3-Triple Multi-Agentic AI Framework
React Dashboard · Real-time BI · ADAG Red Team
TruthLens v2.8.0 - 6 Core Strengths
rPPG heart rate extraction and eye blink pattern analysis detect physiologically impossible patterns - the strongest evidence against deepfakes.
LangGraph orchestration + CrewAI 6-expert consensus + AutoGen adversarial debate - three frameworks working in concert.
Ollama-based local LLM/VLM inference ensures zero data transmission to external servers. Safe for sensitive data.
Every verdict includes LLM-generated detailed explanation and evidence chain for full transparency.
Adversarial testing framework with 4 attack modules automatically verifies detection robustness via Red-Blue Team feedback loop.
Send() parallel dispatch, async architecture, MemorySaver checkpoint for fault-tolerant real-time analysis.
LangGraph + CrewAI + AutoGen - 3 frameworks in synergy
17-node async StateGraph pipeline with Send() parallel dispatch for 5 analysis nodes running simultaneously. MemorySaver checkpoint enables fault recovery. Human-in-the-Loop (HITL) for uncertain zone review.
6 specialized expert agents analyze evidence independently, then the Chief Analyst synthesizes all findings for the final verdict. Supports Sequential and Hierarchical process modes with SQLite memory backend for learning from past judgments.
When fusion scores fall in the uncertain zone (0.35~0.65), adversarial debate automatically triggers. Prosecutor argues FAKE, Defense argues REAL, and Judge renders the final verdict. Supports 1v1 and 6-person GroupChat modes.
14 pages · Real-time BI · WebSocket · 45 REST APIs
Drag & Drop media files here
Video (MP4, AVI, MOV) · Image (JPG, PNG) · Audio (MP3, WAV)
Max 500MB
Fake rPPG + blink pattern injection
FFT masking + camera ISP simulation
Micro-motion + motion blur injection
Statistical noise + typo injection
import requests
resp = requests.post(
"http://localhost:7000/ai/detect/upload",
files={"file": open("video.mp4","rb")},
headers={"X-API-Key": "tl_sk_..."}
)
print(resp.json()["verdict"])
Multimodal analysis with weighted fusion
GAN fingerprint, compression artifacts, face manipulation
TTS/voice cloning detection, spectrum analysis
rPPG heart rate extraction, eye blink pattern analysis
Lip-sync verification, speaker consistency
Subtitle manipulation, document forgery, text consistency
Cross-modal anomaly detection via Whisper transcription
Prototypical Networks for novel deepfake type learning
Production-ready system with 89/89 tests passing