@monoes/monomindcli 1.15.6 → 1.15.7

package/.claude/agents/github/repo-architect.md

@@ -301,7 +301,7 @@ const integrationPattern = {
     "@monomind/memory": {
       role: "persistence_layer",
       dependencies: [],
-      provides: ["AgentDB", "HNSW_search", "sessions"],
+      provides: ["LanceDB", "HNSW_search", "sessions"],
     },
   },
   communication: "MCP_protocol",

package/.claude/agents/specialists/integration-architect.md

@@ -18,7 +18,7 @@ Keep the 5 Monomind packages working as a coherent system. When a package change
 |---------|------|-------------------|
 | `@monomind/cli` | Orchestration layer | MCP server, CLI commands, init generator |
 | `@monomind/hooks` | Intelligence engine | Hook events, background workers, pattern learning |
-| `@monomind/memory` | Persistence layer | AgentDB, HNSW search, session state |
+| `@monomind/memory` | Persistence layer | LanceDB, HNSW search, session state |
 | `@monomind/security` | Input validation | CVE remediation, safe executor, path validator |
 | `@monoes/monograph` | Knowledge graph | Dependency analysis, community detection, impact |
 
@@ -46,9 +46,9 @@ All MCP tools exposed via `@monomind/cli/src/mcp-tools/` must:
 
 ```typescript
 // Standard pattern for cross-package memory access
-import { AgentDB } from '@monomind/memory';
+import { LanceDB } from '@monomind/memory';
 
-const db = AgentDB.getInstance();
+const db = LanceDB.getInstance();
 await db.store({ key, value, namespace: 'package-name' });
 const result = await db.search({ query, namespace: 'package-name' });
 ```
@@ -61,7 +61,7 @@ When a new feature spans multiple packages:
 - [ ] Hook events documented in `@monomind/hooks/src/types.ts`
 - [ ] MCP tool registered in `@monomind/cli/src/mcp-tools/index.ts`
 - [ ] Security validation added at system boundary
-- [ ] Memory schema migration written if AgentDB schema changes
+- [ ] Memory schema migration written if LanceDB schema changes
 - [ ] `sync-claude-assets.sh` run after any `.claude/` changes
 - [ ] Cross-package integration test added
 
@@ -78,7 +78,7 @@ packages/@monomind/hooks/src/
   workers/             — Background worker definitions
 
 packages/@monomind/memory/src/
-  agentdb/             — AgentDB core
+  lancedb/             — LanceDB core
   hnsw/                — Vector search
 
 packages/@monomind/security/src/
@@ -88,7 +88,7 @@ packages/@monomind/security/src/
 
 ## Coordination with Other Specialists
 
-- **Memory Specialist** — AgentDB schema changes, HNSW configuration
+- **Memory Specialist** — LanceDB schema changes, HNSW configuration
 - **Performance Engineer** — Benchmarking cross-package call overhead
 - **Security Architect** — Validating integration boundary security
 - **Queen Coordinator** — Orchestrating multi-package feature rollouts

package/.claude/commands/hive-mind/hive-mind-init.md

@@ -19,7 +19,7 @@ npx monomind hive-mind init [options]
 | `--consensus` | `-c` | string | `byzantine` | Consensus strategy: `byzantine`, `raft`, `gossip`, `crdt`, `quorum` |
 | `--max-agents` | `-m` | number | `15` | Maximum number of agents |
 | `--persist` | `-p` | boolean | `true` | Enable persistent state across sessions |
-| `--memory-backend` | — | string | `hybrid` | Memory backend: `agentdb`, `sqlite`, `hybrid` |
+| `--memory-backend` | — | string | `hybrid` | Memory backend: `lancedb`, `sqlite`, `hybrid` |
 
 ## Examples
 

package/.claude/commands/hive-mind/hive-mind-memory.md

@@ -48,7 +48,7 @@ npx monomind hive-mind memory -a list --format json
 
 ## Relationship to `monomind memory`
 
-`hive-mind memory` operates on the **hive's shared memory namespace** — values here are visible to all agents coordinating in the current hive. This is distinct from `npx monomind memory` which operates on the global AgentDB.
+`hive-mind memory` operates on the **hive's shared memory namespace** — values here are visible to all agents coordinating in the current hive. This is distinct from `npx monomind memory` which operates on the global LanceDB.
 
