written           -> Ed25519-signed entry
    12. Trust score updated         -> +0.01 or -0.05

Who Benefits

ScoreRoleBenefit
95CISO / SecurityCryptographic identity, tamper-proof audit, trust degradation. Proof and control.
90DevOps / SREAuto-handle 80% of ops. Only woken for HITL approvals.
85Compliance / LegalSigned audit trail. Defensible evidence for regulators.
75Enterprise ITOne registry, one policy engine, one audit source.
65Agent DevelopersStandard SDK: connect() -> discover() -> invoke().
60Business LeadersFewer incidents, simplified compliance, reduced risk.

Connect with Hermes Agent

Hermes is a self-improving autonomous AI agent by Nous Research. It features 70+ built-in tools, MCP client/server support, persistent memory, and runs on 20+ messaging platforms. Here's how to connect it to eyeVesa for identity, authorization, and audit.

Install Hermes

curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash

Register Hermes as an Agent

curl -X POST http://localhost:8080/v1/agents/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "hermes-ops",
    "owner": "org:devops",
    "capabilities": ["infrastructure_read", "infrastructure_write", "deployment"],
    "allowed_tools": ["k8s_deploy", "k8s_scale", "log_search", "incident_create"],
    "max_budget_usd": 500.0,
    "delegation_policy": "single_level",
    "behavioral_tags": ["production", "sre", "high_autonomy"]
  }'

Configure Hermes MCP to Use Gateway

mcp_servers:
  agentid-gateway:
    url: "http://localhost:9443/v1/mcp"
    headers:
      X-Agent-ID: "YOUR-AGENT-ID"
    tools:
      include: [tools/list, tools/call, resources/list, prompts/list]

Set Environment Variables

EYEVESA_AGENT_ID=your-agent-id-here
EYEVESA_AGENT_NAME=hermes-ops
EYEVESA_AGENT_OWNER=org:devops
EYEVESA_GATEWAY=https://gateway.yourcompany.com:9443
EYEVESA_KEY_PATH=/run/secrets/hermes.key

Two-Layer Security

LayerSystemWhat it Controls
Hermes approvalHermes AgentShould this shell command run? (local process safety)
eyeVesa authorizationAgentID GatewayShould this agent identity access this enterprise resource? (remote access policy)

Decision Flow

    User sends message to Hermes (Telegram/Discord/CLI)
      |
      +-- Hermes LLM reasons about the request
      |
      +-- Is it an enterprise resource? (via AgentID Gateway MCP)
            |
            +-- Gateway verifies Ed25519 identity
            |
            +-- Gateway evaluates OPA policy
            |     +-- AUTO-DENY  (trust < 0.1, budget exceeded, never event)
            |     +-- AUTO-ALLOW (trust > 0.8, low-risk, tool in allowed_tools)
            |     +-- HITL       (production deploy, bank transfer > $100)
            |
            +-- Gateway signs audit log entry
            |
            +-- Gateway returns result + trust delta to Hermes

[Full Hermes Setup Guide]

Quick Start

Get running in under 5 minutes.

Start Infrastructure

docker-compose up -d

Start Gateway

# Terminal 1: Gateway core (Rust proxy)
cd gateway/core && cargo run

# Terminal 2: Control plane (Go API)
cd gateway/control-plane && go run cmd/api/main.go

Register an Agent

curl -X POST http://localhost:8080/v1/agents/register \
  -H "Content-Type: application/json" \
  -d '{"name":"hermes-ops","owner":"org:devops",
       "capabilities":["infrastructure_read","deployment"],
       "allowed_tools":["k8s_deploy","log_search"]}'

Verify Services

curl http://localhost:8080/health     # Control plane
curl http://localhost:9443/health     # Gateway core
curl http://localhost:8181/v1/data/agentid/authz/allow  # OPA

Ready to Put Guardrails on Your AI Agents?

eyeVesa gives you cryptographic identity, real-time policy enforcement,
and non-repudiable audit trails -- so your agents can act autonomously
without putting production at risk.

[Get Started on GitHub]   [View Architecture]

eyeVesa eyeVesa
Identity and trust layer for the agentic economy. 		Product
Features
How It Works
Use Cases
Architecture 		Developers
GitHub
Quick Start
Documentation 		Stack
Rust Gateway
Go Control Plane
PostgreSQL
OPA/Rego

© 2026 eyeVesa. Proprietary license.