Build a full knowledge graph locally with any video

GoodQ4All, a 100% private, offline video and audio analysis system, now runs on Windows 11, ingesting media into local knowledge graphs with scene segmentation, Whisper transcription, speaker diarization, and semantic search via SQLite and Qdrant. The system ensures verifiability with proof-backed manifests and audit trails, requiring 25 GB of free space and an RTX 4070 Ti SUPER 16GB for large models.

Offline Video Search, Scene Segmentation, Speech Transcription Whisper , Speaker Diarization, and SQLite + Qdrant Semantic Search on Windows 11 https://askgoodq.com/ Note: The optional Ask GoodQ voice agent is a hosted extension using ElevenLabs APIs. The core GoodQ4All memory system itself is 100% local and offline. GoodQ4All is a 100% private, offline alternative to cloud-based media intelligence services. It ingests video, audio, and text files into queryable, structured scene-level memories, persisting the knowledge graph and vector representations locally on your computer. Following a strict "proof-backed" system doctrine , GoodQ4All documents every perception step, tracks evidence manifests, and logs a comprehensive audit trail so that every memory claim can be verified. - Get This Level of Local Control Unified Operator UI : Click the preview above to watch the high-fidelity onboarding video. - From Video Quality as Low as This: Raw Media Inputs : Apollo 11 Moon Walk nasa descent.gif Saturn V Launch nasa launch.gif - Using This All-in-One Installer Unified Windows Installer : 🚀 Download GoodQ4All Setup v2.4.0.exe https://github.com/GoodQ02/goodq4all/releases/download/v2.4.0/GoodQ4All Setup 2.4.0.exe IMPORTANT System Requirement: Windows 11 only. GoodQ4All is built for Windows-first local execution. It requires at least 25 GB of free space to store local database structures, models, and cache files. SmartScreen Workaround: Since the setup installer is currently self-signed, Windows SmartScreen may show an "Unknown Publisher" dialog. Click More info and select Run anyway to proceed. Integrity Checksum: Verify your download authenticity by running the following command in PowerShell:Expected SHA256 hash: Refer to the GitHub Releases page for the latest signed executable checksum. Get-FileHash GoodQ4All Setup 2.4.0.exe Machine memory should earn every claim it makes. GoodQ4All generates step-by-step logs step runs.jsonl , scene manifests, and intermediate features for every ingested file. Single-Use Confirmation Tokens : Ingestion submission routes are protected by a server-generated token handshake with single-use nonce validation, preventing unauthenticated/out-of-bounds execution. Epistemic Verification : Ingestion is tracked using verifiable manifests and SQLite-backed relational schemas. No Silent Failures : The Control Agent and Watchdog processes bubble errors directly to the operator consoles, providing absolute visibility into the execution stack. To run large-parameter local models safely on consumer hardware e.g. RTX 4070 Ti SUPER 16GB without Out-of-Memory OOM crashes, GoodQ4All implements strict VRAM and execution controls: Model Lifecycle Manager : A specialized context manager lib/model lifecycle.py that audits free VRAM using PyTorch and nvidia-smi before loading models, dynamically evicting idle networks from GPU memory. Local Agent Stack : Gated LLM reasoning and local tool execution through zero-dependency policy enforcement middleware, loading schemas, policies, and contracts dynamically from the version-controlled MiniAgentClient agents/stack/ directory. Endpoint Fallback Orchestration : Automatically falls back from the primary local vLLM server prefer speed , running Qwen2.5 to a local Ollama service prefer quality , running Phi-4 or a CPU-safe model variant when VRAM thresholds are breached. High-precision 32-bit floating point embeddings are persisted in Qdrant and FAISS. For rapid candidate filtering, GoodQ4All uses TurboQuant —an SQLite sidecar caching technology employing Lloyd-Max Polar Quantization and Johnson-Lindenstrauss residual projections. Performance: Achieves sub-millisecond candidate pre-filtering. Accuracy: 100% search accuracy is maintained by performing the final rank scoring on the uncompressed raw float32 vectors. Note Hybrid Precision Caching Model : GoodQ4All uses an additive sidecar vector cache architecture. High-precision 32-bit floating point float32 embeddings remain the authoritative truth of the system, stored in Qdrant and FAISS. Performance-oriented query pre-filtering is handled via lightweight TurboQuant fields Lloyd-Max Polar Quantization + Johnson–Lindenstrauss residual corrections stored in SQLite. This ensures zero data loss, guarantees rollback capability, and cuts memory usage. The pipeline dynamically adjusts its computational needs to match your system specs: BASELINE CPU-safe : Fully operational, offline-ready execution on standard CPU hardware. Bypasses GPU requirements gracefully. GPU ENHANCED : Activates local NVIDIA GPU CUDA 12.1 and WSL2 accelerated audio processing paths for fast, high-volume ingestion. GoodQ4All compiles the isolated Python environment, the Qdrant database, and perception libraries into a single executable wrapper: - Download and run GoodQ4All Setup 1.0.0.exe . - Launch GoodQ4All from the desktop shortcut. - Open the local Retro Memory Explorer dashboard at http://127.0.0.1:30000/ui/retro console v1/ . - Drag-and-drop video/audio files onto the yellow-dotted Upload Pad to begin automatic ingestion. If you are developing, customizing the pipeline, or running from source: Developer Source Setup Steps Advanced GoodQ4All ships with two local operator console variants: Classic Operator Console served at /ui/operator console v1/ : Exposes the current scope strip, flight deck, proof/evidence status, recurrence reports, and video inventories. Retro Memory Explorer v1.4.7 served at /ui/retro console v1/ : A premium cyber-CRT dashboard featuring a four-panel resizable/collapsible layout with floating restore tabs, an entity co-occurrence graph with dynamic zoom and flight transitions, an Inspector panel containing keyframe image/transcript views, and bidirectional timeline checklists. - Guided demo: docs/guides/DEMO.md - First run: docs/guides/FIRST RUN.md - Install: docs/guides/install/INSTALL.md - Quickstart: docs/guides/install/QUICKSTART.md - Clean memory start: docs/guides/CLEAN MEMORY START.md - Data Privacy: docs/guides/general/PRIVACY.md - Architecture: docs/architecture/SYSTEM ARCHITECTURE.md - Memory Storage: docs/architecture/MEMORY STORAGE.md - Hybrid Caching: docs/architecture/TURBOQUANT HYBRID CACHING.md - Current Agent State: docs/agent/CURRENT STATE.md MIT. See LICENSE /GoodQ02/goodq4all/blob/main/LICENSE .