Skip to main content
Glama

๐Ÿ›ก๏ธ AegisCore: The Zero-Trust Deterministic Governance Enclave for AI Agents

npm version npm sdk PyPI version License CI Zero-Trust DPDP Ready

AegisCore is an open-source reverse-proxy, deterministic invariant policy enclave, and cryptographic WORM audit ledger for autonomous AI agents. It intercepts model tool calls, validates them against strict schemas and deterministic invariants, and only executes approved actions within an isolated boundary.


๐Ÿ“บ Terminal Showcases & Scenario Deep-Dives

Scenario 01: Model Tool Hijack & Data Exfiltration Defense

Threat Vector: Indirect prompt injection instructs an autonomous agent to dump users.credentials.
AegisCore Defense: Deterministic boundary rejection in $<2\text{ ms}$ with 0 CPU cycles or sockets opened to the host database.

Run live: node --experimental-strip-types scripts/demo-scenario-1.js


Scenario 02: In-Flight DPDP PII Masking & Cryptographic Shredding

Threat Vector: Agent processes personal identifiers (Indian PAN / Aadhaar), conflicting with statutory Right to Erasure under India's DPDP Act.
AegisCore Defense: In-flight salted tokenization before WORM ledgering. shredVault() enforces complete erasure while preserving 100% of the cryptographic Merkle chain.

Run live: node --experimental-strip-types scripts/demo-scenario-2.js


Scenario 03: Cryptographic Merkle Chain & Tamper-Evident Audit

Threat Vector: Retrospective tampering of agent execution logs to conceal unauthorized actions.
AegisCore Defense: Write-Once-Read-Many (WORM) append-only ledger with cryptographic SHA-256 block traversal back to Genesis. Any bit alteration breaks chain validation.

Run live: node --experimental-strip-types scripts/demo-scenario-3.js


๐Ÿ“ฆ Developer Packages & Distribution

Package

Language / Protocol

Status

Description

@aegiscore-ai/core

Node.js / TypeScript (v0.1.1)

Available

Core deterministic engine, WORM ledger, bundled policies, and HTTP gateway daemon

@aegiscore-ai/sdk

TypeScript (v0.1.1)

Available

Zero-dependency client for OpenAI tool calls, LangGraph, and MCP with full parity

aegiscore-ai

Python (>=3.8, v0.1.1)

Available

Zero-dependency Python client for LangGraph, CrewAI, AutoGen (pip install aegiscore-ai)

MCP Adapter

JSON-RPC Stdio

Available

Native sidecar for Claude Desktop, Cursor, and LibreChat

DPDP Guide

Documentation

Complete

India DPDP Act 2023 compliance architecture & cryptographic shredding

Audit Report

Security & Audit

Certified (v0.1.1)

External production readiness audit, DevSecOps report & empirical benchmarks

Show HN

Community

Ready

Hacker News launch narrative & technical breakdown


Related MCP server: Security Guard MCP

โšก Empirical Performance & Security Audit (v0.1.1)

AegisCore underwent an end-to-end production readiness audit, fault isolation analysis, and high-concurrency stress testing by an external DevSecOps architect. Read the complete audit and verification report in AUDIT_REPORT.md.

Verified Micro-Benchmarks (v0.1.1)

Benchmark Metric

Measurement

Operational Impact

Cold Start Time

0.291 ms

Instant container startup with zero JVM/Python runtime warm-up

P50 (Median) Pipeline Overhead

58.2 ยตs (0.058 ms)

Negligible sub-millisecond impact on agentic loop latency

Average Execution Overhead

78.1 ยตs (0.078 ms)

Full invariant verification, PII tokenization, and Merkle chaining

In-Memory Gateway Throughput

>12,500 req/sec

Sustained high-concurrency event loops without thread contention

Memory Footprint Delta (1k reqs)

+1.30 MB Heap

Highly bounded GC pressure suitable for memory-constrained edge sidecars

WORM Ledger Tamper Detection

100% Deterministic

Pinpoints exact mutated entry index from Genesis hash pointer

TIP

Production Readiness Score: 9.5 / 10 (Enterprise), 9.8 / 10 (Startup), 9.6 / 10 (OSS).
All security findings (SEC-01 prototype pollution defense, SEC-02 persistent session rate-limiting, SEC-03 fail-closed CLI audit verification, SEC-04 strict metadata quarantine, SEC-05 atomic append ledger, and PKG-01/PKG-02 clean-slate packaging) are remediated and verified in Release v0.1.1. See AUDIT_REPORT.md.


