@andespindola/brainlink 0.1.0-beta.16 → 0.1.0-beta.161

package/AGENTS.md

@@ -6,7 +6,7 @@ This file tells coding agents and AI assistants how to use this repository.
 
 Brainlink is a local-first knowledge memory for agents.
 
-It reads a Markdown vault, extracts `[[wiki links]]` and `#tags`, builds a local file index at `.brainlink/index.json`, and returns compact context packages that agents can inject into prompts.
+It reads a Markdown vault, extracts concise graph links from `## Context Links`, extracts `#tags`, builds a local file index at `.brainlink/index.json`, and returns compact context packages that agents can inject into prompts.
 
 ## Source Of Truth
 
@@ -27,15 +27,15 @@ By default, the installed Brainlink CLI uses `$HOME/.brainlink/vault` as its vau
 Use this loop when using Brainlink as memory:
 
 1. Write durable knowledge into Markdown notes.
-2. Link related notes with explicit `[[Note Title]]` wiki links inside the note body.
+2. Link related notes with explicit `[[Note Title]]` wiki links inside a `## Context Links` section.
 3. Add explicit `#tags` for retrieval.
 4. Run `index` after writes.
 5. Run `context "<task or question>"` before answering.
 6. Use the returned sources as grounded context.
 
-`context` is read-only. It does not create notes, backlinks, graph edges or durable memory by itself. A relationship exists only when a Markdown note contains a `[[wiki link]]` to another note and the vault has been indexed after that write.
+`context` is read-only. It does not create notes, backlinks, graph edges or durable memory by itself. A relationship exists only when a Markdown note contains a `[[wiki link]]` inside `## Context Links` and the vault has been indexed after that write.
 
-When an agent adds durable memory, it should connect the new note to at least one existing concept unless the note is intentionally a root concept. Prefer exact note titles in links, for example `[[Architecture]]`, and run `broken-links`, `orphans` or `validate` when the graph looks disconnected.
+When an agent adds durable memory, it should add only the canonical relationships to `## Context Links`. Prefer exact note titles in links, for example `[[Architecture]]`, and run `broken-links`, `orphans` or `validate` when graph health matters.
 
 Agents can mark important relationships by placing priority hints on the same line as a wiki link, for example `[[Architecture]] priority: high`, `[[Incident Runbook]] #important` or `[[Incident Runbook]] #critical`. Indexed graph edges expose `weight` and `priority` so agents can sort related notes by importance.
 
@@ -78,11 +78,14 @@ http://127.0.0.1:4321/
 http://127.0.0.1:4321/api/graph
 ```
 
-Use watch mode while editing notes:
+The graph server watches Markdown files by default while editing notes:
 