 Use hive memory for transient inter-agent coordination data (task results, intermediate state). Use global memory for patterns and knowledge that should persist across sessions.
 

package/.claude/commands/mastermind/brain.md

@@ -1,6 +1,6 @@
 ---
 name: mastermind-brain
-description: Mastermind brain management — inspect, compact, refresh, and control the three-tier business memory (AgentDB + Monograph)
+description: Mastermind brain management — inspect, compact, refresh, and control the three-tier business memory (LanceDB + Monograph)
 ---
 
 **First — extract repeat flags:** Follow the REPEAT PREAMBLE from `_repeat.md`. Extracts `--repeat`, `--tillend`, `--maxruns`, `--wait`, `--rep`, `--loop` from `$ARGUMENTS` before all other parsing.
@@ -14,9 +14,9 @@ Parse `$ARGUMENTS` to determine the sub-command and flags.
 Show the current state of all brain tiers across all domains.
 
 For each domain that has data, call:
-- `mcp__monomind__agentdb_health` on namespace `mastermind:<domain>:raw` → Tier 1 entry count, last write date, archived count
-- `mcp__monomind__agentdb_health` on namespace `mastermind:<domain>:weekly` → Tier 2 summary count, last compaction date
-- `mcp__monomind__agentdb_health` on namespace `mastermind:principles` → Tier 3 principle count
+- `mcp__monomind__lancedb_health` on namespace `mastermind:<domain>:raw` → Tier 1 entry count, last write date, archived count
+- `mcp__monomind__lancedb_health` on namespace `mastermind:<domain>:weekly` → Tier 2 summary count, last compaction date
+- `mcp__monomind__lancedb_health` on namespace `mastermind:principles` → Tier 3 principle count
 
 Display as a table:
 
@@ -42,9 +42,9 @@ Avg memory score: 0.64 | Entries below archive threshold: 3
 Force immediate weekly distillation across all domains (or `--domain <name>` for one domain).
 
 For each domain (or the specified domain):
-1. Retrieve all Tier 1 raw entries since last compaction via `mcp__monomind__agentdb_hierarchical-recall` (namespace `mastermind:<domain>:raw`)
+1. Retrieve all Tier 1 raw entries since last compaction via `mcp__monomind__lancedb_hierarchical-recall` (namespace `mastermind:<domain>:raw`)
 2. Produce per-domain weekly summary: synthesize decisions, patterns, and lessons into ≤300 words
-3. Store to Tier 2 via `mcp__monomind__agentdb_hierarchical-store` (namespace `mastermind:<domain>:weekly`)
+3. Store to Tier 2 via `mcp__monomind__lancedb_hierarchical-store` (namespace `mastermind:<domain>:weekly`)
 4. Archive Tier 1 entries with score < 0.1 (update metadata: `{ archived: true }`)
 5. Report: "Compacted <domain>: <N> entries → <M> summary, <K> archived"
 
@@ -56,7 +56,7 @@ Re-cluster the knowledge graph for a specific domain and rebuild Tier 3 principl
 
 1. Call `mcp__monomind__monograph_community` for nodes matching `mastermind:<domain>`
 2. For any cluster of 3+ similar nodes: merge into a single principle (LLM synthesis)
-3. Store merged principle: `mcp__monomind__agentdb_hierarchical-store` namespace `mastermind:principles`
+3. Store merged principle: `mcp__monomind__lancedb_hierarchical-store` namespace `mastermind:principles`
 4. For conflicting nodes: add `EXCEPTION` edge via `mcp__monomind__monograph_add_fact`
 5. Report: "Refreshed <domain>: <N> clusters found, <M> principles updated, <K> exceptions noted"
 
@@ -66,9 +66,9 @@ Re-cluster the knowledge graph for a specific domain and rebuild Tier 3 principl
 
 Show raw contents of a specific brain tier.
 
