@agentmemory/agentmemory 0.7.2 → 0.7.4

package/AGENTS.md

@@ -98,16 +98,16 @@ Hook scripts in `src/hooks/` are standalone Node.js scripts (no iii-sdk import).
 
 ## Testing
 
-- All tests must pass before PR: `npm test` (573+ tests)
+- All tests must pass before PR: `npm test` (613+ tests)
 - Mock pattern: `vi.mock("iii-sdk")` with mock `sdk.trigger`, `kv.get/set/list`
 - Test files go in `test/` with `.test.ts` extension
 - Follow existing patterns in `test/crystallize.test.ts` for function tests
 
 ## Current Stats (v0.7.0)
 
-- 41 MCP tools (7 visible by default, `AGENTMEMORY_TOOLS=all` for all)
-- 100 REST endpoints
+- 43 MCP tools (8 visible by default, `AGENTMEMORY_TOOLS=all` for all)
+- 103 REST endpoints
 - 6 MCP resources, 3 MCP prompts
 - 12 hooks, 4 skills
 - 50+ iii functions
-- 581 tests
+- 627 tests

package/README.md

@@ -26,7 +26,7 @@
 
 ---
 
-Every AI coding agent has the same blind spot. Session ends, memory vanishes. You re-explain architecture. You re-discover bugs. You re-teach preferences. Built-in memory files like CLAUDE.md and .cursorrules are 200-line sticky notes that overflow and go stale. agentmemory replaces that with a searchable, versioned, cross-agent database — 41 MCP tools, triple-stream retrieval (BM25 + vector + knowledge graph), 4-tier memory consolidation, provenance-tracked citations, and cascading staleness so retired facts never pollute your context again. One instance serves Claude Code, Cursor, Codex, Windsurf, and any MCP client simultaneously. 581 tests. Zero external DB dependencies.
+Every AI coding agent has the same blind spot. Session ends, memory vanishes. You re-explain architecture. You re-discover bugs. You re-teach preferences. Built-in memory files like CLAUDE.md and .cursorrules are 200-line sticky notes that overflow and go stale. agentmemory replaces that with a searchable, versioned, cross-agent database — 43 MCP tools, triple-stream retrieval (BM25 + vector + knowledge graph), 4-tier memory consolidation, provenance-tracked citations, and cascading staleness so retired facts never pollute your context again. One instance serves Claude Code, Cursor, Codex, Windsurf, and any MCP client simultaneously. 627 tests. Zero external DB dependencies.
 
 The result is measurable. On 240 real observations across 30 sessions, agentmemory hits 64% Recall@10 and perfect MRR while using 92% fewer tokens than dumping everything into context. When an agent searches "database performance optimization," it finds the N+1 fix you made three weeks ago — something keyword grep literally cannot do. Memories version automatically, supersede each other, propagate staleness to related graph nodes, and sync across agent instances via P2P mesh. Your agents stop repeating mistakes. Your context stays clean. Your sessions start fast.
 
@@ -131,7 +131,7 @@ These agents support hooks natively. agentmemory captures tool usage automatical
 
 ### MCP support (any MCP-compatible agent)
 
-Any agent that connects to MCP servers can use agentmemory's 41 tools, 6 resources, and 3 prompts. The agent actively queries and saves memory through MCP calls.
+Any agent that connects to MCP servers can use agentmemory's 43 tools, 6 resources, and 3 prompts. The agent actively queries and saves memory through MCP calls.
 
 | Agent | How to connect |
 |---|---|
@@ -143,7 +143,7 @@ Any agent that connects to MCP servers can use agentmemory's 41 tools, 6 resourc
 