 ```bash
-npm run dev -- server --vault ./vault --watch
+npm run dev -- server --vault ./vault
 npm run dev -- watch --vault ./vault
+npm run dev -- bench --vault ./vault
+npm run dev -- bench --vault ./vault --watch
+npm run dev -- pack-backup --vault ./vault
 ```
 
 Start MCP over stdio:

package/CHANGELOG.md

@@ -14,6 +14,9 @@
 - Added default MCP startup bootstrap behavior controlled by `brainlink_policy.autoBootstrapOnStartup`.
 - Added CLI MCP policy presets through `blink agent policy --preset fully-auto|strict`.
 - Added write-time non-orphan enforcement by auto-linking notes without wiki edges to agent hub notes.
+- Changed graph indexing to keep every non-self Markdown wiki link as a weighted graph edge so the default star graph represents complete note connectivity.
+- Added `blink index --full` and MCP `brainlink_index` `full=true` for complete source reindexing without clearing the existing index first.
+- Improved index migration so stale graph link model metadata automatically triggers a complete source reindex.
 - Added MCP `brainlink_policy` presets (`fully-auto`, `strict`) for one-call policy switching.
 - Added MCP write connectivity metadata in `brainlink_add_note`/`brainlink_add_file` responses.
 - Added MCP `brainlink_recommendations` tool for plug-and-play workflow guidance.
@@ -22,6 +25,30 @@
 - Added short-lived hybrid search cache with automatic invalidation on index changes.
 - Added `stats --extended` observability output with storage, quality and latency probes.
 - Added `docs/QUICKSTART.md` and aligned README/agent docs with the latest CLI/MCP flows.
+- Added middle-out context assembly so chunk selection expands around the strongest note chunk.
+- Added compressed-space pack prefiltering (token bloom index) before `.blpk` decryption and scan.
+- Improved graph UI auto-fit and viewport recovery so loaded nodes are re-centered when zoom/pan drifts to empty canvas.
+- Added cross-platform native desktop GUI auto-open for `blink server` (macOS Swift/WebKit, Windows PowerShell WinForms, Linux Python GTK/WebKit2), with app-window/browser fallback.
+- Changed Linux default UI launch to app-window/browser for lighter startup; Linux native GUI is now opt-in via `BRAINLINK_LINUX_NATIVE_GUI=1`.
+- Added native GUI parent-process monitoring so GUI windows close automatically when `blink server` stops.
+- Improved non-mac browser detection fallback to try installed Edge/Chrome/Firefox/Chromium candidates before system default open.
+- Improved graph filter rendering to keep hub anchor nodes visible (`Memory Hub`/`MOC`/high-degree fallback) for coherent relationship context.
+- Fixed graph modal content loading by correcting agent query parameter composition for `/api/graph-node` and `/api/graph-filter` requests.
+- Improved 50k+ graph rendering performance with viewport-aware spatial node culling, cached render visibility, and node-adjacent edge selection to avoid full graph scans every frame.
+- Added incremental vault indexing with file snapshots to reuse unchanged documents/chunks/embeddings, plus adaptive search-pack rebuild thresholds to avoid full re-compression on small edits.
+- Reduced large-graph HTTP payload size with compact `/api/graph-layout` encoding for high-node vaults and capped transmitted edges to improve UI load responsiveness.
+- Added aggressive graph LOD clustering when zoomed out, dynamic per-zoom edge render budgets, and a dedicated frontend worker for off-main-thread graph filter matching.
+- Improved Linux browser fallback launch stability by auto-applying Chromium compatibility flags (`--ozone-platform=x11`, `--disable-gpu`, `--disable-features=Vulkan,VaapiVideoDecoder`, `--disable-background-networking`) for app-window/browser modes.
+- Improved massive-graph UI responsiveness with stricter render budgets, adaptive heavy-graph frame throttling, reduced interaction hit-test frequency, and URL-first agent selection on initial graph load.
+- Improved 50k+ graph LOD behavior so zoomed-out views render lightweight cluster overviews and progressively reveal nodes/edges only as zoom increases.
+- Added `blink bench` with realtime index phase telemetry and per-run compressed-pack analysis (input/output bytes, ratio, saved space, rebuild reason and duration), including continuous watch mode.
+- Added tunable single-stage search-pack compression settings (`searchPack.rowChunkSize`, `searchPack.compressionLevel`, `searchPack.useDictionary`).
+- Added benchmark guardrails for compression savings and latency regression (`searchPack.guardrailMinSavingsPercent`, `searchPack.guardrailMaxLatencyRegressionPercent`), reported in `blink bench`.
+- Added `blink pack-backup` for offline second-stage compression backups of encrypted `.blpk` packs, outside the online query path.
+- Hardened Linux browser launch flags for Ubuntu 26 Chromium/Wayland compatibility (`--disable-vulkan`, `--use-gl=swiftshader`, `--ozone-platform-hint=x11`).
+- Improved pack resilience by auto-repairing missing search-pack manifests from existing `.blpk` files, avoiding unnecessary full repacks on small incremental updates.
+- Updated Linux graph auto-open behavior to prioritize the system default browser (`xdg-open`) before explicit browser fallbacks.
+- Removed implicit Chromium dependency in Linux auto-open flow; app-window launch is now opt-in (`BRAINLINK_LINUX_APP_WINDOW=1`).
 
 ## 0.1.0-beta.3
 

package/COPYRIGHT.md

@@ -0,0 +1,5 @@
+Copyright (c) 2026 Substructa
+
+This project is licensed under the MIT License.
+
+See [LICENSE](./LICENSE) for full terms.

package/README.md

@@ -58,6 +58,7 @@ LLMs do not have infinite context. Brainlink gives agents an external memory lay
 
 Markdown is the source of truth. `.brainlink/index.json` is a rebuildable index artifact.
 After each index run, Brainlink also writes private encrypted search packs at `.brainlink/search-packs/*.blpk` to preserve fast retrieval and portable recovery.
+Online retrieval always uses a single compression stage per pack; optional second-stage compression is reserved for offline backup artifacts only.
 Pack decryption uses a Brainlink key from `$BRAINLINK_HOME/keys` or from `BRAINLINK_SEARCH_PACK_KEY` when explicitly configured.
 Legacy `.jsonl.gz` packs are upgraded to `.blpk` automatically on first search/context access.
 
@@ -67,8 +68,13 @@ Legacy `.jsonl.gz` packs are upgraded to `.blpk` automatically on first search/c
 - Obsidian-compatible `[[wiki links]]` and `#tags`.
 - Weighted graph edges so agents can rank relationship importance and priority.
 - Backlinks, broken-link reports, orphan detection and validation.
-- Full-text, semantic and hybrid retrieval modes.
 - Full-text, semantic and hybrid retrieval on a local file index.
+- Middle-out context assembly around the strongest chunk per document.
+- In-process index and context caching with automatic invalidation on index updates.
+- HTTP graph server caches generated frontend assets and graph-layout JSON payloads by signature, and skips layout serialization when ETag returns `304`.
+- Compressed-space prefiltering for `.blpk` packs before decryption and scan.
+- Incremental indexing that reprocesses only changed markdown files and reuses existing chunks/embeddings for unchanged notes.
+- Adaptive compressed-pack rebuild policy to keep indexing fast during small edit batches.
 - Agent namespaces under `agents/<agent-id>/`.
 - S3-compatible bucket vaults through `s3://bucket/prefix` URIs.
 - CLI with machine-readable `--json` output.
@@ -76,6 +82,17 @@ Legacy `.jsonl.gz` packs are upgraded to `.blpk` automatically on first search/c
 - Built-in MCP stdio server for agent tool integration.
 - Local HTTP API.
 - Realtime graph UI with agent selector and colored knowledge groups.
+- Graph renderer uses a cauliflower-style hub layout: the primary hub stays centered, segment hubs anchor surrounding lobes, and visual edges are simplified to root hub -> segment hubs -> local context nodes.
+- Real weighted `[[wiki link]]` edges stay preserved in the indexed graph APIs for backlinks, ranking and context traversal; the browser layout uses a separate visual edge layer for readability.
+- Graph exploration uses stable chunk streaming (`/api/graph-stream`) with explicit node/edge budgets, returning the full mode-level scene while it fits the budget.
+- Render pipeline uses WebGL in a dedicated worker through `OffscreenCanvas`, keeping the main thread focused on UI controls and details panels.
+- Large graph layout API automatically uses compact payload encoding with link-coverage-aware edge selection to reduce initial client load without hiding major relationships.
+- Large-segment layout spacing now grows logarithmically to keep initial visual density consistent between medium and very large vaults (for example, ~1k vs ~50k notes).
+- Graph coordinates are visually compacted across graph sizes so reset starts from a stable fitted scene and zoom-in progressively reveals local detail.
+- Zoomed-out graph summarizes the scene as segment hub clusters, then progressively reveals individual nodes as the user zooms in.
+- Graph reset fits the full graph scene instead of starting in a separate macro overview mode.
+- Graph filtering runs in a dedicated browser worker to keep the UI thread responsive during heavy datasets.
+- Node titles are shown as the user zooms closer, while labels remain bounded to visible on-screen nodes in very large graphs.
 
 ## Install
 
@@ -193,19 +210,19 @@ Only store knowledge that is likely to matter later:
 ```bash
 blink add "Testing Policy" \
   --agent "$BLINK_AGENT" \
-  --content "Run npm run check before final delivery. Related: [[Release Checklist]]. #testing #process"
+  --content $'Run npm run check before final delivery. #testing #process\n\n## Context Links\n\n- [[Release Checklist]]'
 ```
 
-Brainlink does not infer durable graph relationships from generated context. A context result is only a read package for the model. To create a real link in the knowledge graph, the agent must write Markdown that contains an explicit `[[Note Title]]` wiki link.
+Brainlink does not infer durable graph relationships from generated context. A context result is only a read package for the model. To create a real graph link, write a concise `## Context Links` section and put the canonical `[[Note Title]]` links there.
 
 Writes with `blink add` reindex the vault automatically by default. This can be disabled with `--no-auto-index` and controlled globally with `autoIndexOnWrite` in `brainlink.config.json`.
 
 When adding memory, follow this contract:
 
-- Link the new note to at least one existing note when there is a related concept.
+- Link the new note to existing notes through `## Context Links` when there is a related concept.
 - Use the exact target note title inside `[[...]]`.
 - Add retrieval tags such as `#architecture`, `#decision`, `#runbook` or `#preference`.
-- Do not leave isolated notes unless they are intentionally root concepts.
+- General wiki-link mentions outside `## Context Links` remain searchable Markdown content, but they do not become graph edges.
 
 If you disable auto-index, run `blink index` after batched writes.
 
@@ -248,7 +265,7 @@ blink search "jwt auth" --vault ./vault
 
 blink context "how does auth work?" --vault ./vault
 
-blink server --vault ./vault --watch
+blink server --vault ./vault
 ```
 