-- Tier 1: Call `mcp__monomind__agentdb_hierarchical-recall` on `mastermind:<domain>:raw`, display each entry with its score and date.
-- Tier 2: Call `mcp__monomind__agentdb_hierarchical-recall` on `mastermind:<domain>:weekly`, display summaries with dates.
-- Tier 3: Call `mcp__monomind__agentdb_hierarchical-recall` on `mastermind:principles`, display all principles.
+- Tier 1: Call `mcp__monomind__lancedb_hierarchical-recall` on `mastermind:<domain>:raw`, display each entry with its score and date.
+- Tier 2: Call `mcp__monomind__lancedb_hierarchical-recall` on `mastermind:<domain>:weekly`, display summaries with dates.
+- Tier 3: Call `mcp__monomind__lancedb_hierarchical-recall` on `mastermind:principles`, display all principles.
 
 Default limit: 10. Use `--limit N` to override.
 
@@ -78,7 +78,7 @@ Default limit: 10. Use `--limit N` to override.
 
 Find and archive all brain entries semantically matching the query.
 
-1. Call `mcp__monomind__agentdb_pattern-search` with query text across all mastermind namespaces
+1. Call `mcp__monomind__lancedb_pattern-search` with query text across all mastermind namespaces
 2. Display matching entries with their scores and domains
 3. Ask: "Archive these N entries? (yes/no)"
 4. If yes: update each entry's metadata to `{ archived: true }`

package/.claude/commands/mastermind/master.md

@@ -179,7 +179,7 @@ These sequences are non-negotiable in all modes:
 - **When fixing bugs**: `mastermind:debug` first (root cause) → write failing test via `mastermind:tdd` → fix → `mastermind:verify`
 - **After building**: `mastermind:review` — at minimum one pass before reporting complete
 - **Consuming a review**: `mastermind:receive-review` — verify before implementing, clarify unclear items first
-- **After any run**: Brain Write Procedure — score decisions, append to AgentDB
+- **After any run**: Brain Write Procedure — score decisions, append to LanceDB
 - **Before releasing**: `mastermind:review --tillend --auto` → `mastermind:verify` → `mastermind:finish`
 - **Isolated work**: `mastermind:worktree` before making changes to avoid contaminating main
 - **Before claiming complete**: Run `mastermind:verify` — never claim completion based on agent reports, linter passes, or partial checks
@@ -289,8 +289,8 @@ project_name="${project_name:-$(basename "$PWD")}"
 
 Follow the Brain Load Procedure from `_protocol.md`:
 
-1. Call `mcp__monomind__agentdb_hierarchical-recall` namespace `mastermind:principles` (limit 20)
-2. For each domain that appears relevant to the prompt, call `mcp__monomind__agentdb_context-synthesize` namespace `mastermind:<domain>:weekly`
+1. Call `mcp__monomind__lancedb_hierarchical-recall` namespace `mastermind:principles` (limit 20)
+2. For each domain that appears relevant to the prompt, call `mcp__monomind__lancedb_context-synthesize` namespace `mastermind:<domain>:weekly`
 3. Call `mcp__monomind__monograph_query` with 3-5 keywords from the prompt
 
 Assemble the BRAIN CONTEXT block from results.
@@ -861,7 +861,7 @@ Monotask boards:
 
 Follow the Brain Write Procedure from `_protocol.md` for each domain that ran:
 1. Score all decisions from this run
-2. Append to Tier 1 raw log (AgentDB)
+2. Append to Tier 1 raw log (LanceDB)
 3. Check and trigger weekly compaction if threshold met
 4. Check and trigger graph consolidation if cluster detected
 

package/.claude/commands/mastermind/memory.md

@@ -1,17 +1,17 @@
 ---
 name: mastermind-memory
-description: AgentDB memory system — store, search, retrieve, list, delete, and manage cross-session persistent memory with vector embeddings
+description: LanceDB memory system — store, search, retrieve, list, delete, and manage cross-session persistent memory with vector embeddings
 ---
 
 # Monomind Memory System
 
-Persistent memory backed by AgentDB with pure-JS HNSW vector indexing for semantic search (O(log n) approximate nearest neighbor). Supports cross-session and cross-agent collaboration.
+Persistent memory backed by LanceDB with pure-JS HNSW vector indexing for semantic search (O(log n) approximate nearest neighbor). Supports cross-session and cross-agent collaboration.
 
