Dolos
Getting the software ready
Preparing your private AI workspace…
Clear, fair rules for using Forensic Intelligence.
To use the Dolos application, you must create an account with a valid email address and password. You are responsible for maintaining the confidentiality of your credentials and for all activity under your account. Each account is for a single individual. You must be at least 16 years old to create an account.
Account DeletionFor questions about these terms, contact us at [email protected].
By accessing the Forensic Intelligence website, using the Dolos AI application (iOS, web, or desktop), or any related services, you agree to these Terms of Service. If you do not agree, do not use our services.
To use the Dolos application, you must create an account with a valid email address and password. You are responsible for maintaining the confidentiality of your credentials and for all activity under your account. Each account is for a single individual. You must be at least 16 years old to create an account.
Account DeletionYou may use our services for lawful purposes including data analysis, research, collaboration, document processing, and professional communication. You must comply with all applicable laws and regulations.
You retain ownership of all data and content you upload or create in Dolos. We store your data encrypted on our servers solely to provide you with the service. We do not use your content to train, fine-tune, or improve AI models.
You must not use our services to:
Dolos uses artificial intelligence to generate responses and process information. AI-generated outputs may be inaccurate, incomplete, or outdated. You are responsible for verifying the accuracy of any AI output before relying on it for professional, legal, financial, or medical purposes.
Certain features rely on third-party services including Perplexity, OpenAI, ElevenLabs, Stripe, and Cloudflare. When you use these features, your data may be processed by the respective service under their own terms.
Dolos uses the following open-source and third-party AI models. All locally hosted models are run on Forensic Intelligence servers — no user data is sent to model providers for inference or training:
| Model | Purpose | Hosted by | License |
|---|---|---|---|
| GPT-OSS (20B) | Chat and advanced reasoning | Forensic Intelligence | Apache 2.0 |
| Qwen3.8 (27B) | General chat, routing, and reasoning | Forensic Intelligence | Apache 2.0 |
| Qwen3.8 Abliterated (27B) | General chat, routing, and reasoning | Forensic Intelligence | Apache 2.0 |
| Gemma 4 (31B / 26B / E4B) | Chat, multimodal reasoning, image analysis, video summary, guest chat, and chat naming | Forensic Intelligence | Apache 2.0 |
| Muse Glimmer (30B) | Agentic chat, tool use, and multimodal reasoning | Forensic Intelligence | Apache 2.0 |
| Nemotron 3.5 Lightning | Agentic chat, tool use, and long-context reasoning | Forensic Intelligence | NVIDIA Open Model License |
| Ornith (9B) | Agent workflows and chat utilities | Forensic Intelligence | MIT |
| laguna-xs-2.1 | Code and script generation | Forensic Intelligence | OpenMDW-1.1 |
| TabICL v2 | Zero-shot prediction on spreadsheet data (predict_table) | Forensic Intelligence | BSD-3-Clause |
| GLM-OCR | Structured data extraction | Forensic Intelligence | Apache 2.0 |
| Chandra OCR 2 | Document OCR and text extraction | Forensic Intelligence | OpenRAIL-M |
| JoyTag | Image content classification | Forensic Intelligence | Apache 2.0 |
| Qwen3-Embedding-0.6B | Document embeddings for semantic search | Forensic Intelligence | Apache 2.0 |
| BGE Reranker v2-m3 | Search result reranking | Forensic Intelligence | Apache 2.0 |
| xGen-MM-Vid | Video scene analysis | Forensic Intelligence | BSD-3-Clause |
| TEN-VAD | Voice activity detection | Forensic Intelligence | Apache 2.0 |
| Whisper Large v3 Turbo | Long-form audio transcription (99+ languages) | Forensic Intelligence | MIT |
| Kokoro-82M | Local text-to-speech synthesis | Forensic Intelligence | Apache 2.0 |
| TranslateGemma (12B) | Text translation | Forensic Intelligence | Apache 2.0 |
| Perplexity Sonar Deep Research | Internet search and deep research | Perplexity (External) | Proprietary API |
| OpenAI (GPT-4o mini / GPT-4o / o4-mini Deep Research (2025-06-26) / GPT-4.1) | Internet search, deep research, and research refinement | OpenAI (External) | Proprietary API |
| ElevenLabs (v3 / Multilingual v2 / Flash v2.5 / Turbo v2.5) | Premium text-to-speech voices | ElevenLabs (External) | Proprietary API |
The Dolos iOS application is distributed through the Apple App Store. Apple Inc. is not a party to these Terms of Service. The app requires iOS 16.0 or later.
Dolos offers free and paid subscription plans. Paid subscriptions are processed by Stripe. You can cancel at any time through your account settings. Upon cancellation, you retain access until the end of the current billing period.
You may delete your account at any time from the Settings page. Account deletion permanently removes all your data. We reserve the right to suspend or terminate accounts that violate these Terms of Service.
We implement complete end-to-end encryption (E2EE) across all communication between your browser and our servers. A per-session AES-256-GCM key is negotiated via RSA-OAEP-256 (3072-bit) key exchange at connection time. Every request, response, real-time event, file transfer, and API call is encrypted at the application layer — above TLS — ensuring no network intermediary can access plaintext data. Sensitive database fields are independently encrypted at rest. You are responsible for maintaining the security of your account credentials.
The Dolos application and website are provided "as is" without warranties of any kind. To the maximum extent permitted by law, Forensic Intelligence is not liable for indirect or consequential damages arising from use of our services.
To the maximum extent permitted by law, Forensic Intelligence is not liable for indirect, incidental, special, or consequential damages arising from use of our services, including but not limited to loss of data, business interruption, or reliance on AI-generated content.
For questions about these terms, contact us at [email protected].