 Open the graph UI:
@@ -395,6 +412,7 @@ blink agent upgrade
 ```
 
 This configures `~/.codex/config.toml` with Brainlink MCP (`brainlink-mcp`) so Brainlink is available by default in agent sessions.
+`agent install` and `agent upgrade` also apply the MCP `fully-auto` bootstrap policy by default (`enforceBootstrap`, `enforceContextFirst`, `autoBootstrapOnRead`, `autoBootstrapOnStartup` all enabled).
 
 If you are inside this repository and want plugin gallery setup too:
 
@@ -514,13 +532,19 @@ Available tools:
 - `brainlink_recommendations`: return an automatic action plan so agents can run Brainlink in the recommended order.
 - `brainlink_context`: read indexed context for a task or question.
 - `brainlink_search`: search indexed notes.
+- `brainlink_dedupe`: detect duplicate candidates using exact hash + semantic similarity scores.
+- `brainlink_resolve_duplicate`: resolve duplicate pairs (`merge`, `link`, `ignore`) with connectivity-safe fallback edges.
 - `brainlink_add_note`: write durable Markdown memory and reindex.
 - `brainlink_add_file`: ingest a local file as a note and reindex.
-- `brainlink_index`: rebuild the vault index.
+- `brainlink_canonicalize_context_links`: ensure existing notes link to inferred context hubs.
+- `brainlink_volatile_add`: write temporary agent-decided memory with TTL; volatile sections are included in context and never create durable graph edges.
+- `brainlink_volatile_clear`: clear temporary memory for the current vault/agent namespace.
+- `brainlink_index`: rebuild the vault index. Pass `full=true` for a complete source reindex.
 - `brainlink_stats`: read indexed vault statistics.
 - `brainlink_validate`: validate broken links and orphan notes.
 - `brainlink_sync`: run index, stats, validation, broken-link and orphan checks in one call.
 - `brainlink_graph`: read indexed graph nodes and weighted links.
+- `brainlink_graph_contexts`: list the visual graph contexts used by the local server.
 - `brainlink_broken_links`: list unresolved wiki links.
 - `brainlink_orphans`: list disconnected notes.
 
@@ -532,7 +556,7 @@ If you disable `autoBootstrapOnRead` through `brainlink_policy`, read tools retu
 `brainlink_bootstrap`, `brainlink_policy` and preflight responses include structured `nextActions` so MCP clients can continue automatically without custom parsing.
 For one-call planning, use `brainlink_recommendations` to get the recommended tool sequence for the current vault/agent/query.
 
-The same linking rule applies through MCP: `brainlink_context` is read-only, and real graph links require Markdown notes with explicit `[[wiki links]]`. `brainlink_add_note` and `brainlink_add_file` reindex by default and include index + `writeConnectivity` metadata. Brainlink guarantees at least one edge per new note by auto-linking when needed.
+The same linking rule applies through MCP: `brainlink_context` is read-only, and real graph links require Markdown notes with explicit `## Context Links` sections. `brainlink_add_note` and `brainlink_add_file` reindex by default and include index + `writeConnectivity` metadata. Brainlink does not auto-link new notes to fallback hubs.
 
 Agents can raise the importance of a relationship by putting priority markers on the same line as a wiki link:
 
@@ -541,31 +565,61 @@ Agents can raise the importance of a relationship by putting priority markers on
 Related: [[Incident Runbook]] #critical
 ```
 