 ## Subcommands
 
 | Subcommand | Alias | Description |
 |---|---|---|
-| `init` | — | Initialize memory database (sql.js + AgentDB) |
+| `init` | — | Initialize memory database (sql.js + LanceDB) |
 | `store` | — | Store a key/value entry |
 | `edit` | — | Edit an existing entry |
 | `retrieve` | `get` | Retrieve entry by key |
@@ -30,11 +30,11 @@ Persistent memory backed by AgentDB with pure-JS HNSW vector indexing for semant
 
 ```bash
 npx monomind memory init
-npx monomind memory init --backend agentdb --verbose --verify
+npx monomind memory init --backend lancedb --verbose --verify
 npx monomind memory init --force  # Overwrite existing
 ```
 
-**Flags:** `--backend hybrid|sqlite|agentdb` (default: `hybrid`), `--path`, `--force`, `--verbose`, `--verify` (default: true), `--load-embeddings`
+**Flags:** `--backend hybrid|sqlite|lancedb` (default: `hybrid`), `--path`, `--force`, `--verbose`, `--verify` (default: true), `--load-embeddings`
 
 ## store — Store Data
 
@@ -135,7 +135,7 @@ Shows backend, total entries, storage size, oldest/newest entry.
 ## configure — Backend Settings
 
 ```bash
-npx monomind memory configure --backend agentdb
+npx monomind memory configure --backend lancedb
 npx monomind memory configure --backend hybrid --cache-size 512 --hnsw-m 16 --hnsw-ef 200
 ```
 

package/.claude/commands/memory/README.md

@@ -4,13 +4,13 @@ name: memory:README
 
 # Memory Commands
 
-Commands for the AgentDB memory system — vector search, namespaced storage, HNSW indexing, and cross-session persistence.
+Commands for the LanceDB memory system — vector search, namespaced storage, HNSW indexing, and cross-session persistence.
 
 ## Available Subcommands
 
 | Subcommand | Description |
 |---|---|
-| `memory init` | Initialize memory backend (agentdb, sqlite, hybrid) |
+| `memory init` | Initialize memory backend (lancedb, sqlite, hybrid) |
 | `memory store` | Store a memory entry with optional vector embedding |
 | `memory retrieve` | Retrieve a memory entry by key |
 | `memory search` | Search memory (semantic / keyword / hybrid) |
@@ -68,9 +68,9 @@ npx monomind memory import --input backup.json --merge
 
 | Backend | Description | Recommended |
 |---|---|---|
-| `agentdb` | Full AgentDB with HNSW vector search | Production |
+| `lancedb` | Full LanceDB with HNSW vector search | Production |
 | `sqlite` | SQLite-only, no vector search | Lightweight |
-| `hybrid` | SQLite + AgentDB HNSW | Default (recommended) |
+| `hybrid` | SQLite + LanceDB HNSW | Default (recommended) |
 
 ## See Also
 

package/.claude/commands/truth/start.md

@@ -74,8 +74,8 @@ mcp__monomind__hooks_intelligence_stats({})
 mcp__monomind__task_summary({})
 mcp__monomind__progress_summary({})
 
-// AgentDB health (memory integrity)
-mcp__monomind__agentdb_health({})
+// LanceDB health (memory integrity)
+mcp__monomind__lancedb_health({})
 ```
 
 ### Performance
@@ -105,7 +105,7 @@ When invoked, run these checks in parallel:
 mcp__monomind__system_health({})
 mcp__monomind__agent_health({})
 mcp__monomind__neural_status({ verbose: true })
-mcp__monomind__agentdb_health({})
+mcp__monomind__lancedb_health({})
 mcp__monomind__performance_report({ format: "detailed" })
 ```
 

package/.claude/helpers/extras-registry.json

@@ -3715,7 +3715,7 @@
     {
       "slug": "v1-memory-specialist",
       "name": "v1-memory-specialist",
-      "description": "v1 Memory Specialist for unifying 6+ memory systems into AgentDB with HNSW indexing. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend) to achieve 150x-12,500x search improvements.",
+      "description": "v1 Memory Specialist for unifying 6+ memory systems into LanceDB with HNSW indexing. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend) to achieve 150x-12,500x search improvements.",
       "category": "specialists",
       "filePath": "../agents/specialists/memory-specialist.md",
       "keywords": [
@@ -3724,7 +3724,7 @@
         "unifying",
         "systems",
         "into",
-        "agentdb",
+        "lancedb",
         "hnsw",
         "indexing",
         "implements",