โšก The Core Problem: Why Prompt Guardrails Fail

Modern AI agent architectures couple model intent directly to tool execution. Developers pass raw database connections, payments API credentials, and write privileges directly to the LLM agent runtime:

[User / Jailbreak Prompt] โ”€โ”€> [LLM Model Weights] โ”€โ”€> [Direct Tool Execution] โ”€โ”€> ๐Ÿ”ฅ Disaster

Why prompt guardrails cannot guarantee security:

  1. Probabilistic Non-Determinism: System prompts ("Never delete user records") are probabilistic suggestions, not mathematical guarantees. Adversarial jailbreaks, indirect prompt injections, and context drift routinely bypass prompt instructions.

  2. Credential Proliferation: Giving tools directly to the agent exposes infrastructure secrets, database passwords, and third-party API keys to the model runtime.

  3. Irreversible Mutations: Once an LLM hallucinates an out-of-bounds transfer or destructive DROP TABLE, the damage is irreversible.

The AegisCore Solution: Strict Intent-Execution Decoupling

AegisCore strips all execution power from the agent. The agent produces only an Intent Proposal. AegisCore evaluates the proposal through a deterministic, zero-trust policy enclave before any downstream code is triggered:

                                  AEGIS-CORE GATEWAY ENCLAVE
                             โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”
                             โ”‚ 1. DPDP PII Tokenizer & Vault          โ”‚
                             โ”‚ 2. Strict Schema Quarantine            โ”‚
[Agent Intent] โ”€โ”€(Proposal)โ”€โ”€>โ”‚ 3. Invariant Engine (Rate / Bounds)   โ”‚โ”€โ”€(Only if APPROVED)โ”€โ”€> [Isolated Execution Boundary]
                             โ”‚ 4. WORM Cryptographic Merkle Chain    โ”‚                          โ”‚ (Sanitized Env / Timeout)
                             โ”‚ 5. Asynchronous HITL Escalation Gating โ”‚                          โ–ผ
                             โ””โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”˜                 [Real Backend / DB / API]

๐Ÿ“Š Core Architecture

               +-------------------------------------------------------------+
               |                       AI AGENT LOOP                         |
               |             (LangGraph / MCP / Raw OpenAI)                  |
               +-------------------------------------------------------------+
                                              |
                                     (POST /v1/gateway/dispatch)
                                              v
+-------------------------------------------------------------------------------------------+
|                                 AEGIS-CORE GATEWAY PIPELINE                               |
|                                                                                           |
|  [Step 1: PII Sanitizer]   โ”€โ”€> Detects PAN, Aadhaar, Phone, Email & tokenizes via salt     |
|  [Step 2: Schema Validate] โ”€โ”€> Enforces strict types; extra fields fail closed            |
|  [Step 3: Policy Engine]   โ”€โ”€> Invariants: param_boundary, rate_limit, disallowed_targets  |
|                                                                                           |
|       |                              |                                       |            |
|       | (BLOCKED)                    | (REQUIRES_HITL)                       | (APPROVED) |
|       v                              v                                       v            |
|  [WORM Ledger Entry]        [HITL Challenge Created]                   [WORM Ledger Entry]|
|  Return 403 Forbidden       Wait for Supervisor Signoff               Dispatch to Sandbox |
+------------------------------------------------------------------------------|------------+
                                                                               v
                                                          +---------------------------------+
                                                          |    ISOLATED SANDBOX RUNNER      |
                                                          |  - process.env secrets scrubbed |
                                                          |  - Hard safety timeout abort    |
                                                          |  - Stack trace leak isolation   |
                                                          +---------------------------------+
                                                                               |
                                                                               v
                                                                  [Protected Real System]

๐Ÿš€ 60-Second Quickstart

Option A: Local CLI

# Clone and verify
git clone https://github.com/Sandeep-Hipparagi/aegis-core.git
cd aegis-core

# Run full test suite (37 tests across 10 suites)
npm test

# Start HTTP Gateway daemon on port 8080
node --experimental-strip-types bin/aegis.ts start --port 8080

Option B: Docker Compose

# Spin up AegisCore gateway with persistent audit volume
docker compose up -d

# Check health
curl http://localhost:8080/health
# {"status":"healthy","version":"0.1.1"}

Option C: Run Banking Invariant Demonstration

npm run demo:banking

๐Ÿงฉ Model Context Protocol (MCP) Integration

AegisCore provides a native stdio Model Context Protocol (MCP) server.