-Indexed edges expose `weight` and `priority` (`low`, `normal`, `high`, `critical`) through CLI JSON, HTTP graph APIs and `brainlink_graph`.
+Indexed edges expose `weight` and `priority` (`low`, `normal`, `high`, `critical`) through CLI JSON, HTTP graph APIs and `brainlink_graph`. Brainlink indexes every non-self `[[wiki link]]` inside `## Context Links` as a graph edge. Old indexes are rebuilt automatically when their graph link model version is missing or stale.
+
+To migrate older vaults without deleting existing Markdown, generate concise context-link sections from current wiki-link mentions:
+
+```bash
+blink migrate-context-links --vault ./vault --limit 5
+blink index --vault ./vault --full
+```
 
 ## Graph UI
 
 Start the local frontend:
 
 ```bash
-blink server --host 127.0.0.1 --port 4321 --watch
+blink server --host 127.0.0.1 --port 4321
 ```
 
 By default, the server uses `$HOME/.brainlink/vault`. Pass `--vault ./vault` only when you want to inspect a custom vault.
+By default, the server watches Markdown files in local filesystem vaults and reindexes after note changes. Use `--no-watch` to disable realtime reindexing.
+By default, `blink server` tries to open the graph in a native desktop GUI window:
+- macOS: Swift + WebKit
+- Windows: PowerShell WinForms WebBrowser
+- Linux: optional Python GTK + WebKit2 (requires `python3` + `gi` + `WebKit2`)
+
+On Linux, native GUI is disabled by default for better startup performance. Enable it with `BRAINLINK_LINUX_NATIVE_GUI=1`.
+If native GUI launch is unavailable on your system, it falls back to dedicated app-window mode and then to the default browser.
+For Chromium-family browsers on Linux (`chromium`, `chromium-browser`, `google-chrome`, `microsoft-edge`, `brave-browser`), Brainlink now auto-applies compatibility flags during launch (`--ozone-platform=x11`, `--ozone-platform-hint=x11`, `--disable-gpu`, `--disable-vulkan`, `--use-gl=swiftshader`, `--disable-features=Vulkan,VaapiVideoDecoder`, `--disable-background-networking`) to avoid common Wayland/Vulkan/VAAPI startup issues.
+On Linux, Brainlink opens the graph through the system default browser first (`xdg-open`), then `$BROWSER`/detected browsers as fallback. Chromium-family app-window mode is optional via `BRAINLINK_LINUX_APP_WINDOW=1`.
+Use `--no-open` to keep it headless.
+When native GUI is used, the GUI window automatically closes when the `blink server` process stops.
 