package/.claude/helpers/skill-registry.json

@@ -509,8 +509,8 @@
       "primaryAgent": "devops"
     },
     {
-      "skill": "agentdb-vector-search",
-      "invoke": "Skill(\"agentdb-vector-search\")",
+      "skill": "lancedb-vector-search",
+      "invoke": "Skill(\"lancedb-vector-search\")",
       "description": "Vector search operations — semantic search, HNSW, embeddings, nearest neighbor",
       "keywords": [
         "vector search",
@@ -518,7 +518,7 @@
         "hnsw",
         "embedding",
         "similarity",
-        "agentdb",
+        "lancedb",
         "nearest"
       ],
       "category": "memory",
@@ -555,38 +555,38 @@
       "primaryAgent": "frontend-dev"
     },
     {
-      "skill": "agentdb-advanced",
-      "invoke": "Skill(\"agentdb-advanced\")",
-      "description": "Advanced AgentDB — QUIC sync, multi-database, custom metrics, distributed systems",
+      "skill": "lancedb-advanced",
+      "invoke": "Skill(\"lancedb-advanced\")",
+      "description": "Advanced LanceDB — QUIC sync, multi-database, custom metrics, distributed systems",
       "keywords": [
-        "agentdb",
+        "lancedb",
         "quic",
         "synchronization",
         "distributed",
         "vector-search",
         "multi-database"
       ],
-      "category": "agentdb",
+      "category": "lancedb",
       "primaryAgent": "coder"
     },
     {
-      "skill": "agentdb-learning",
-      "invoke": "Skill(\"agentdb-learning\")",
-      "description": "AgentDB RL — 9 algorithms: DQN, PPO, Decision Transformer, Q-Learning, SARSA",
+      "skill": "lancedb-learning",
+      "invoke": "Skill(\"lancedb-learning\")",
+      "description": "LanceDB RL — 9 algorithms: DQN, PPO, Decision Transformer, Q-Learning, SARSA",
       "keywords": [
         "reinforcement-learning",
         "training",
         "rl",
-        "agentdb",
+        "lancedb",
         "decision-transformer",
         "q-learning"
       ],
-      "category": "agentdb",
+      "category": "lancedb",
       "primaryAgent": "ml-developer"
     },
     {
-      "skill": "agentdb-memory-patterns",
-      "invoke": "Skill(\"agentdb-memory-patterns\")",
+      "skill": "lancedb-memory-patterns",
+      "invoke": "Skill(\"lancedb-memory-patterns\")",
       "description": "Persistent memory patterns for stateful agents and context management",
       "keywords": [
         "memory",
@@ -596,13 +596,13 @@
         "sessions",
         "stateful"
       ],
-      "category": "agentdb",
+      "category": "lancedb",
       "primaryAgent": "coder"
     },
     {
-      "skill": "agentdb-optimization",
-      "invoke": "Skill(\"agentdb-optimization\")",
-      "description": "AgentDB optimization — quantization (4-32x), HNSW (150x faster), caching, batch ops",
+      "skill": "lancedb-optimization",
+      "invoke": "Skill(\"lancedb-optimization\")",
+      "description": "LanceDB optimization — quantization (4-32x), HNSW (150x faster), caching, batch ops",
       "keywords": [
         "optimization",
         "hnsw",
@@ -611,7 +611,7 @@
         "performance",
         "batch"
       ],
-      "category": "agentdb",
+      "category": "lancedb",
       "primaryAgent": "coder"
     },
     {
@@ -731,9 +731,9 @@
       "primaryAgent": "coder"
     },
     {
-      "skill": "reasoningbank-agentdb",
-      "invoke": "Skill(\"reasoningbank-agentdb\")",
-      "description": "ReasoningBank adaptive learning with AgentDB vector search and trajectory tracking",
+      "skill": "reasoningbank-lancedb",
+      "invoke": "Skill(\"reasoningbank-lancedb\")",
+      "description": "ReasoningBank adaptive learning with LanceDB vector search and trajectory tracking",
       "keywords": [
         "reasoningbank",
         "adaptive-learning",
@@ -741,7 +741,7 @@
         "vector-search",
         "verdict"
       ],
-      "category": "agentdb",
+      "category": "lancedb",
       "primaryAgent": "ml-developer"
     },
     {
@@ -902,12 +902,12 @@
     {
       "skill": "memory-unification",
       "invoke": "Skill(\"memory-unification\")",
-      "description": "Unify 6+ memory systems into AgentDB with HNSW indexing (150x-12,500x faster)",
+      "description": "Unify 6+ memory systems into LanceDB with HNSW indexing (150x-12,500x faster)",
       "keywords": [
         "memory",
         "unification",
         "hnsw",
-        "agentdb",
+        "lancedb",
         "hierarchical"
       ],
       "category": "memory",