Claude Desktop Setup

Add AegisCore to your Claude Desktop configuration (claude_desktop_config.json):

macOS / Linux:

{
  "mcpServers": {
    "aegiscore": {
      "command": "node",
      "args": ["--experimental-strip-types", "/path/to/AegisCore/bin/aegis.ts", "mcp"]
    }
  }
}

Windows:

{
  "mcpServers": {
    "aegiscore": {
      "command": "node",
      "args": ["--experimental-strip-types", "C:\\Users\\username\\Downloads\\AegisCore\\bin\\aegis.ts", "mcp"]
    }
  }
}

Cursor IDE Setup

In Cursor Settings โž” Features โž” MCP Servers โž” Add New MCP Server:

  • Name: AegisCore

  • Type: command

  • Command: node --experimental-strip-types <PATH_TO_AEGISCORE>/bin/aegis.ts mcp


๐Ÿ’Ž Feature Matrix

Feature

AegisCore Guarantee

Traditional Prompt Guardrails

Schema Quarantine

Fail-closed. Extra or injected fields throw REJECTED_SCHEMA immediately.

Vulnerable to prompt injection parameter smuggling.

Invariant Policy Engine

Deterministic. Mathematical rules (e.g., amount <= 10000, max 5 calls/min).

Probabilistic instructions that degrade with conversation length.

DPDP Compliance

Automated. Aadhaar, PAN, phone numbers & emails tokenized; vault shredding.

Raw PII permanently leaked into model context & logs.

WORM Audit Ledger

Cryptographic Merkle Chain. SHA-256 hash chaining detects any tampering.

Mutable, unchained plain text log files.

Ephemeral Sandbox

Scrubbed Environment. process.env stripped of keys; timeout guards.

Full environment and network socket access given to LLM.

Async HITL Gating

Cryptographic Gating. High-risk actions held in PENDING state until signed.

"Please ask user" prompts easily bypassed by prompt injection.


๐Ÿ›ก๏ธ Pre-Configured Policy Packs

AegisCore ships with enterprise policy packs in /policies:

  • policies/dpdp-india.json: Enforces India's Digital Personal Data Protection Act. Restricts bulk customer data exports, blocks unmasked identity table access, and requires Data Protection Officer authorization for customer profile purges.

  • policies/fintech-guardrails.json: Enforces transaction ceilings, whitelists operating currencies (USD, EUR, INR, GBP), and requires dual-custody supervisor approval for transactions over $25,000.

  • policies/banking-policy.json: Limits autonomous transfers to $10,000, blocks sanctioned/blacklisted destinations, and escalates mid-value transfers.

  • policies/data-governance.json: Prohibits destructive DDL statements (DROP TABLE, TRUNCATE) and unauthorized account deletions.


๐Ÿ“œ HTTP Gateway API Reference

POST /v1/gateway/dispatch

Submit an intent proposal for evaluation and execution.

curl -X POST http://localhost:8080/v1/gateway/dispatch \
  -H "Content-Type: application/json" \
  -d '{
    "tool": "transfer_funds",
    "parameters": {
      "amount": 250,
      "recipient": "ACC-SUPPLIER-01"
    },
    "context": {
      "sessionId": "sess-prod-001",
      "agentId": "copilot-agent",
      "role": "finance-operator"
    }
  }'

POST /v1/hitl/challenges/:ticketId/resolve

Resolve a pending Human-in-the-Loop approval challenge.

curl -X POST http://localhost:8080/v1/hitl/challenges/hitl-uuid-1234/resolve \
  -H "Content-Type: application/json" \
  -d '{
    "decision": "APPROVED",
    "approverSignature": "sig-compliance-officer-99"
  }'

GET /v1/audit/integrity

Cryptographically verify ledger Merkle chain integrity.

curl http://localhost:8080/v1/audit/integrity
# {"isValid":true}

๐Ÿค Contributing

We welcome community contributions! Please review CONTRIBUTING.md for local environment setup, zero-trust invariants, and pull request guidelines.


๐Ÿ“„ License

Licensed under the Apache License 2.0. See LICENSE for details.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    F
    maintenance
    Deterministic agentic data firewall that secures, monitors, and controls AI agent interactions with data and software via MCP, preventing data leaks.
    290
    GPL 3.0
  • A
    license
    Not graded
    quality
    D
    maintenance
    Enables secure interaction between LLMs and MCP tools by applying zero-trust security controls, including sensitive data masking, file system protection, and policy enforcement.
    MIT
  • A
    license
    B
    quality
    A
    maintenance
    A governance proxy for AI tools โ€” every MCP/agent tool call is policy-gated, secret-redacted, and written to a hash-chained, offline-verifiable audit trail.
    13
    MIT
  • F
    license
    Not graded
    quality
    D
    maintenance
    A governed MCP server with OAuth 2.1 + PKCE, declarative tool scoping, row-level data filters, per-identity rate limits, and a tamper-evident audit trail.
    -