> For the complete documentation index, see [llms.txt](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/docs/knowledge-graph/knowledge-graph-unlocks.md). # Knowledge Graph Unlocks This roadmap lists future Knowledge Graph work. It is not a shipped-behavior contract. The current shipped surface is documented in [Knowledge Graph](/ai-os-and-trend-finder-docs/docs/knowledge-graph/knowledge-graph.md) and [Knowledge Graph Handover](/ai-os-and-trend-finder-docs/docs/knowledge-graph/knowledge-graph-handover.md). ## Current Baseline AI OS currently ships: * Per-project graph registry and graph JSON files. * `/knowledge-graph` dashboard route. * Seed/demo fallback behavior. * Dashboard-mediated local and Git URL ingest. * Admin-gated remove. * Home Shared Brain preview. * Grounded Hermes chat using active graph context. * Setup scripts for the shared graphify registry. The value of future work is not the 3D picture alone. The value is that a persistent, queryable, objective project map exists and can become a reliable action surface for operators and agents. ## Tier 1: Turn The Map Into A Tool ### 1. Node-To-Chat Actions Future behavior: * Click a graph node and ask Hermes or Claude about that file, cluster, or relationship. * Carry the selected node id and graph path into chat grounding. * Keep chat answers tied to concrete graph evidence. Why it matters: * Converts visual exploration into immediate project reasoning. * Reduces repeated orientation for common questions such as "what owns auth?" or "what changes if I touch this file?" ### 2. Graph Query Bar Future behavior: * Add a route-level query input for graphify queries. * Surface path, neighborhood, explain, and related-node answers inside AI OS. Why it matters: * Lets operators interrogate the graph without leaving the dashboard or opening a chat session. ### 3. Editor Launchpad Future behavior: * Open a source file from a graph node in the operator's configured editor. * Copy a source path or project-scoped prompt from the node inspector. Why it matters: * Makes the Knowledge Graph the front door to codebase navigation. ### 4. Runtime MCP Exposure Future behavior: * Expose each graph JSON through graphify MCP or an AI OS local equivalent. * Let local agents query structure at runtime instead of re-grepping. Why it matters: * Gives Hermes, Claude Code, Codex, and future agents a shared structural map. ## Tier 2: Code Intelligence ### 5. Blast Radius View Future behavior: * Select a node and highlight direct and transitive dependents. * Rank affected communities and high-degree files. Why it matters: * Helps estimate review risk before a change starts. ### 6. God-Object And Orphan Detection Future behavior: * Promote over-connected nodes and degree-zero nodes into a maintainability panel. * Track trend over time when graph snapshots exist. Why it matters: * Turns graph structure into actionable refactor and dead-code candidates. ### 7. Surprising Connections Future behavior: * Detect cross-cluster links that appear unusual or fragile. * Explain why the link matters and what evidence supports it. Why it matters: * Finds hidden coupling that normal file trees conceal. ### 8. PR And Diff Risk Triage Future behavior: * Compare a changed file list against graph communities and dependency paths. * Produce a bounded review-risk summary. Why it matters: * Gives code review a structural risk read before tests are run. ### 9. Guided Onboarding Tour Future behavior: * Auto-walk the graph's top files, communities, and key paths. * Produce a short architecture tour for a new project. Why it matters: * Shortens first-session project orientation. ## Tier 3: Creator And Content Graphs ### 10. Content-Corpus Graph Future behavior: * Graph a curated corpus of transcripts, notes, outlines, or scripts. * Surface topic pillars, sparse areas, and repeated concepts. Why it matters: * Helps convert a large content archive into concrete creator strategy. ### 11. Audience-Demand Graph Future behavior: * Graph approved public or operator-provided comment/question corpora. * Cluster repeated demand signals and map them to content gaps. Why it matters: * Links Knowledge Graph structure with Trend Finder style creator planning. ### 12. Competitive White-Space Map Future behavior: * Graph reviewed competitor transcript or source corpora. * Compare saturated versus under-covered concepts. Why it matters: * Helps operators find differentiated content and product angles. ### 13. Build-As-Content Workflow Future behavior: * Package graph builds, surprising findings, and before/after maps as creator artifacts. Why it matters: * The Knowledge Graph can become both an operating tool and a demonstrable content asset. ## Tier 4: OS And Agent Integration ### 14. Memory Constellation Integration Future behavior: * Relate code graphs, notes, and local memory stores without merging unrelated domains by default. Why it matters: * Keeps per-project graph clarity while allowing opt-in second-brain context. ### 15. Dream Integration Future behavior: * Feed god objects, surprising connections, graph drift, and source gaps into daily Dream prescriptions. Why it matters: * Moves the graph from passive reference to proactive recommendation. ### 16. Auto-Ingest Hooks Future behavior: * Refresh graphs after commits, agent sessions, or approved local hooks. * Keep vendored dependency excludes explicit. Why it matters: * Keeps graph state current without relying on manual ingest. ## Tier 5: Portfolio And Cross-Project Views ### 17. Global Overlay Future behavior: * Build an opt-in overlay across multiple project graphs. * Highlight repeated concepts, duplicated utilities, and shared modules. Why it matters: * Supports portfolio-level cleanup without losing per-project isolation. ### 18. Portfolio Health Board Future behavior: * Rank projects by size, coupling, confidence, stale age, and graph health. Why it matters: * Gives operators a maintenance queue across local projects. ### 19. Graph Over Time Future behavior: * Diff graph snapshots between sessions or releases. * Show complexity drift, new coupling, and reduced or expanded clusters. Why it matters: * Helps catch architectural decay early. ## Recommended Sequence 1. Node-to-chat actions and editor launchpad. 2. Runtime graph query bar. 3. MCP or equivalent agent exposure. 4. Auto-ingest hooks. 5. Blast radius, god-object detection, and surprising connections. 6. Dream integration. 7. Content-corpus graph. 8. Portfolio overlay and graph-over-time views. ## Guardrails For Future Work * Keep graphify optional until a product decision makes it required. * Preserve seed/demo fallback behavior for fresh clones. * Keep admin writes loopback-only, token-gated, admin-gated, non-demo, and unavailable in production. * Do not add hosted graph ingestion without a new privacy and security review. * Keep per-project graphs isolated by default; make cross-project overlays opt-in. * Avoid storing private graph payloads, screenshots, traces, auth headers, or tokens in committed evidence. * Add focused tests for every new trust boundary, schema field, or write path. --- # 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://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/docs/knowledge-graph/knowledge-graph-unlocks.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.