package/.claude/helpers/statusline.cjs

@@ -283,7 +283,7 @@ function getLearningStats() {
     path.join(CWD, '.monomind', 'memory.db'),
     path.join(CWD, '.claude', 'memory.db'),
     path.join(CWD, 'data', 'memory.db'),
-    path.join(CWD, '.agentdb', 'memory.db'),
+    path.join(CWD, '.lancedb', 'memory.db'),
   ];
 
   for (const dbPath of memoryPaths) {
@@ -431,7 +431,7 @@ function getSwarmStatus() {
 function getSystemMetrics() {
   const memoryMB = Math.floor(process.memoryUsage().heapUsed / 1024 / 1024);
   const learning = getLearningStats();
-  const agentdb = getAgentDBStats();
+  const lancedb = getLanceDBStats();
 
   // Intelligence from learning.json
   const learningData = readJSON(path.join(CWD, '.monomind', 'metrics', 'learning.json'));
@@ -443,7 +443,7 @@ function getSystemMetrics() {
   } else {
     // Use actual vector/entry counts — 2000 entries = 100%
     const fromPatterns = learning.patterns > 0 ? Math.min(100, Math.floor(learning.patterns / 20)) : 0;
-    const fromVectors = agentdb.vectorCount > 0 ? Math.min(100, Math.floor(agentdb.vectorCount / 20)) : 0;
+    const fromVectors = lancedb.vectorCount > 0 ? Math.min(100, Math.floor(lancedb.vectorCount / 20)) : 0;
     intelligencePct = Math.max(fromPatterns, fromVectors);
   }
 
@@ -559,8 +559,8 @@ function getActiveAgent() {
   } catch { return null; }
 }
 
-// AgentDB stats — count real entries, not file-size heuristics
-function getAgentDBStats() {
+// LanceDB stats — count real entries, not file-size heuristics
+function getLanceDBStats() {
   let vectorCount = 0;
   let dbSizeKB = 0;
   let namespaces = 0;
@@ -1142,7 +1142,7 @@ function generateDashboard() {
   const system      = getSystemMetrics();
   const adrs        = getADRStatus();
   const hooks       = getHooksStatus();
-  const agentdb     = getAgentDBStats();
+  const lancedb     = getLanceDBStats();
   const tests       = getTestStats();
   const session     = getSessionStats();
   const integration = getIntegrationStatus();
@@ -1288,7 +1288,7 @@ function generateJSON() {
     system:     getSystemMetrics(),
     adrs:       getADRStatus(),
     hooks:      getHooksStatus(),
-    agentdb:    getAgentDBStats(),
+    lancedb:    getLanceDBStats(),
     tests:      getTestStats(),
     git:        { modified: git.modified, untracked: git.untracked, staged: git.staged, ahead: git.ahead, behind: git.behind },
     tokenCost:  getTokenCostSummary(),
@@ -1313,7 +1313,7 @@ if (require.main !== module) {
   module.exports = {
     readJSON, safeStat, modelLabel,
     getSecurityStatus, getSwarmStatus, getADRStatus,
-    getHooksStatus, getActiveAgent, getAgentDBStats,
+    getHooksStatus, getActiveAgent, getLanceDBStats,
     getLearningStats, getTestStats, getIntegrationStatus,
     generateJSON,
   };

