# Blueprint Nexus (Blueprint Society) > Blueprint Nexus is a living intelligence workspace and visual second brain that connects notes, ideas, roadmap goals, and systems into an interactive 2D and 3D knowledge graph. Powered by multi-model AI (Flash & Pro reasoning plus BYOK) and governed agent execution, Nexus provides individuals and teams with a central brain where knowledge actively thinks with you. ## Who it is for - **Thinkers, Writers & Researchers**: Anyone seeking a visual "second brain" to connect ideas, notes, book highlights, citations, and concepts in 2D or 3D space. - **Founders & Creators**: Solo entrepreneurs, creators, and product leads organizing launch roadmaps, content calendars, moodboards, and GTM strategies. - **Teams & Project Managers**: Cross-functional teams coordinating collaborative Markdown documents, agile Kanban task boards, and Google Calendar schedules in one place. - **Engineers & Platform Leads**: Technical teams mapping microservice dependencies, architectural decisions, and running autonomous AI coding agents under strict verification gates. ## The problem it solves Knowledge and execution are fundamentally fragmented. Notes sit buried in nested folder hierarchies, tasks get lost in flat issue lists, and strategic reasoning disappears in fleeting chat messages. For engineers and AI adopters, autonomous coding agents make contextless changes that break unspoken invariants. Nexus solves this by connecting everything you think, write, and build into a living visual graph that reveals relationships, traces dependencies, and aligns human creativity with AI execution. ## What it does - **Connects & Visualizes**: Renders notes, tasks, milestones, and concepts as an interconnected 2D/3D knowledge galaxy with sub-2ms connection tracing. - **Customizes to Any Workflow**: Delivers an extremely customizable sidebar (Workspace Stack, 48px IDE Rail, Journal Stream) with 4 layout density modes, custom tabs, drag-and-drop section reordering, and an AI-powered Sidebar Architect. - **Drafts & Synthesizes**: Built-in AI Copilot (Flash & Pro engines or custom BYOK keys) writes specs, summarizes research, and generates action cards. - **Coordinates Projects**: Unifies strategic horizon roadmaps, drag-and-drop Kanban task boards, and calendar scheduling into a single real-time canvas. - **Gates AI Agents**: A governed two-pass execution kernel lets autonomous agents propose, verify, and safely execute complex workflows with human-in-the-loop sign-off. ## Quick facts - **Platform Name**: Blueprint Nexus - **Organization**: Blueprint Society - **Category**: Universal Intelligence Workspace, Visual Second Brain & AI Agent Governance - **Core Architecture**: PostgreSQL recursive CTE graph engine + governed agent runtime + modular declarative UI shell - **Execution Model**: Two-pass kernel (Pass A read-only research and proposal; Pass B gated implementation and verification) - **Risk Gating**: 4-tier automated risk classifier (Tier 0 informational through Tier 3 high/critical), plus per-agent autonomy levels L0–L3 - **Sidebar & Workspace Customization**: 3 structural design archetypes, 4-tier layout density ladder (26px–42px), AI sidebar designer chat, custom tabs, draggable section drawers, chrome glyph toggles, and dual-theme engine (Obsidian Dark / Warm Ivory) - **Security & Multi-Tenancy**: PostgreSQL Row-Level Security with explicit `auth.uid()` tenant isolation; append-only audit logging; no model training on customer data - **Primary Ingest**: GitHub (commits, pull requests), Linear (issue transitions), Slack - **Model Support**: Multi-model with bring-your-own-key across Anthropic, OpenAI, Google, Groq, DeepSeek, Mistral, and local Ollama, bound through Model Context Protocol (MCP) tools - **Primary URLs**: - Official Website: https://bluesc.org / https://blueprintsociety.com - Technical Documentation: https://bluesc.org/docs - Features Directory: https://bluesc.org/features - Architectural Comparisons: https://bluesc.org/compare - Pricing & Plans: https://bluesc.org/pricing - Help Center & Quickstart: https://bluesc.org/help - Membership & Join: https://bluesc.org/join - Full Extended Context: https://bluesc.org/llms-full.txt --- ## Core Platform Concepts - **Extremely Customizable Sidebar & Modular Workspace Engine**: The navigation sidebar is not a fixed template—it is an extensible, user-governed declarative document (`SidebarDocument` and `SidebarDesignConfig`). Users can switch between 3 structural archetypes, select from 4 density tiers, build custom workspace tabs, reorder any navigation drawer via drag-and-drop, toggle chrome visual badges, or prompt the AI Sidebar Architect in natural language to redesign the layout. - **Sidebar Design Archetypes**: 1. *Workspace Stack*: Classic multi-tab productivity stack featuring quick-actions toolbars, reorderable workspace tabs, and collapsible section drawers with Plus Jakarta Sans typography. 