 The graph UI shows:
 
 - notes as nodes
-- `[[wiki links]]` as weighted edges
-- details opened on node click (tags, outgoing links, backlinks, full Markdown content)
+- all non-self `[[wiki links]]` inside `## Context Links` as weighted indexed edges
+- default cauliflower-style visual layout centered on the primary hub, with segment hubs anchoring surrounding lobes and visual edges simplified to root hub -> segment hubs -> local context nodes
+- details opened in a non-modal side panel (tags, outgoing links, backlinks, full Markdown content), so zoom and pan remain available while inspecting data
 - neutral graph nodes with segment/group metadata
-- agent selector for isolated views
+- agent selector (id-only labels) for isolated views
+- context selector for segment-scoped cauliflower subgraphs derived from the visual graph context
 - graph filter matches title, path, tags and note content
-- realtime refresh while `--watch` is enabled
+- graph filter keeps hub context nodes visible (`Memory Hub`/`MOC`/high-degree fallback) to preserve relationship readability
+- realtime refresh while watch mode is enabled
 - graph controls for zoom in, zoom out, fit visible nodes and reset-to-fit-all
-- wheel zoom anchored to cursor position for faster navigation in large graphs
+- wheel zoom (including `cmd+scroll` and `ctrl+scroll`) anchored to cursor position for faster navigation in large graphs
+- wheel/button zoom updates immediately at the cursor anchor without delayed focus-transition interpolation
+- Bloom-like scene navigation: reset fits the current graph scene, wheel zoom stays anchored to the cursor, and worker-driven WebGL rendering keeps pan/zoom interaction responsive
+- zoom-out cluster mode that shows segment hub clusters first, then reveals local nodes as zoom increases
+- keyboard shortcuts: `+` zoom in, `-` zoom out, `0` reset fit
+- click on a node opens its details panel; double-click on empty canvas zooms in at cursor position
 - floating graph totals (notes, links, tags) below the Brainlink title
-- large-graph rendering safeguards (edge draw caps, lower redraw rate, zoom-aware interaction)
+- graph rendering safeguards (batched GPU draw calls, lower redraw rate, zoom-aware interaction)
+- adaptive CPU safeguards for large graphs: idle frame pacing, throttled background physics updates and cached viewport dimensions to reduce redraw/layout overhead while preserving interaction responsiveness
+- worker-first WebGL rendering with Canvas fallback when `OffscreenCanvas` or worker rendering is unavailable
+- large graph view keeps one indexed graph model across zoom levels, uses a stable visual hierarchy for rendering, uses segment clusters at high zoom-out, and shows node titles as zoom approaches readable scale
 
 The server indexes before starting by default. Use `--no-index` to skip that step:
 
@@ -582,8 +636,11 @@ The server always refuses non-loopback hosts. Brainlink HTTP only runs on localh
 Routes:
 
 - `GET /api/agents`
+- `GET /api/graph-contexts`
 - `GET /api/graph`
 - `GET /api/graph-layout`
+- `GET /api/graph-view?x=<x>&y=<y>&w=<width>&h=<height>&scale=<scale>`
+- `GET /api/graph-stream?x=<x>&y=<y>&w=<width>&h=<height>&scale=<scale>&nodeBudget=<n>&edgeBudget=<n>`
 - `GET /api/graph-node?id=<node-id>`
 - `GET /api/search?q=<query>&limit=10&mode=hybrid`
 - `GET /api/context?q=<query>&limit=12&tokens=2000&mode=hybrid`
@@ -598,6 +655,7 @@ Read routes accept `agent=<agent-id>`:
 
 ```txt
 /api/graph-layout?agent=coding-agent
+/api/graph-layout?agent=coding-agent&context=Architecture
 /api/search?q=typescript&agent=coding-agent&mode=hybrid
 /api/context?q=module-boundaries&agent=coding-agent&mode=semantic
 ```
@@ -652,6 +710,7 @@ blink config set-vault "s3://my-memory-bucket/brainlink" --global
 
 `config set-vault` writes configuration through CLI (no manual file edits required).  
 By default it writes local config (`./brainlink.config.json`), appends the vault to `allowedVaults`, and migrates Markdown memory from the current configured vault when the target is empty.  
+When the configured default vault is changed manually in config files, Brainlink also performs automatic migration on the next command that uses the configured vault (without explicit `--vault`).
 Use `--global` to write to `$BRAINLINK_HOME/brainlink.config.json`, `--no-migrate` to skip migration, and `--no-index` to skip post-migration indexing.
 `config doctor` is dry-run by default; use `--fix` to apply safe config normalization and allowlist fixes.
 
@@ -667,6 +726,18 @@ blink migrate-vault --from ~/.brainlink/vault --to ./team-vault --report ./migra
 Runs explicit markdown migration between vaults while preserving conflicts as `.conflict-<timestamp>` files.  
 Use `--dry-run` to preview `copied`, `conflicted` and `unchanged` counts before writing.
 