package/.claude/skills/agentic-jujutsu/SKILL.md

@@ -165,7 +165,7 @@ const key = crypto.randomBytes(32).toString('base64');
 jj.enableEncryption(key);
 ```
 
-### 6. Operation Tracking with AgentDB
+### 6. Operation Tracking with LanceDB
 
 Automatic tracking of all operations:
 
@@ -396,7 +396,7 @@ for (let i = 1; i <= 10; i++) {
 | `queryTrajectories(task, limit)` | Find similar trajectories | JSON: Trajectory[] |
 | `resetLearning()` | Clear learned data | void |
 
-### AgentDB Methods
+### LanceDB Methods
 
 | Method | Description | Returns |
 |--------|-------------|---------|
@@ -628,7 +628,7 @@ async function agentSwarm(taskList) {
 - **GitHub**: https://github.com/monoes/monomind
 - **Full README**: See package README.md
 - **Validation Guide**: docs/VALIDATION_FIXES_v2.3.1.md
-- **AgentDB Guide**: docs/AGENTDB_GUIDE.md
+- **LanceDB Guide**: docs/LANCEDB_GUIDE.md
 
 ## Version History
 

package/.claude/skills/mastermind/_protocol.md

@@ -29,12 +29,12 @@ This makes delegation recursive: every spawned agent can itself spawn sub-agents
 Execute at the START of every mastermind run (master or standalone domain command). Load in this order:
 
 **Step A — Tier 3 core principles (all domains):**
-Try `mcp__monomind__agentdb_hierarchical-recall` with query `"mastermind principles"`, topK 20.
-If it returns `"AgentDB bridge not available"` or any error, fall back to:
+Try `mcp__monomind__lancedb_hierarchical-recall` with query `"mastermind principles"`, topK 20.
+If it returns `"LanceDB bridge not available"` or any error, fall back to:
 `mcp__monomind__memory_search` with query `"mastermind principles"`, namespace `"mastermind:principles"`, limit 20.
 
 **Step B — Tier 2 weekly summary for this domain:**
-Try `mcp__monomind__agentdb_context-synthesize` with query `[current prompt keywords]`, maxEntries 10.
+Try `mcp__monomind__lancedb_context-synthesize` with query `[current prompt keywords]`, maxEntries 10.
 If it fails, fall back to:
 `mcp__monomind__memory_search` with query `[current prompt keywords]`, namespace `"mastermind:<domain>:weekly"`, limit 10.
 
@@ -69,31 +69,31 @@ score = confidence × (1 / (days_since_run + 1)) × log(uses + 1)
 - `uses`: 1 (first write)
 
 **Step 2 — Append to Tier 1 raw log:**
-Try `mcp__monomind__agentdb_hierarchical-store` with:
+Try `mcp__monomind__lancedb_hierarchical-store` with:
 - namespace: `mastermind:<domain>:raw`
 - content: [full unified output schema YAML from this run, as a string]
 - metadata: `{ score, project, run_id, date: ISO8601, domain }`
 
-If AgentDB is unavailable, fall back to `mcp__monomind__memory_store`:
+If LanceDB is unavailable, fall back to `mcp__monomind__memory_store`:
 - key: `mastermind:<domain>:run:<run_id>`
 - value: [JSON-encoded unified output schema]
 - namespace: `mastermind:<domain>:raw`
 - tags: `["mastermind", "<domain>", "run"]`
 
 **Step 3 — Check weekly compaction trigger:**
-Try `mcp__monomind__agentdb_health` on namespace `mastermind:<domain>:raw`.
+Try `mcp__monomind__lancedb_health` on namespace `mastermind:<domain>:raw`.
 If unavailable, call `mcp__monomind__memory_stats` and check entry count manually.
 If `entry_count >= 20` OR `days_since_last_compaction >= 7`:
 1. Retrieve all Tier 1 entries since last compaction
 2. Produce a per-domain weekly summary (use LLM synthesis: "Summarize the key decisions, patterns, and lessons from these run logs in under 300 words")
-3. Store summary: `mcp__monomind__agentdb_hierarchical-store` namespace `mastermind:<domain>:weekly`
+3. Store summary: `mcp__monomind__lancedb_hierarchical-store` namespace `mastermind:<domain>:weekly`
 4. Archive (do not delete) Tier 1 entries with score < 0.1 by updating their metadata: `{ archived: true }`
 
 **Step 4 — Check graph consolidation trigger:**
 Call `mcp__monomind__monograph_community` for nodes matching `mastermind:<domain>`.
 If 3+ similar memory nodes are detected in a cluster:
 1. Merge into a single principle via LLM: "Distill these memories into one clear principle in 1-2 sentences"
-2. Store principle: `mcp__monomind__agentdb_hierarchical-store` namespace `mastermind:principles`
+2. Store principle: `mcp__monomind__lancedb_hierarchical-store` namespace `mastermind:principles`
 3. Add `EXCEPTION` edge in Monograph for any conflicting memory: `mcp__monomind__monograph_add_fact`
 
 ---

package/README.md

@@ -66,7 +66,7 @@ flowchart TD
     R["Reviewer"]
     M["Growth Marketer"]
     BOARD[("Shared\nTask Board")]
-    MEM[("AgentDB\nMemory")]
+    MEM[("LanceDB\nMemory")]
 
     U --> CO --> RO --> BOSS
     BOSS -->|spawns| W
@@ -126,7 +126,7 @@ Type "go" to save, or describe changes.
 | **Boss agent** | Coordinator type, no supervisor — owns the goal |
 | **Role agents** | Spawned on demand, specialized by task type |
 | **Task board** | Todo → Doing → Done, shared across all agents |
-| **Memory** | All output stored in org-scoped AgentDB namespace |
+| **Memory** | All output stored in org-scoped LanceDB namespace |
 | **Checkpoint** | State saved every 30 min — survives crashes and restarts |
 | **Governance** | `auto` (free), `board` (approve sensitive), `strict` (approve all external actions) |
 
@@ -221,13 +221,13 @@ Open Claude Code. You now have 80+ slash commands available:
 
 ## 🧠 Memory That Persists
 
-Every session, every agent, every org writes to **AgentDB** — a hybrid SQLite + HNSW vector store that survives across sessions. The next time you run anything, Monomind already knows what was built, what failed, and which patterns work.
+Every session, every agent, every org writes to **LanceDB** — a hybrid SQLite + HNSW vector store that survives across sessions. The next time you run anything, Monomind already knows what was built, what failed, and which patterns work.
 
