> For the complete documentation index, see [llms.txt](https://incogai.gitbook.io/incogai-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://incogai.gitbook.io/incogai-docs/incog-docs/introduction.md). # Introduction ## Overview INCOG AI is a privacy-first browsing and network infrastructure protocol designed to systematically eliminate the surveillance surface of modern internet interactions. The protocol addresses a fundamental asymmetry in contemporary web architecture: browsers and network intermediaries accumulate behavioral, telemetric, and metadata signals at a rate far exceeding what users observe or consent to, while the economic incentives of incumbent infrastructure operators are structurally misaligned with user privacy. This documentation covers the full technical specification of the INCOG AI system, including the browser isolation model, the decentralized relay mesh architecture, the node operator participation layer, the $INCOG token incentive system, the privacy-preserving wallet module, and the in-browser private inference runtime. *** ## Design Philosophy ### Privacy as an Architectural Property Most existing privacy solutions are additive — extensions, VPN overlays, or consent frameworks bolted onto surveillance-first architectures. INCOG AI treats privacy as a foundational architectural constraint. Every system component is designed from first principles around the question: *what is the minimum information that needs to be observable for this function to work?* This approach rejects the notion that privacy can be achieved through policy or legal compliance alone. Privacy must be enforced by the architecture itself, not promised by the operator. ### Trust-Minimized Design INCOG AI operates under a trust-minimized design philosophy. The protocol is constructed so that no single party — including INCOG AI itself — needs to be trusted to maintain user privacy. This is achieved through: * Client-side execution of privacy-sensitive operations * Distributed relay routing across independent node operators * Open cryptographic protocols for relay coordination * Token-aligned incentive structures that punish defection ### Adversarial Assumptions The threat model underlying INCOG AI assumes adversarial observers at multiple layers of the network stack: passive traffic analysis at the ISP and CDN level, active fingerprinting by first and third-party web properties, behavioral profiling by browser vendors, and correlation attacks by entities controlling multiple relay hops. The protocol is designed to remain resilient against passive surveillance across all these layers simultaneously, rather than optimizing against a single threat vector. *** ## System Components The INCOG AI protocol consists of six primary components: | Component | Function | | --------------------- | ------------------------------------------------------------------ | | INCOG Privacy Browser | Hardened browsing client with isolation-first execution model | | INCOG Mesh Network | Decentralized relay infrastructure for traffic routing obfuscation | | Node Operator Layer | Hardware-backed relay participation and reward distribution | | $INCOG Token | Incentive coordination and network participation alignment | | INCOG Wallet | Privacy-preserving on-chain interaction layer | | INCOG LLM | Private inference runtime for browser-integrated AI | *** ## How to Use This Documentation This documentation is structured to serve multiple audiences simultaneously. Engineers building on or integrating with the INCOG AI protocol should read the core architecture and system design sections first. Node operators should prioritize the network and hardware layer sections. Token participants and governance stakeholders should focus on the token and incentive model sections. The threat model section is required reading for anyone making security assumptions about the protocol — it defines the boundaries of what the system does and does not protect against. *** ## Status INCOG AI is in active development. The initial product — the INCOG Privacy URL Shortener — is live. The Privacy Browser is in active development. Subsequent protocol layers are specified in this documentation and will ship in deliberate phases, each building on verified infrastructure from the previous phase. Readers should treat specifications for components marked as planned or in-development as protocol design documents, not as descriptions of currently deployed infrastructure. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://incogai.gitbook.io/incogai-docs/incog-docs/introduction.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.