 ### REST API (any agent, any language)
 
-Agents without hooks or MCP can integrate via 100 REST endpoints directly. This works with any agent, language, or framework.
+Agents without hooks or MCP can integrate via 103 REST endpoints directly. This works with any agent, language, or framework.
 
 ```bash
 POST /agentmemory/observe       # Capture what the agent did
@@ -161,7 +161,7 @@ GET  /agentmemory/profile       # Get project intelligence
 | Claude Code user | Plugin install (hooks + MCP + skills) |
 | Building a custom agent with Claude SDK | AgentSDKProvider (zero config) |
 | Using Cursor, Windsurf, or any MCP client | MCP server (41 tools + 6 resources + 3 prompts) |
-| Building your own agent framework | REST API (100 endpoints) |
+| Building your own agent framework | REST API (103 endpoints) |
 | Sharing memory across multiple agents | All agents point to the same iii-engine instance |
 
 ## Quick Start
@@ -632,7 +632,7 @@ ANTHROPIC_API_KEY=sk-ant-...
 
 ## API
 
-106 endpoints on port `3111` (100 core + 6 MCP protocol). Protected endpoints require `Authorization: Bearer <secret>` when `AGENTMEMORY_SECRET` is set. The table below shows a representative subset; see `src/triggers/api.ts` for the full endpoint list.
+109 endpoints on port `3111` (103 core + 6 MCP protocol). Protected endpoints require `Authorization: Bearer <secret>` when `AGENTMEMORY_SECRET` is set. The table below shows a representative subset; see `src/triggers/api.ts` for the full endpoint list.
 
 | Method | Path | Description |
 |--------|------|-------------|
@@ -700,7 +700,7 @@ ANTHROPIC_API_KEY=sk-ant-...
 /plugin install agentmemory
 ```
 
-Restart Claude Code. All 12 hooks, 4 skills, and 41 MCP tools are registered automatically.
+Restart Claude Code. All 12 hooks, 4 skills, and 43 MCP tools are registered automatically.
 
 ### Plugin Commands
 
@@ -724,72 +724,45 @@ agentmemory is built on iii-engine's three primitives:
 | Prometheus / Grafana | iii OTEL + built-in health monitor |
 | Redis (circuit breaker) | In-process circuit breaker + fallback chain |
 