+### `db-import`
+
+```bash
+blink db-import --vault ./team-vault
+blink db-import --vault ./team-vault --db ./legacy/brainlink.db
+blink db-import --vault ./team-vault --db ./legacy/brainlink.db --table legacy_notes --dry-run
+```
+
+Imports durable memory from a legacy SQLite database into Markdown notes (`agents/<agent-id>/*.md`) and reindexes by default.
+When `--db` is omitted, Brainlink auto-detects common legacy paths such as `<vault>/.brainlink/brainlink.db`.
+Use `--agent <id>` to force all imported rows into one namespace, `--limit` for incremental imports, `--dry-run` to preview without writing files, and `--no-index` to defer reindexing.
+
 ### `init`
 
 ```bash
@@ -691,15 +762,72 @@ blink add "Note Title" --vault ./vault --content-file ./notes.md --no-auto-index
 
 Creates a Markdown note under `agents/<agent-id>/`. Common secret patterns are blocked by default; use `--allow-sensitive` only for an intentionally protected vault.
 To avoid disconnected memory, Brainlink auto-adds a fallback wiki edge when a note is written without links, creating agent hub notes when needed.
+`add` also returns `possibleDuplicates` (exact hash + semantic candidates) so agents can resolve duplicate memory right after writes.
+
+### `dedupe`
+
+```bash
+blink dedupe --vault ./vault --json
+blink dedupe --vault ./vault --agent coding-agent --limit 20 --min-score 0.92 --json
+blink dedupe --vault ./vault --no-semantic --json
+```
+
+Detects `possibleDuplicate` pairs using exact content hashes and optional semantic similarity.
+
+### `dedupe-resolve`
+
+```bash
+blink dedupe-resolve --vault ./vault --left agents/shared/a.md --right agents/shared/b.md --action merge --json
+blink dedupe-resolve --vault ./vault --left agents/shared/a.md --right agents/shared/b.md --action link --json
+blink dedupe-resolve --vault ./vault --left agents/shared/a.md --right agents/shared/b.md --action ignore --json
+```
+
+Resolves a duplicate pair with `merge`, `link` or `ignore`.
+When action is not `merge`, Brainlink still creates a low-priority related edge (`#related-to`) so notes remain connected.
 
 ### `index`
 
 ```bash
 blink index
 blink index --vault ./vault
+blink index --vault ./vault --full
 ```
 
-Rebuilds the local index from Markdown files.
+Rebuilds the local index from Markdown files. By default, unchanged notes reuse existing indexed chunks for speed.
+Use `--full` to force a complete source reindex of every Markdown note. Full reindex builds the replacement index before persisting it, so existing context is not cleared first.
+Brainlink also performs this complete source reindex automatically when it detects that the stored graph link model is older than the current model.
+
+### `bench`
+
+```bash
+blink bench --vault ./vault
+blink bench --vault ./vault --watch
+blink bench --vault ./vault --watch --debounce 500
+blink bench --vault ./vault --json
+```
+
+Runs indexing with realtime phase telemetry (`start`, `scan`, `parse`, `embed`, `persist`, `packs`, `complete`) and prints a benchmark summary at the end of each run.
+
+Summary includes compression behavior for `.blpk` packs when rebuild happens:
+- pack rebuild reason
+- pack count and pack build duration
+- uncompressed input bytes vs compressed output bytes
+- saved percentage
+- objective guardrails (minimum savings and maximum latency regression thresholds)
+
+Use `--watch` to keep benchmarking incremental reindex runs after Markdown changes (local filesystem vaults only).
+When `.brainlink/search-packs/manifest.json` is missing but `.blpk` files exist, Brainlink repairs the manifest first and avoids unnecessary full pack rebuild on small edits.
+
+### `pack-backup`
+
+```bash
+blink pack-backup --vault ./vault
+blink pack-backup --vault ./vault --output ./vault/.brainlink/backups/custom.blpkbak.gz
+blink pack-backup --vault ./vault --json
+```
+
+Creates an offline backup artifact of encrypted search packs with a second compression pass.
+This is intentionally outside the online retrieval path (`index`, `search`, `context`).
 
 ### `agents`
 
@@ -728,6 +856,7 @@ Modes:
 - `semantic`: local deterministic embedding similarity only.
 
 Hybrid results are cached in-memory for a short TTL and invalidated automatically when the local index file changes.
+Context selection uses a middle-out strategy: it starts from the strongest chunk in a note and expands to neighboring chunks while respecting token budget.
 
 ### `context`
 
@@ -738,6 +867,7 @@ blink context "question" --vault ./vault --agent coding-agent --mode hybrid --js
 ```
 
 Builds a compact context package for an agent.
+Repeated calls with the same vault, agent, query, mode and token/limit settings are served from a short in-memory cache while the index is unchanged.
 
