โ๏ธ Agentic Reliability Framework
Adaptive anomaly detection + policy-driven self-healing for AI systems
Minimal, fast, and production-focused.
## ๐ง Agentic Reliability Framework
**Autonomous Reliability Engineering for Production AI Systems**
Transform reactive monitoring into proactive, self-healing reliability. The Agentic Reliability Framework (ARF) is a production-grade, multi-agent system that detects, diagnoses, predicts, and resolves incidents automatically in under 100ms.
## โญ Key Features
- **Real-time anomaly detection** across latency, errors, throughput & resources
- **Root-cause analysis** with evidence correlation
- **Predictive forecasting** (15-minute lookahead)
- **Automated healing policies** (restart, rollback, scale, circuit break)
- **Incident memory** with FAISS for semantic recall
- **Security hardened** (all CVEs patched)
- **Thread-safe, async, process-pooled architecture**
- **Sub-100ms end-to-end latency** (p50)
## ๐ Security Hardening (v2.0)
| CVE | Severity | Component | Status |
|-----|----------|-----------|--------|
| CVE-2025-23042 | 9.1 | Gradio Path Traversal | โ
Patched |
| CVE-2025-48889 | 7.5 | Gradio SVG DOS | โ
Patched |
| CVE-2025-5320 | 6.5 | Gradio File Override | โ
Patched |
| CVE-2023-32681 | 6.1 | Requests Credential Leak | โ
Patched |
| CVE-2024-47081 | 5.3 | Requests .netrc Leak | โ
Patched |
### Additional Hardening
- SHA-256 hashing everywhere (no MD5)
- Pydantic v2 input validation
- Rate limiting (60 req/min/user)
- Atomic operations w/ thread-safe FAISS single-writer pattern
- Lock-free reads for high throughput
## โก Lock-Free Reads for High Throughput
By restructuring the internal memory stores around lock-free, single-writer / multi-reader semantics, the framework delivers deterministic concurrency without blocking. This removes tail-latency spikes and keeps event flows smooth even under burst load.
### Performance Impact
| Metric | Before | After | ฮ |
|--------|--------|-------|---|
| Event Processing (p50) | ~350ms | ~100ms | โก 71% faster |
| Event Processing (p99) | ~800ms | ~250ms | โก 69% faster |
| Agent Orchestration | Sequential | Parallel | 3ร throughput |
| Memory Behavior | Growing | Stable / Bounded | 0 leaks |
## ๐งฉ Architecture Overview
### System Flow
```
Your Production System
(APIs, Databases, Microservices)
โ
Agentic Reliability Core
Detect โ Diagnose โ Predict
โ
Agents:
๐ต๏ธ Detective Agent โ Anomaly detection
๐ Diagnostician Agent โ Root cause analysis
๐ฎ Predictive Agent โ Forecasting / risk estimation
โ
Policy Engine (Auto-Healing)
โ
Healing Actions:
โข Restart
โข Scale
โข Rollback
โข Circuit-break
```
## ๐๏ธ Core Framework Components
### Web Framework & UI
- **Gradio 5.50+** - High-performance async web framework serving both API layer and interactive observability dashboard (localhost:7860)
- **Python 3.10+** - Core implementation with asynchronous, thread-safe architecture
### AI/ML Stack
- **FAISS-CPU 1.13.0** - Facebook AI Similarity Search for persistent incident memory and vector operations
- **SentenceTransformers 5.1.1** - Neural embedding framework using MiniLM models from Hugging Face Hub for semantic analysis
- **NumPy 1.26.4** - Numerical computing foundation for vector operations and data processing
### Data & HTTP Layer
- **Pydantic 2.11+** - Type-safe data modeling with frozen models for immutability and runtime validation
- **Requests 2.32.5** - HTTP client library for external API communication (security patched)
### Reliability & Resilience
- **CircuitBreaker 2.0+** - Circuit breaker pattern implementation for fault tolerance and cascading failure prevention
- **AtomicWrites 1.4.1** - Atomic file operations ensuring data consistency and durability
## ๐ฏ Architecture Pattern
ARF implements a **Multi-Agent Orchestration Pattern** with three specialized agents:
- **Detective Agent** - Anomaly detection
- **Diagnostician Agent** - Root cause analysis
- **Predictive Agent** - Future risk forecasting
All agents run in **parallel** (not sequential) for **3ร throughput improvement**.
