diff --git a/gitbooks/.gitbook/assets/V11 — Tiered Memory Deep Dive@2x (1) (1).png b/gitbooks/.gitbook/assets/V11 — Tiered Memory Deep Dive@2x (1) (1).png new file mode 100644 index 000000000..b7333d122 Binary files /dev/null and b/gitbooks/.gitbook/assets/V11 — Tiered Memory Deep Dive@2x (1) (1).png differ diff --git a/gitbooks/.gitbook/assets/V11 — Tiered Memory Deep Dive@2x (1) (2).png b/gitbooks/.gitbook/assets/V11 — Tiered Memory Deep Dive@2x (1) (2).png new file mode 100644 index 000000000..b7333d122 Binary files /dev/null and b/gitbooks/.gitbook/assets/V11 — Tiered Memory Deep Dive@2x (1) (2).png differ diff --git a/gitbooks/.gitbook/assets/image (1) (1).png b/gitbooks/.gitbook/assets/image (1) (1).png new file mode 100644 index 000000000..9de536ebb Binary files /dev/null and b/gitbooks/.gitbook/assets/image (1) (1).png differ diff --git a/gitbooks/README.md b/gitbooks/README.md index dc8478ecb..5d9312724 100644 --- a/gitbooks/README.md +++ b/gitbooks/README.md @@ -3,10 +3,10 @@ description: >- OpenHuman is a personal AI assistant that runs natively across desktop, mobile, and web that connects your communication platforms, tools, and workflows into a single intelligence layer you control. -icon: diamond +icon: hand-wave --- -# Welcome to OpenHuman +# Welcome OpenHuman is the first open-source AI agent with Big Data capabilities and a personalized subconscious mind. Built on the OpenClaw architecture and licensed under GNU GPL3, OpenHuman is designed to close the gap between what AI models can do and what they actually know about you. @@ -38,8 +38,6 @@ It **thinks proactively** through its subconscious system, making connections an It **preserves privacy** by design. Raw data stays on your device. Encryption keys never leave the device. Only compressed metadata and summaries are processed server-side. - - ## Who it's for OpenHuman is built for people and teams who operate across many conversations and tools, and feel the cost of it. diff --git a/gitbooks/SUMMARY.md b/gitbooks/SUMMARY.md index 8f285e84e..5e8f9f575 100644 --- a/gitbooks/SUMMARY.md +++ b/gitbooks/SUMMARY.md @@ -2,23 +2,20 @@ ## Overview -* [Welcome to OpenHuman](README.md) -* [How It Works](overview/how-it-works.md) +* [Welcome](README.md) * [Getting Started](overview/getting-started.md) +* [How Does It Work?](overview/how-it-works.md) +* [Architecture](overview/architecture.md) -## Technology +## Features -* [Neocortex](technology/neocortex.md) -* [The Subconscious](technology/the-subconscious.md) -* [Architecture](technology/architecture.md) - -## Product - -* [Platform & Availability](product/platform.md) -* [Skills & Integrations](product/skills-and-integrations.md) -* [Teams & Organizations](product/teams.md) -* [Privacy & Security](product/privacy-and-security.md) -* [Pricing](product/pricing.md) +* [Neocortex](features/neocortex/README.md) + * [Subconscious Loop](features/neocortex/the-subconscious.md) +* [Platform & Availability](features/platform.md) +* [Skills & Integrations](features/skills-and-integrations.md) +* [Teams & Organizations](features/teams.md) +* [Privacy & Security](features/privacy-and-security.md) +* [Pricing](features/pricing.md) ## Use Cases diff --git a/gitbooks/technology/neocortex.md b/gitbooks/features/neocortex/README.md similarity index 92% rename from gitbooks/technology/neocortex.md rename to gitbooks/features/neocortex/README.md index fa8a2fa0a..e75ea21e4 100644 --- a/gitbooks/technology/neocortex.md +++ b/gitbooks/features/neocortex/README.md @@ -1,8 +1,12 @@ +--- +icon: brain +--- + # Neocortex Neocortex is OpenHuman's memory engine. It is a human-like AI memory system designed to work accurately with over 1 billion tokens of data while supporting the computational demands of a subconscious system. -
+
Neocortex goes far beyond vector databases that simply store embeddings and retrieve whatever is semantically similar. It understands time, entities, and relationships. It builds knowledge graphs. It forgets strategically. It models memory the way the human brain does. @@ -44,13 +48,13 @@ Neocortex uses a tiered memory architecture modeled on how the human brain manag Intelligent pruning moves memories between tiers based on recency, frequency of access, and contextual relevance. Nothing is ever permanently deleted. Memories can always be reactivated. -
+
#### The neuroscience of forgetting The tiered architecture is grounded in neuroscience research. -
+
A Carnegie Mellon University study demonstrated that intentionally forgetting some things helps us remember others by freeing up working memory resources. Memory formation depletes a limited working memory resource that recovers over time. @@ -64,7 +68,7 @@ This validates the core design principle of Neocortex. AI systems that try to re Neocortex does not store flat text. It builds knowledge graphs: structured representations of entities, relationships, and temporal chains. -
+