 ### `links`
 
@@ -817,14 +947,31 @@ blink watch --vault ./vault
 
 Watches Markdown files and rebuilds the index when notes change.
 
+### `canonicalize-context-links`
+
+```bash
+blink canonicalize-context-links --vault ./vault --dry-run
+blink canonicalize-context-links --vault ./vault
+```
+
+Ensures existing notes have canonical `## Context Links` entries to inferred context hubs such as `User Preferences Hub`, `GitHub Repositories Hub` or `Brainlink Hub`. The command is idempotent, creates missing hub notes by default, and fully reindexes after writes unless `--no-index` is passed.
+
 ### `server`
 
 ```bash
-blink server --watch
-blink server --vault ./vault --watch
+blink server
+blink server --vault ./vault
+blink server --vault ./vault --no-open
+blink server --vault ./vault --no-watch
 ```
 
 Starts the local read-only graph UI and HTTP API.
+Watch mode is enabled by default for Markdown changes in local filesystem vaults. Use `--no-watch` to run without the watcher.
+By default, it tries to open a native desktop GUI window for the graph URL.
+On Linux, native GUI is disabled by default; enable it with `BRAINLINK_LINUX_NATIVE_GUI=1`.
+If native GUI launch is unavailable, it falls back to dedicated app-window mode and then browser open.
+When fallback opens Chromium-family browsers on Linux, Brainlink automatically uses compatibility launch flags for stable rendering on Ubuntu/Wayland setups.
+Use `--no-open` to skip that behavior.
 
 The HTTP server only binds to loopback hosts such as `127.0.0.1`, `localhost` or `::1`.
 
@@ -860,11 +1007,19 @@ If no `vault` is configured and no `--vault` flag is passed, Brainlink uses `$HO
   "allowedVaults": [".brainlink-vault"],
   "defaultAgent": "shared",
   "autoIndexOnWrite": true,
+  "autoCanonicalContextLinks": true,
   "defaultSearchLimit": 10,
   "defaultContextTokens": 2000,
   "embeddingProvider": "local",
   "defaultSearchMode": "hybrid",
   "chunkSize": 1200,
+  "searchPack": {
+    "rowChunkSize": 5000,
+    "compressionLevel": 5,
+    "useDictionary": true,
+    "guardrailMinSavingsPercent": 8,
+    "guardrailMaxLatencyRegressionPercent": 5
+  },
   "agentProfiles": {
     "coding-agent": {
       "defaultSearchMode": "semantic",
@@ -882,6 +1037,7 @@ If no `vault` is configured and no `--vault` flag is passed, Brainlink uses `$HO
 `agentProfiles` is optional. When present, CLI and MCP resolve `mode`, `limit` and `tokens` per agent automatically, then fallback to global defaults.
 
 `autoIndexOnWrite` is optional and defaults to `true`. Set it to `false` to defer indexing after writes.
+`autoCanonicalContextLinks` is optional and defaults to `true`. When enabled, `blink add`, `brainlink_add_note` and `brainlink_add_file` add a canonical `## Context Links` entry to the inferred context hub, creating that hub when needed.
 
 Use `"embeddingProvider": "none"` when you want FTS-only indexing.
 
@@ -960,7 +1116,7 @@ Local CLI:
 
 ```bash
 npm run dev -- --help
-npm run dev -- server --vault .brainlink-vault --watch
+npm run dev -- server --vault .brainlink-vault
 ```
 
 Package smoke test:
@@ -1025,6 +1181,7 @@ See [CONTRIBUTING.md](CONTRIBUTING.md).
 ## License
 
 MIT. See [LICENSE](LICENSE).
+Copyright (c) 2026 Substructa. See [COPYRIGHT.md](COPYRIGHT.md).
 
