Metadata-Version: 2.4
Name: agentx-security-sdk
Version: 0.2.7
Summary: The self-healing exception handler for autonomous AI agents.
Home-page: https://github.com/vdalal/semantic-gateway
Author: AgentX Core Team
Author-email: founders@agentx-core.com
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.8
Description-Content-Type: text/markdown
Requires-Dist: requests>=2.25.0
Dynamic: author
Dynamic: author-email
Dynamic: classifier
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# 🛡️ AgentX: The Semantic Firewall for AI Agents
[![Python 3.9+](https://img.shields.io/badge/python-3.9+-blue.svg)](https://www.python.org/downloads/)
[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

LLM Agents are brilliant, but they are incredibly brittle. They will drop your production database, leak AWS keys, and fall victim to prompt injections. Traditional firewalls just crash the agent by returning a `403 Forbidden`. 

**AgentX is different.** It is a neuro-symbolic edge gateway that intercepts dangerous tool calls, blocks them, and returns a **Socratic Challenge** back to the agent's context window—forcing the agent to rethink its strategy and self-correct *without crashing*.

### 🧠 Don't just block agents. Coach them.

---

## ⚡ 1. Two-Minute Quickstart (Zero-Configuration Protection)

AgentX requires **zero changes** to your underlying agentic logic, tools, or custom parameters payload schema. The SDK dynamically inspects function calls at runtime using an auto-reflective ingestion engine.

### Step 1: Install the SDK
```bash
pip install agentx-security-sdk
```

### Step 2: Decorate Sensitive Tool Operations
Simply attach the @agentx_protect decorator over any high-risk system mutation tools. The SDK automatically serializes execution signatures, tracks cognitive monologue frames across multi-turn retries, and protects your infrastructure.

```python
from agentx_sdk import agentx_protect

@agentx_protect(agent_id="production_database_worker")
def drop_client_records(confirm: str):
    # Your native code runs untouched past the firewall boundary
    db.execute(f"DELETE FROM users WHERE confirm_token = {confirm}")
```

### Step 3: Configure Environment Boundry Flags

Copy .env.example to .env and add your API keys (AGENTX_API_KEY, CONTROL_PLANE_URL, GEMINI_API_KEY).

### Step 4: Spin up the Edge Gateway
AgentX requires an Edge node to process heuristics and embeddings at sub-millisecond speeds.
Boot the gateway:

```bash
docker-compose up -d
```

The gateway is now listening on http://localhost:8000 and mirroring policies from your Control Plane.

---

### Step 4: Run the Simulation
Watch the AgentX Gateway coach a rogue agent in real-time.

```bash 
python examples/01_self_healing_agent.py
```

```text
════════════════════════════════════════════════════════════
 🛡️  AgentX Session Summary (Trace: 7012938b-4cde-4bea-aac8)
════════════════════════════════════════════════════════════
 ⏱️  Uptime:                15.49 seconds
 🛠️  Tools Monitored:       2
────────────────────────────────────────────────────────────
 🛑 Intercepts:            1   |  Cumulative: 34
 💥 Critical Blocks:       1   |  Cumulative: 18
 🔄 Self-Corrections:      1   |  Recovery Rate: 100.0%
 💰 Tokens Saved:         ~1500  |  Cumulative: ~51000
 ⏳ Time Saved:           ~5s    |  Cumulative: ~170s
════════════════════════════════════════════════════════════
 🩺 AGENT HEALTH INSIGHT
────────────────────────────────────────────────────────────
 ⚠️  Top Offender: 'Database Isolation'
 💡 Tip: Consider refining your agent's system prompt to avoid this.

---

🧠 The 5 Pillars of Agentic Security

AgentX is built on a "Reasoning Engine" architecture that treats AI agents as autonomous employees rather than static scripts. We secure them through five core pillars:

1. Cognitive Interception: We intercept tool calls to compare the agent's stated intent (Chain of Thought) against its actual deterministic action.

2. Socratic Nudging: Instead of crashing the agent with a 403 Forbidden, we issue a Socratic Challenge to guide them to a safe, desired end-goal.

3. Human-in-the-Loop (HITL): If the gateway cannot judge intent safely, the agent is paused (202 Accepted) and sent to a SOC Sandbox for human evaluation.

4. Dynamic Policy Refresh: Policies are pushed out-of-band via a centralized Control Plane, updating localized edge-caches within 3 seconds.

5. Auditable Self-Healing: The system dynamically captures successful agent recovery rates on your dashboard when a model successfully self-corrects post-challenge.

---

🚀 The 4 Shields (Defense-in-Depth)
1. The Inbound Shield (Prompt Injection): Sanitizes inbound user text to prevent cognitive hijacking ("Ignore previous instructions") before the agent reads it.

2. The Logic Shield (Database Guard): Uses AST parsing and Gemini to catch destructive queries (DROP, DELETE) and nudges the agent to write safer SQL.

3. The Network Shield (SSRF Guard): Prevents agents from acting as confused deputies to hit cloud metadata IPs (e.g., 169.254.169.254).

4. The Egress Shield (DLP/PII Scrubber): Dynamically masks PII and API keys on the wire, maintaining clean audit logs without triggering SOC alert fatigue.

---

## 📊 Local Telemetry & Agent Health

AgentX ships with a built-in, privacy-first SQLite time-series event log (`.agentx.db`). It tracks every interception locally. When your agent script finishes or crashes, AgentX automatically prints a comprehensive Session Summary and Lifetime ROI dashboard:

```text
══════════════════════════════════════════════════
 🛡️  AgentX Session Summary
══════════════════════════════════════════════════
 ⏱️  Uptime:                9.17 seconds
 🛠️  Tools Monitored:       2
──────────────────────────────────────────────────
 🛑 Intercepts:            1   |  Cumulative: 5
 💥 Critical Blocks:       1   |  Cumulative: 5
 💰 Tokens Saved:      ~1500   |  Cumulative: ~7500
 ⏳ Time Saved:        ~5m     |  Cumulative: ~25m
══════════════════════════════════════════════════
 🩺 AGENT HEALTH INSIGHT
──────────────────────────────────────────────────
 ⚠️ Top Offender: 'Database Isolation'
 🛠️  Tip: Consider refining your agent's system prompt to avoid this.
══════════════════════════════════════════════════

```

---

📦 Try the Developer Demos
Inside the examples/ folder, you will find a few standalone scripts proving the AgentX Reasoning Layer:

* **01_self_healing_agent.py:** Watch AgentX catch a hallucination and coach the agent to self-correct (Saving tokens and uptime).
* **02_cognitive_intent_block.py:** Watch the Semantic Firewall catch malicious intent even when the raw syntax is perfectly safe.
* **03_human_escalation.py:** See how an agent safely pauses execution and pings a SOC analyst for approval using a 202 Accepted queue.
* **And many more...**

---


## 🕹️ Human-in-the-Loop (HITL) & Control Plane
Sometimes, an agent needs to drop a table for a valid business reason.

AgentX features a Next.js Control Plane Dashboard. If an agent requests an escalation, the SDK securely pauses local execution and polls the Edge Gateway. A human SOC analyst can click "Approve" or "Deny" in the UI, and the Python execution loop will automatically resume.

```bash
cd ui
npm install
npm run dev

---

## 🤝 Contributing
We are actively looking for design partners. If you are building autonomous agents in production and are terrified of what they might do, open an issue or reach out!

---

## 🏗️ The Architecture (Split-Plane)

AgentX relies on a decoupled, hybrid-cloud architecture to ensure maximum performance and security for AI-driven enterprise systems.

* **The Edge SDK (AgentX)**: The lightweight Python package that instruments agent tools and triggers local Socratic self-healing.
* **The Data Plane (Semantic Firewall)**: A Python FastAPI middleware (the "Wedge") that intercepts raw HTTP/SQL payloads *before* they hit the database.
* **The Control Plane (Dashboard)**: A Next.js application (deployed via Vercel) that allows human reviewers to monitor intercepted agent traffic, review chains of thought, and approve or deny parked requests.
* **The Shared Brain**: Supabase acts as the central state manager. Both the Control Plane and Data Plane synchronize via Supabase, decoupling the network architecture and allowing asynchronous state polling.
* **The Evaluator**: Google's Gemini 2.5 Flash is used to translate an agent's Chain of Thought (CoT) into a zero-knowledge taxonomy to evaluate intent against YAML-defined enterprise policies.

---

## ✨ Key Features & Built-in Policies

* **Automated Socratic Self-Healing**: Intercepts dangerous tool calls and challenges the agent to revise its strategy.
* **Fast Pass Heuristic Traps**: Instantly intercepts structurally dangerous queries (e.g., `DROP TABLE`, `DELETE`) with minimal latency.
* **Zero-Knowledge Intent Extraction**: Prevents malicious prompt injection by translating raw agent logic into a strict schema before policy evaluation.
* **Dynamic Cloud Policies**: Enforces isolation rules instantly via a Supabase-backed Control Plane that syncs to edge caches in 3 seconds.

---

## 🔒 Security Posture

* **Secret Management**: API keys are never checked into version control. Production variables are managed securely via the Vercel Dashboard.
* **History Scrubbing**: This repository has been scrubbed of legacy keys using git-filter-repo.
* **Private IP**: Repository is private to protect proprietary evaluation prompts and architecture.

---

📈 Updated Roadmap
✅ Trust Boundary Shift: Moved neuro-symbolic evaluation entirely into the Data Plane container to eliminate agent runtime bypasses. (Completed)

✅ Zero-Knowledge Hard Split-Plane: Mathematically enforced VPC telemetry isolation via localized metric stripping. (Completed)

✅ Zero-Config Reflection Engine: Eliminated manual query and CoT boilerplate function writing; implemented dynamic parameter serialization natively within the SDK decorator loop. (Completed)

⬜ Local LRU Neural Cache: Deduplicate vector embeddings to minimize edge latency down to sub-1ms. (Next up)

⬜ Core DevX Inspection Engine: Expose a unified CLI interface for localized policy and metric auditing. (Active)

⬜ Containerize the Data Plane for deployment to AWS ECS / Render for persistent, low-latency edge interception.