**Semantic deduplication** strips redundant noise before it enters the graph. In group chats, 80%+ of messages are repetitive. Neocortex removes this automatically. diff --git a/gitbooks/technology/the-subconscious.md b/gitbooks/features/neocortex/the-subconscious.md similarity index 96% rename from gitbooks/technology/the-subconscious.md rename to gitbooks/features/neocortex/the-subconscious.md index c2f1ca067..a845b97cf 100644 --- a/gitbooks/technology/the-subconscious.md +++ b/gitbooks/features/neocortex/the-subconscious.md @@ -1,4 +1,4 @@ -# The Subconscious +# Subconscious Loop OpenHuman's subconscious is what separates it from every other AI agent. Most AI systems follow the conscious mind model: they wait for instructions and execute them. They cannot think on their own. OpenHuman can. @@ -28,7 +28,7 @@ The outputs are proactive. You do not need to prompt OpenHuman to get value from #### The mirror test -
+
The team uses an internal success metric called the "mirror test." When you read the subconscious output, it should feel like looking at yourself in a mirror. Not generic AI analysis. A reflection of your own thinking patterns, priorities, and concerns. diff --git a/gitbooks/product/platform.md b/gitbooks/features/platform.md similarity index 100% rename from gitbooks/product/platform.md rename to gitbooks/features/platform.md diff --git a/gitbooks/product/pricing.md b/gitbooks/features/pricing.md similarity index 100% rename from gitbooks/product/pricing.md rename to gitbooks/features/pricing.md diff --git a/gitbooks/product/privacy-and-security.md b/gitbooks/features/privacy-and-security.md similarity index 100% rename from gitbooks/product/privacy-and-security.md rename to gitbooks/features/privacy-and-security.md diff --git a/gitbooks/product/skills-and-integrations.md b/gitbooks/features/skills-and-integrations.md similarity index 100% rename from gitbooks/product/skills-and-integrations.md rename to gitbooks/features/skills-and-integrations.md diff --git a/gitbooks/product/teams.md b/gitbooks/features/teams.md similarity index 100% rename from gitbooks/product/teams.md rename to gitbooks/features/teams.md diff --git a/gitbooks/technology/architecture.md b/gitbooks/overview/architecture.md similarity index 97% rename from gitbooks/technology/architecture.md rename to gitbooks/overview/architecture.md index 1e0cc5025..184adc762 100644 --- a/gitbooks/technology/architecture.md +++ b/gitbooks/overview/architecture.md @@ -1,3 +1,7 @@ +--- +icon: hammer +--- + # Architecture OpenHuman is built on the OpenClaw architecture and open-sourced under the GNU GPL3 license. This page explains how the major components connect. @@ -12,7 +16,7 @@ OpenHuman's architecture rests on three pillars that work together: **Multi-agent orchestration** distributes work across specialized agents rather than relying on a single monolithic model. An orchestrator agent manages routing, personality, and context distribution. Specialist agents handle specific domains: communication analysis, document synthesis, task management, trading. Agents execute in parallel, not sequentially, enabling real-time responsiveness. -**Privacy-preserving inference** ensures that raw data never leaves the user's device. Data is encrypted on-device with AES-256-GCM. Encryption keys never leave the device. Only compressed metadata and summaries are processed server-side. Detailed in [Privacy & Security](../product/privacy-and-security.md). +**Privacy-preserving inference** ensures that raw data never leaves the user's device. Data is encrypted on-device with AES-256-GCM. Encryption keys never leave the device. Only compressed metadata and summaries are processed server-side. Detailed in [Privacy & Security](../features/privacy-and-security.md). #### How data flows diff --git a/gitbooks/overview/getting-started.md b/gitbooks/overview/getting-started.md index c8249b863..75d4f9ce3 100644 --- a/gitbooks/overview/getting-started.md +++ b/gitbooks/overview/getting-started.md @@ -1,5 +1,5 @@ --- -icon: play +icon: baby-carriage --- # Getting Started @@ -78,7 +78,7 @@ After your first request, explore what else OpenHuman can do: * **Integrations** let you push structured results to Notion, Google Sheets, and other tools * **Workflows** turn conversation decisions into trackable actions you can follow through on -Learn more in [Skills & Integrations](../product/skills-and-integrations.md). +Learn more in [Skills & Integrations](../features/skills-and-integrations.md). *** diff --git a/gitbooks/resources/faq.md b/gitbooks/resources/faq.md index fd23df2b9..d689ac1f3 100644 --- a/gitbooks/resources/faq.md +++ b/gitbooks/resources/faq.md @@ -101,7 +101,7 @@ OpenHuman currently integrates with **Telegram** (read and analyze conversations OpenHuman offers individual and team plans with core analysis included. Deeper features are available in higher tiers. A credit system provides usage-metered flexibility, and credits can be earned through referrals. -See [Pricing](../product/pricing.md) for details. +See [Pricing](../features/pricing.md) for details. ***