-**113 source files. ~20,000 LOC. 581 tests. Zero external DB dependencies.**
-
-### Functions (57)
-
-| Function | Purpose |
-|----------|---------|
-| `mem::observe` | Store raw observation with dedup check |
-| `mem::compress` | LLM compression with validation + quality scoring + embedding |
-| `mem::search` | BM25-ranked full-text search |
-| `mem::smart-search` | Hybrid search with progressive disclosure |
-| `mem::context` | Build session context within token budget |
-| `mem::summarize` | Generate validated session summaries |
-| `mem::remember` | Save to long-term memory (auto-supersedes similar) |
-| `mem::forget` | Delete observations, sessions, or memories |
-| `mem::file-index` | File-specific observation lookup |
-| `mem::consolidate` | Merge duplicate observations |
-| `mem::patterns` | Detect recurring patterns |
-| `mem::generate-rules` | Generate CLAUDE.md rules from patterns |
-| `mem::migrate` | Import from SQLite |
-| `mem::evict` | Age + importance + cap-based memory eviction |
-| `mem::relate` | Create relationship between memories |
-| `mem::evolve` | Create new version of a memory |
-| `mem::get-related` | Traverse memory relationship graph |
-| `mem::timeline` | Chronological observations around anchor |
-| `mem::profile` | Aggregate project profile |
-| `mem::auto-forget` | TTL expiry + contradiction detection |
-| `mem::enrich` | Unified enrichment (file context + observations + bug memories) |
-| `mem::export` / `mem::import` | Full JSON round-trip (v0.3.0 – v0.7.0 formats, includes lessons) |
-| `mem::claude-bridge-read` | Read Claude Code native MEMORY.md |
-| `mem::claude-bridge-sync` | Sync top memories back to MEMORY.md |
-| `mem::graph-extract` | LLM-powered entity extraction from observations |
-| `mem::graph-query` | BFS traversal of knowledge graph |
-| `mem::graph-stats` | Node/edge counts by type |
-| `mem::consolidate-pipeline` | 4-tier memory consolidation with strength decay |
-| `mem::team-share` | Share memory/observation with team namespace |
-| `mem::team-feed` | Fetch recent shared items from team |
-| `mem::team-profile` | Aggregate team concepts, files, patterns |
-| `mem::governance-delete` | Delete specific memories with audit trail |
-| `mem::governance-bulk` | Bulk delete by type/date/quality filter |
-| `mem::snapshot-create` | Git commit memory state |
-| `mem::snapshot-list` | List all snapshots |
-| `mem::snapshot-restore` | Restore memory from snapshot commit |
-| `mem::action-create` / `action-update` | Dependency-aware work items with typed edges |
-| `mem::frontier` / `mem::next` | Priority-ranked unblocked action queue |
-| `mem::lease-acquire` / `release` / `renew` | TTL-based atomic agent claims |
-| `mem::routine-create` / `run` / `status` | Frozen workflow templates instantiated into action chains |
-| `mem::signal-send` / `read` / `threads` | Threaded inter-agent messaging with read receipts |
-| `mem::checkpoint-create` / `resolve` | External condition gates (CI, approval, deploy) |
-| `mem::flow-compress` | LLM-powered summarization of completed action chains |
-| `mem::mesh-register` / `sync` / `receive` | P2P sync between agentmemory instances |
-| `mem::detect-worktree` / `branch-sessions` | Git worktree detection for shared memory |
-| `mem::sentinel-create` / `trigger` / `check` | Event-driven condition watchers (webhook, timer, threshold, pattern, approval) |
-| `mem::sketch-create` / `add` / `promote` / `discard` | Ephemeral action graphs for exploratory work with auto-expiry |
-| `mem::crystallize` / `auto-crystallize` | LLM-powered compaction of completed action chains into crystal digests |
-| `mem::diagnose` / `heal` | Self-diagnosis across 8 categories with auto-fix for stuck/orphaned/stale state |
-| `mem::facet-tag` / `query` / `stats` | Multi-dimensional tagging with AND/OR queries on actions, memories, observations |
-| `mem::expand-query` | LLM-generated query reformulations for improved recall |
-| `mem::sliding-window` | Context-window enrichment at ingestion (resolve pronouns, abbreviations) |
-| `mem::temporal-graph` | Append-only versioned edges with point-in-time queries |
-| `mem::retention-score` / `evict` | Ebbinghaus-inspired decay with tiered storage (hot/warm/cold/evictable) |
-| `mem::graph-retrieval` | Entity search + chunk expansion + temporal queries via knowledge graph |
-| `mem::verify` | JIT verification — trace memory provenance back to source observations |
-| `mem::cascade-update` | Propagate staleness to graph nodes, edges, and sibling memories |
-| `mem::lesson-save` / `recall` / `list` | Confidence-scored lessons with dedup, reinforcement, and decay |
-| `mem::lesson-strengthen` / `decay-sweep` | Reinforce lessons on reuse, sweep for time-based decay |
-| `mem::obsidian-export` | Export vault as Obsidian-compatible Markdown with YAML frontmatter + wikilinks |
+**113 source files. ~20,000 LOC. 627 tests. Zero external DB dependencies.**
+
+### Functions (89 mem:: functions)
+
+| Category | Functions | Purpose |
+|----------|-----------|---------|
+| **Core Memory** | `observe`, `compress`, `search`, `smart-search` | Capture, compress, and search observations |
+| | `context`, `summarize`, `remember`, `forget` | Build context, generate summaries, save/delete memories |
+| | `file-context`, `enrich`, `patterns`, `generate-rules` | File history, enrichment, pattern detection, rule generation |
+| | `migrate`, `export`, `import` | SQLite migration, JSON round-trip (v0.3.0–v0.7.2) |
+| **Search** | `expand-query`, `sliding-window`, `graph-retrieval` | Query reformulations, context enrichment, entity-based retrieval |
+| | `retention-score`, `retention-evict` | Ebbinghaus decay with tiered storage (hot/warm/cold) |
+| **Memory Evolution** | `evolve`, `auto-forget`, `evict` | Version memories, TTL expiry, importance-based eviction |
+| | `consolidate`, `consolidate-pipeline` | Merge duplicates, 4-tier consolidation (working→episodic→semantic→procedural) |
+| | `verify`, `cascade-update` | Citation chain provenance, staleness propagation |
+| **Knowledge Graph** | `graph-extract`, `graph-query`, `graph-stats` | LLM entity extraction, BFS traversal, statistics |
+| | `temporal-graph-extract`, `temporal-query` | Temporal knowledge extraction + point-in-time queries |
+| **Relationships** | `relate`, `get-related`, `timeline`, `profile` | Memory relations, chronological view, project profiles |
+| **Claude Bridge** | `claude-bridge-read`, `claude-bridge-sync` | Bi-directional sync with MEMORY.md |
+| **Actions** | `action-create`, `action-update`, `action-get`, `action-list` | Dependency-aware work items with typed edges |
+| | `action-edge-create` | Create typed edges between actions (requires, unlocks, gated_by) |
+| | `frontier`, `next` | Priority-ranked unblocked action queue |
+| **Leases** | `lease-acquire`, `lease-release`, `lease-renew`, `lease-cleanup` | TTL-based atomic agent claims with auto-cleanup |
+| **Routines** | `routine-create`, `routine-freeze`, `routine-list`, `routine-run`, `routine-status` | Frozen workflow templates instantiated into action chains |
+| **Signals** | `signal-send`, `signal-read`, `signal-threads`, `signal-cleanup` | Threaded inter-agent messaging with read receipts |
+| **Checkpoints** | `checkpoint-create`, `checkpoint-resolve`, `checkpoint-list`, `checkpoint-expire` | External condition gates (CI, approval, deploy) |
+| **Mesh** | `mesh-register`, `mesh-sync`, `mesh-receive`, `mesh-list`, `mesh-remove` | P2P sync between agentmemory instances |
+| **Sentinels** | `sentinel-create`, `sentinel-trigger`, `sentinel-check`, `sentinel-cancel`, `sentinel-list`, `sentinel-expire` | Event-driven condition watchers |
+| **Sketches** | `sketch-create`, `sketch-add`, `sketch-promote`, `sketch-discard`, `sketch-list`, `sketch-gc` | Ephemeral action graphs with auto-expiry |
+| **Crystals** | `crystallize`, `auto-crystallize`, `crystal-list`, `crystal-get` | LLM-powered compaction of action chains into digests |
+| **Lessons** | `lesson-save`, `lesson-recall`, `lesson-list`, `lesson-strengthen`, `lesson-decay-sweep` | Confidence-scored lessons with dedup, reinforcement, and decay |
+| **Facets** | `facet-tag`, `facet-untag`, `facet-query`, `facet-get`, `facet-stats`, `facet-dimensions` | Multi-dimensional tagging with AND/OR queries |
+| **Diagnostics** | `diagnose`, `heal` | Self-diagnosis across 8 categories with auto-fix |
+| **Flow** | `flow-compress` | LLM summarization of completed action chains |
+| **Branch** | `detect-worktree`, `list-worktrees`, `branch-sessions` | Git worktree detection for shared memory |
+| **Team** | `team-share`, `team-feed`, `team-profile` | Namespaced shared + private team memory |
+| **Governance** | `governance-delete`, `governance-bulk`, `audit-query` | Delete with audit trail, bulk operations |
+| **Snapshots** | `snapshot-create`, `snapshot-list`, `snapshot-restore` | Git-versioned memory state |
+| **Export** | `obsidian-export` | Obsidian-compatible Markdown with YAML frontmatter + wikilinks |
 