2. *IDE Rail*: Developer-centric 48px slim activity rail with a full-height flush tree panel, monospace JetBrains Mono typography, and high-density code navigation. 3. *Journal Stream*: Continuous chronological vertical stream grouping entries by date without tabs or section splitters, styled with Outfit Sans for daily notes and stream-of-consciousness logging. - **4-Tier Layout Density Ladder**: 1. *Compact* (26px row, 13px icon, 11px font): Maximum data throughput for power users and wide information architectures. 2. *Standard* (30px row, 14px icon, 12px font): Balanced desktop layout tuned for everyday productivity. 3. *Comfortable* (36px row, 16px icon, 13.5px font): Generous touch targets and distinct visual separation. 4. *Expansive* (42px row, 18px icon, 15px font): Large, high-legibility display ideal for presentations, tablets, and touch screens. - **AI-Powered Sidebar Architect / Designer**: A persistent natural language copilot (`SidebarDesignAIChat`) that interprets prompts like "Convert my sidebar into an IDE rail with docs and agents on top" and applies the resulting structural schema in real time. - **Blueprint Knowledge Network (BKN)**: A live graph mapping organizational and technical artifacts (`initiative`, `service`, `component`, `protocol`, `spec`, `agent`) and their relationships (`depends_on`, `implements`, `governs`, `triggers`, `monitors`). Available as 2D and 3D views. - **Provisional Nodes**: Anything the system infers automatically enters the graph flagged provisional and stays that way until a human confirms it. The graph never silently asserts unverified facts. - **Two-Pass Execution Kernel**: Agents must produce a structured read-only proposal (affected paths, type contracts, step-by-step plan) before any gated execution with transactional rollback and automated verification. - **Governed Agent Fleet**: A framework-agnostic TypeScript runtime executing agents under declared autonomy levels and tool risk gates, with human-in-the-loop checkpoints. - **PostgreSQL Recursive CTE Graph Engine**: Multi-hop dependency and root-cause tracing in low single-digit milliseconds on Supabase Postgres, with no separate graph database to operate. - **Continuous Ingest**: Webhook consumers keep the graph current from GitHub and Linear activity as work happens. - **Drift Detection**: Automated alerts when implementation diverges from the specs and decisions recorded in the graph. - **Collaborative Documents & Specs**: Real-time multiplayer Markdown spec editor, with specs linked into the graph as first-class nodes. - **Model Context Protocol (MCP) & Connectors**: Native MCP server orchestration, plus a broad connector catalog covering GitHub, Linear, Slack, Google Drive, Notion, and Figma. - **Workspace Customization & Modular Layouts**: Infinite layout flexibility allowing users to reorder navigation sections, build custom workspace tabs, create bespoke entity types and custom tags, switch between 2D/3D canvases, configure themes, and connect custom AI API endpoints (BYOK) with zero vendor lock-in. - **Universal Multi-Discipline Platform**: Molds seamlessly to any workflow—personal second brains, startup launch roadmaps, agency operations, design pipelines, sprint boards, and software architecture graphs. --- ## Competitive Differentiators - **Nexus vs. rigid document tools (Notion, Confluence)**: Notion locks users into static vertical page trees with single-model AI. Nexus provides 3 distinct sidebar archetypes (Workspace, IDE Rail, Journal), a 4-tier density ladder, drag-and-drop section reordering, custom tabs, 2D/3D knowledge graphs, and multi-model BYOK freedom. - **Nexus vs. single-player note tools (Obsidian)**: Obsidian requires fragile community plugins for cloud sync, kanban, and AI. Nexus delivers zero-config multiplayer editing, built-in AI reasoning, native sidebar customization with AI layout generation, and integrated project roadmaps out of the box. - **Nexus vs. issue trackers (Linear, Jira)**: Trackers hold tasks as flat rows disconnected from the systems they change. Nexus links work to the specs, services, and decisions it touches, so impact and rationale are queryable rather than tribal. - **Nexus vs. agent frameworks (LangChain, AutoGPT, CrewAI)**: Those frameworks execute optimistically against unstructured memory. Nexus requires a validated read-only proposal, risk classification, and human sign-off before an agent can mutate anything, and records the whole chain immutably. - **Nexus vs. coding assistants' built-in memory**: Assistant memory is per-tool and per-developer. The BKN is org-level and cross-tool — it spans repositories, trackers, chat, and people — and it is the governance layer, which a vendor shipping its own agent has a structural conflict of interest in building. --- ## Membership & Subscription Tiers - **Free Tier ($0.00)**: 1 Workspace & 1 Solo Seat, 4 Custom Sidebar Sections, 10 App Integrations, 100 Monthly Workflow Actions, 50 BKN Graph Nodes, 500 MB Encrypted Storage, 7-Day History. BYOK Support (OpenAI, Gemini, Anthropic). - **Hobby