### โก Performance Features
- Native async handlers (no event loop overhead)
- Thread-safe single-writer/multi-reader pattern for FAISS
- RLock-protected policy evaluation
- Queue-based writes to prevent race conditions
- Sub-100ms p50 latency at 100+ events/second
The framework combines **Gradio** for the web/UI layer, **FAISS** for vector memory, and **SentenceTransformers** for semantic analysis, all orchestrated through a custom multi-agent Python architecture designed for production reliability.
## ๐งช The Three Agents
### ๐ต๏ธ Detective Agent โ Anomaly Detection
Real-time vector embeddings + adaptive thresholds to surface deviations before they cascade.
- Adaptive multi-metric scoring
- CPU/mem resource anomaly detection
- Latency & error spike detection
- Confidence scoring (0โ1)
### ๐ Diagnostician Agent (Root Cause Analysis)
Identifies patterns such as:
- DB connection pool exhaustion
- Dependency timeouts
- Resource saturation
- App-layer regressions
- Misconfigurations
### ๐ฎ Predictive Agent (Forecasting)
- 15-minute risk projection
- Trend analysis
- Time-to-failure estimates
- Risk levels: low โ critical
## ๐ Quick Start
### 1. Clone
```bash
git clone https://github.com/petterjuan/agentic-reliability-framework.git
cd agentic-reliability-framework
```
### 2. Create environment
```bash
python3.10 -m venv venv
source venv/bin/activate # Windows: venv\Scripts\activate
```
### 3. Install
```bash
pip install -r requirements.txt
```
### 4. Start
```bash
python app.py
```
**UI:** http://localhost:7860
## ๐ Configuration
Create `.env`:
```env
HF_TOKEN=your_token
DATA_DIR=./data
INDEX_FILE=data/incident_vectors.index
LOG_LEVEL=INFO
HOST=0.0.0.0
PORT=7860
```
**Note:** `HF_TOKEN` is optional and used for downloading SentenceTransformer models from Hugging Face Hub.
## ๐งฉ Custom Healing Policies
```python
custom = HealingPolicy(
name="custom_latency",
conditions=[PolicyCondition("latency_p99", "gt", 200)],
actions=[HealingAction.RESTART_CONTAINER, HealingAction.ALERT_TEAM],
priority=1,
cool_down_seconds=300,
max_executions_per_hour=5,
)
```
## ๐ณ Docker Deployment
Dockerfile and docker-compose.yml included.
```bash
docker-compose up -d
```
## ๐ Performance Benchmarks
**On Intel i7, 16GB RAM:**
| Component | p50 | p99 |
|-----------|-----|-----|
| Total End-to-End | ~100ms | ~250ms |
| Policy Engine | 19ms | 38ms |
| Vector Encoding | 15ms | 30ms |
**Stable memory:** ~250MB
**Throughput:** 100+ events/sec
## ๐งช Testing
### Production Dependencies
```bash
pip install -r requirements.txt
```
### Development Dependencies
```bash
pip install pytest pytest-asyncio pytest-cov pytest-mock black ruff mypy
```
### Run Tests
```bash
pytest tests/ -v --cov
```
**Coverage:** 87%
Includes:
- Unit tests
- Thread-safety tests
- Stress tests
- Integration tests
### Code Quality
```bash
# Format code
black .
# Lint code
ruff check .
# Type checking
mypy app.py
```
## ๐บ Roadmap
### v2.1
- Distributed FAISS
- Prometheus / Grafana
- Slack & PagerDuty integration
- Custom alerting DSL
### v3.0
- Reinforcement learning for policy optimization
- LSTM forecasting
- Dependency graph neural networks
## ๐ค Contributing
Pull requests welcome.
Please run tests before submitting.
## ๐ฌ Contact
**Author:** Juan Petter (LGCY Labs)
- ๐ง [petter2025us@outlook.com](mailto:petter2025us@outlook.com)
- ๐ [linkedin.com/in/petterjuan](https://linkedin.com/in/petterjuan)
- ๐
[Book a session](https://calendly.com/petter2025us/30min)
## โญ Support
If this project helps you:
- โญ Star the repo
- ๐ Share with your network
- ๐ Report issues
- ๐ก Suggest features
Built with โค๏ธ for production reliability