 ### Data Model (34 KV scopes)
 
@@ -835,7 +808,7 @@ agentmemory is built on iii-engine's three primitives:
 ```bash
 npm run dev               # Hot reload
 npm run build             # Production build (~425KB)
-npm test                  # Unit tests (581 tests, ~1.5s)
+npm test                  # Unit tests (627 tests, ~1.5s)
 npm run test:integration  # API tests (requires running services)
 ```
 

package/dist/cli.mjs

@@ -159,12 +159,12 @@ async function main() {
 	p.intro("agentmemory");
 	if (skipEngine) {
 		p.log.info("Skipping engine check (--no-engine)");
-		await import("./src-1fTKFEtN.mjs");
+		await import("./src-DP8JSXkx.mjs");
 		return;
 	}
 	if (await isEngineRunning()) {
 		p.log.success("iii-engine is running");
-		await import("./src-1fTKFEtN.mjs");
+		await import("./src-DP8JSXkx.mjs");
 		return;
 	}
 	if (!await startEngine()) {
@@ -192,7 +192,7 @@ async function main() {
 		process.exit(1);
 	}
 	s.stop("iii-engine is ready");
-	await import("./src-1fTKFEtN.mjs");
+	await import("./src-DP8JSXkx.mjs");
 }
 main().catch((err) => {
 	p.log.error(err instanceof Error ? err.message : String(err));