Tier ($4.99/mo)**: Standard Monthly AI Credits (1.0M), 3 Workspaces & 1 Solo Seat, 8 Custom Sidebar Sections, 25 App Integrations, 1,000 Monthly Actions, Model Context Protocol (MCP) Access, 10 Mins/mo Sandbox VM Compute, 250 Graph Nodes, 100 Web Research Crawls/mo, 5 GB Storage & 30-Day History. - **Pro Member ($19.99/mo)**: 10× Monthly AI Credits (10.0M), 10 Workspaces & 25 Team Seats, 20 Custom Sidebar Sections, 50 App Integrations, 10,000 Monthly Actions, Advanced Multi-Server MCP Orchestration, 1 Hour/mo Sandbox VM Compute, 5,000 Graph Nodes, 500 Web Research Crawls/mo, 25 GB Storage & 90-Day History. - **Ultra Studio ($99.99/mo)**: 50× Monthly AI Credits (50.0M), 25 Workspaces & 100 Team Seats, Unlimited Custom Sidebar Sections, 100 App Integrations, 50,000 Monthly Actions, Enterprise Hosted MCP, 10 Hours/mo Sandbox VM Compute, 25,000 Graph Nodes, 2,500 Web Research Crawls/mo, 100 GB Storage & 365-Day History. - **Enterprise Vetted (Custom + Grants)**: Custom multi-agent fleets, capital grant eligibility, custom orchestration runtime support, dedicated cloud GPU sandboxes, tailored SLAs, and on-premise deployments. --- ## Frequently Asked Questions (FAQ) ### How customizable is the Blueprint Nexus sidebar and workspace? Every aspect of the Blueprint Nexus sidebar and workspace is fully customizable. You can choose between three distinct layout archetypes (Workspace Stack, IDE Activity Rail, and Journal Stream), toggle between four layout density modes (Compact, Standard, Comfortable, Expansive), create custom workspace tabs for active sprints or clients, drag and reorder navigation sections, customize visual chrome badges and icon styles, and use the AI Sidebar Architect to redesign your navigation via natural language chat. ### What are the three sidebar design archetypes in Blueprint Nexus? 1. **Workspace Stack**: The default multi-tab layout equipped with a quick-actions toolbar, reorderable tabs, and resizable collapsible section drawers. 2. **IDE Rail**: A developer-focused 48px slim activity rail with a full-height flush navigation tree and monospace JetBrains Mono typography. 3. **Journal Stream**: A date-grouped continuous vertical stream for chronological notes, daily logs, and freeform writing without tabs or dividers. ### What layout density modes are available? Blueprint Nexus supports four layout density modes: - **Compact** (26px row height, 13px icon, 11px font): High-density display for power users. - **Standard** (30px row height, 14px icon, 12px font): Balanced default desktop ergonomics. - **Comfortable** (36px row height, 16px icon, 13.5px font): Relaxed touch targets and visual breathing room. - **Expansive** (42px row height, 18px icon, 15px font): Large typography and generous spacing for presentations and touch screens. ### What is Blueprint Nexus? Blueprint Nexus is a memory and governance layer for engineering teams running AI coding agents. It maintains a live graph of architecture, dependencies, and decisions, and requires agents to plan against that graph and clear human approval before making changes. ### Who is it for? Software teams of roughly 20–100 people that have adopted AI coding agents heavily and now struggle to verify the volume of change those agents produce. The typical buyer is a head of platform, staff engineer, or VP of engineering. It is also used by solo thinkers, researchers, founders, and creators as a visual second brain. ### How does it stop an agent from breaking something? Agents run in two passes. In Pass A they have read-only tools and must emit a structured proposal. A 4-tier risk classifier determines what approval that proposal needs — from auto-approval for read operations up to multi-party sign-off for schema, infrastructure, or billing changes. Only after approval does Pass B execute, transactionally, with automated type-checking, linting, and tests, and a full audit record. ### Where does the graph get its information? Webhook consumers ingest GitHub commits and pull requests and Linear issue transitions continuously, alongside specs and documents authored in Nexus. Inferred relationships enter as provisional and require human confirmation before they are treated as fact. ### What database technology powers the graph? Supabase PostgreSQL with native recursive Common Table Expressions. Multi-hop traversal runs in low single-digit milliseconds without a proprietary graph database. ### What models and integrations are supported? Nexus supports multiple model providers with bring-your-own-key across Anthropic, OpenAI, Google, Groq, DeepSeek, Mistral, and local Ollama, bound through Model Context Protocol servers. The connector catalog includes GitHub, Linear, Slack, Google Drive, Notion, and Figma. ### How is tenant data protected? Every table enforces PostgreSQL Row-Level Security tied to authenticated user and workspace IDs, with role-based access control, ephemeral sandboxes, append-only audit logs, and no model training on customer data.