 ### Memory Optimization Loop (1-7)
 

package/dist/application/add-note.js

@@ -1,20 +1,14 @@
-import { access } from 'node:fs/promises';
-import { join } from 'node:path';
 import { writeMarkdownFile } from '../infrastructure/file-system-vault.js';
 import { sanitizeAgentId, sharedAgentId } from '../domain/agents.js';
-import { extractWikiLinks } from '../domain/markdown.js';
 import { validateNoteInput } from '../domain/note-safety.js';
 import { ensureVault } from '../infrastructure/file-system-vault.js';
+import { addCanonicalContextLinkToContent, ensureCanonicalContextHub } from './canonical-context-links.js';
 const slugify = (title) => title
     .normalize('NFKD')
     .replace(/[\u0300-\u036f]/g, '')
     .toLowerCase()
     .replace(/[^a-z0-9]+/g, '-')
     .replace(/^-+|-+$/g, '');
-const systemHubTitle = 'Memory Hub';
-const systemRootTitle = 'Knowledge Root';
-const normalizeTitle = (title) => title.trim().replace(/\.md$/i, '').toLowerCase();
-const noteFilename = (agentId, title) => `agents/${agentId}/${slugify(title) || 'untitled'}.md`;
 const buildNote = (title, content, agentId) => [
     `---`,
     `title: "${title.replaceAll('"', '\\"')}"`,
@@ -26,38 +20,6 @@ const buildNote = (title, content, agentId) => [
     content.trim(),
     ''
 ].join('\n');
-const ensureSystemNote = async (vaultPath, absoluteVaultPath, agentId, title, content) => {
-    const filename = noteFilename(agentId, title);
-    const absolutePath = join(absoluteVaultPath, filename);
-    try {
-        await access(absolutePath);
-        return;
-    }
-    catch { }
-    await writeMarkdownFile(vaultPath, filename, buildNote(title, content, agentId));
-};
-const ensureNonOrphanContent = async (vaultPath, absoluteVaultPath, title, content, agentId) => {
-    const links = extractWikiLinks(content).filter((link) => normalizeTitle(link) !== normalizeTitle(title));
-    if (links.length > 0) {
-        return {
-            content: content.trim(),
-            autoLinked: false,
-            linkTarget: null
-        };
-    }
-    const fallbackTitle = normalizeTitle(title) === normalizeTitle(systemHubTitle) ? systemRootTitle : systemHubTitle;
-    if (fallbackTitle === systemRootTitle) {
-        await ensureSystemNote(vaultPath, absoluteVaultPath, agentId, systemRootTitle, `Entry point for agent memory. [[${systemHubTitle}]] #memory #root`);
-    }
-    else {
-        await ensureSystemNote(vaultPath, absoluteVaultPath, agentId, systemHubTitle, 'Central memory index for this agent namespace. #memory #hub');
-    }
-    return {
-        content: `${content.trim()}\n\nRelated: [[${fallbackTitle}]]`,
-        autoLinked: true,
-        linkTarget: fallbackTitle
-    };
-};
 export const addNoteWithMetadata = async (vaultPath, title, content, agentId = sharedAgentId, options = {}) => {
     validateNoteInput({
         title,
@@ -65,15 +27,22 @@ export const addNoteWithMetadata = async (vaultPath, title, content, agentId = s
         allowSensitive: options.allowSensitive
     });
     const sanitizedAgentId = sanitizeAgentId(agentId);
-    const absoluteVaultPath = await ensureVault(vaultPath);
     const filename = `agents/${sanitizedAgentId}/${slugify(title) || 'untitled'}.md`;
-    const linkedContent = await ensureNonOrphanContent(vaultPath, absoluteVaultPath, title, content, sanitizedAgentId);
-    const note = buildNote(title, linkedContent.content, sanitizedAgentId);
+    await ensureVault(vaultPath);
+    const canonical = options.autoContextLinks === false
+        ? null
+        : addCanonicalContextLinkToContent(title, content.trim());
+    const hub = canonical?.changed
+        ? await ensureCanonicalContextHub(vaultPath, canonical.context, sanitizedAgentId)
+        : null;
+    const note = buildNote(title, canonical?.content ?? content.trim(), sanitizedAgentId);
     const path = await writeMarkdownFile(vaultPath, filename, note);
     return {
         path,
-        autoLinked: linkedContent.autoLinked,
-        linkTarget: linkedContent.linkTarget
+        autoLinked: canonical?.changed ?? false,
+        linkTarget: canonical?.changed ? canonical.hubTitle : null,
+        context: canonical?.context ?? null,
+        hubCreated: hub?.created ?? false
     };
 };
 export const addNote = async (vaultPath, title, content, agentId = sharedAgentId, options = {}) => (await addNoteWithMetadata(vaultPath, title, content, agentId, options)).path;

package/dist/application/auto-migrate-configured-vault.js

@@ -0,0 +1,37 @@
+import { indexVault } from './index-vault.js';
+import { migrateVaultContent } from './migrate-vault.js';
+import { getLastConfiguredVaultForKey, setLastConfiguredVaultForKey } from '../infrastructure/vault-migration-state.js';
+export const autoMigrateConfiguredVaultIfChanged = async (input) => {
+    const configKey = input.configKey.trim();
+    const configuredVault = input.configuredVault.trim();
+    if (configKey.length === 0 || configuredVault.length === 0) {
+        return {
+            changed: false,
+            migrated: false
+        };
+    }
+    const previousVault = await getLastConfiguredVaultForKey(configKey);
+    if (!previousVault) {
+        await setLastConfiguredVaultForKey(configKey, configuredVault);
+        return {
+            changed: false,
+            migrated: false
+        };
+    }
+    if (previousVault === configuredVault) {
+        return {
+            changed: false,
+            migrated: false
+        };
+    }
+    const migration = await migrateVaultContent(previousVault, configuredVault);
+    const shouldIndex = migration.copied + migration.conflicted > 0;
+    if (shouldIndex) {
+        await indexVault(configuredVault);
+    }
+    await setLastConfiguredVaultForKey(configKey, configuredVault);
+    return {
+        changed: true,
+        migrated: shouldIndex
+    };
+};