 ```mermaid
 graph TD
     L0["L0 - In-flight\nCurrent session drawers\nephemeral"]
     L1["L1 - Working\nCross-session memory\nBM25 K1=1.5, B=0.75"]
-    L2["L2 - Long-term\nAgentDB + HNSW index\nSemantic search"]
+    L2["L2 - Long-term\nLanceDB + HNSW index\nSemantic search"]
     L3["L3 - Shared\nCross-agent namespace\nFederated swarm reads"]
 
     L0 -->|promoted| L1 --> L2 --> L3
@@ -275,7 +275,7 @@ flowchart LR
     H --> I["route\nlearn\nbuild-agents"]
     H --> T["teammate-idle\ntask-completed"]
 
-    I --> DB[("AgentDB\npatterns.json")]
+    I --> DB[("LanceDB\npatterns.json")]
     DB -->|next session| CE
 ```
 
@@ -358,7 +358,7 @@ graph TD
     CC <-->|"23 tools: monograph, memory, swarm"| MCP
     MCP <--> D
 
-    D --> ADB[("AgentDB\nSQLite + HNSW")]
+    D --> ADB[("LanceDB\nSQLite + HNSW")]
     D --> MG[("Monograph\ncode graph")]
     D --> HK["Hooks\n22 event types"]
     D --> SW["Swarm\n6 topologies\n5 consensus algos"]

package/dist/src/__tests__/browse-analyzer.test.js

@@ -38,7 +38,24 @@ function mockPage(url = 'https://linkedin.com/feed', title = 'LinkedIn') {
 describe('analyzePageForAction', () => {
     let analyzePageForAction;
     beforeEach(async () => {
-        mockCreate.mockClear();
+        mockCreate.mockResolvedValue({
+            content: [{
+                    type: 'text',
+                    text: JSON.stringify({
+                        id: 'linkedin:comment_post',
+                        platform: 'linkedin',
+                        name: 'Comment on Post',
+                        params: ['post_url', 'text'],
+                        steps: [
+                            { type: 'navigate', url: '{{params.post_url}}' },
+                            { type: 'find', selectors: ['.comment-box'], as: 'box' },
+                            { type: 'click', target: '{{box}}' },
+                            { type: 'type', target: '{{box}}', text: '{{params.text}}', humanDelay: true },
+                            { type: 'wait', condition: 'network_idle', timeout: 3000 },
+                        ],
+                    }),
+                }],
+        });
         const mod = await import('@monoes/monobrowse');
         analyzePageForAction = mod.analyzePageForAction;
     });