mnemon-mcp 1.0.0 → 1.1.0

package/CHANGELOG.md

@@ -7,6 +7,32 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.1.0] - 2026-03-17
+
+### Added
+- **Session lifecycle tools**: `memory_session_start`, `memory_session_end`, `memory_session_list` — group episodic memories by agent session with client, project, and summary tracking
+- **Search query logging** — `search_log` table (migration v5) for query observability: query text, mode, result count, duration
+- **Recency boost** in FTS scoring: `1 / (1 + daysSince / 365)` rewards recently created memories
+- **Query-centered snippets** — search results highlight the first matched term instead of always starting from content beginning
+- 12 new integration tests for session lifecycle (194 total: 17 md-parser + 13 kb-import + 123 integration + 41 validation)
+
+### Fixed
+- Pagination with `min_confidence`/`min_importance` filters: moved from JS post-filter to SQL WHERE (fixes empty pages at high offsets)
+- `memory_health` cleanup: chain repair now correctly reactivates predecessors when superseding entry is deleted
+- Contradiction detection: properly handles edge case where superseded memory matches source_file
+- Removed dead `conflicting` variable in memory-add
+
+## [1.0.1] - 2026-03-16
+
+### Added
+- MCP Registry manifest (`server.json`) for official registry submission
+- `mcpName` field in package.json for registry verification
+- Landing page link in README
+- Demo GIF with VHS recording scripts
+
+### Changed
+- Homepage URL updated to landing page (aisatisfy.me/mnemon/)
+
 ## [1.0.0] - 2026-03-16
 
 ### Added
@@ -30,5 +56,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - 182 tests (unit + integration + validation)
 - CI pipeline with build, test, and smoke tests
 
-[Unreleased]: https://github.com/nikitacometa/mnemon-mcp/compare/v1.0.0...HEAD
+[Unreleased]: https://github.com/nikitacometa/mnemon-mcp/compare/v1.1.0...HEAD
+[1.1.0]: https://github.com/nikitacometa/mnemon-mcp/compare/v1.0.1...v1.1.0
+[1.0.1]: https://github.com/nikitacometa/mnemon-mcp/compare/v1.0.0...v1.0.1
 [1.0.0]: https://github.com/nikitacometa/mnemon-mcp/releases/tag/v1.0.0

package/README.md

@@ -2,16 +2,22 @@
 
 [![CI](https://github.com/nikitacometa/mnemon-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/nikitacometa/mnemon-mcp/actions/workflows/ci.yml)
 [![npm version](https://img.shields.io/npm/v/mnemon-mcp)](https://www.npmjs.com/package/mnemon-mcp)
-[![Node.js](https://img.shields.io/badge/node-%E2%89%A522-brightgreen)](https://nodejs.org/)
+[![Node.js](https://img.shields.io/badge/node-%E2%89%A520-brightgreen)](https://nodejs.org/)
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
 
 **Persistent layered memory for AI agents.**
 Local-first. Zero-cloud. Single SQLite file.
 
+[Landing Page](https://aisatisfy.me/mnemon/) · [npm](https://www.npmjs.com/package/mnemon-mcp) · [GitHub](https://github.com/nikitacometa/mnemon-mcp)
+
 Your AI agent forgets everything after each session. Mnemon fixes that.
 
 It gives any [MCP](https://modelcontextprotocol.io)-compatible client — [OpenClaw](https://openclaw.ai), Claude Code, Cursor, Windsurf, or your own — a structured long-term memory backed by a single SQLite database on your machine. No API keys, no cloud, no telemetry. Just `npm install` and your agent remembers.
 
+<p align="center">
+  <img src="demo/mnemon-demo.gif" alt="mnemon-mcp demo — memory_add, memory_search, memory_inspect, memory_update" width="800">
+</p>
+
 ---
 
 ## Why Layered Memory?
@@ -121,13 +127,13 @@ Use the full path to the compiled entry point:
 echo '{"jsonrpc":"2.0","method":"tools/list","id":1}' | mnemon-mcp
 ```
 
-You should see 7 tools in the response. The database (`~/.mnemon-mcp/memory.db`) is created automatically on first run.
+You should see 10 tools in the response. The database (`~/.mnemon-mcp/memory.db`) is created automatically on first run.
 
 That's it. Your agent now has persistent memory.
 
 ## What It Can Do
 
-### 7 MCP Tools
+### 10 MCP Tools
 
 | Tool | What it does |
 |------|-------------|
@@ -138,6 +144,9 @@ That's it. Your agent now has persistent memory.
 | **`memory_inspect`** | Get layer statistics or trace a single memory's version history |
 | **`memory_export`** | Export to JSON, Markdown, or Claude-md format with filters |
 | **`memory_health`** | Run diagnostics: expired entries, orphaned chains, stale memories; optionally GC |
+| **`memory_session_start`** | Start an agent session — returns session ID for grouping memories |
+| **`memory_session_end`** | End a session with optional summary; returns duration and memory count |
+| **`memory_session_list`** | List sessions with filters by client, project, or active status |
 
 ### MCP Resources & Prompts
 
@@ -164,7 +173,9 @@ Two modes, both supporting layer / entity / scope / date / confidence filters:
 
 **FTS mode** (default) — tokenized full-text search with BM25 ranking. Multi-word queries use AND; if too few results, OR supplements with a score penalty. Progressive AND relaxation tries top-3 most specific terms before falling back to full OR.
 
-Scores: `bm25 × (0.3 + 0.7 × importance) × decay(layer)`
+Scores: `bm25 × (0.3 + 0.7 × importance) × decay(layer) × recency`
+
+Recency boost: `1 / (1 + daysSince / 365)` — gently rewards recently created memories without penalizing old ones.
 
 **Exact mode** — `LIKE` substring match for precise phrase lookups.
 
@@ -392,6 +403,45 @@ Returns: status (`healthy` / `warning` / `degraded`), per-layer stats, expired e
 
 </details>
 
+<details>
+<summary><code>memory_session_start</code></summary>
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `client` | string | Yes | Client identifier (e.g. `claude-code`, `cursor`, `api`) |
+| `project` | string | No | Project scope for this session |
+| `meta` | object | No | Additional session metadata |
+
+Returns: `id` (session UUID), `started_at` (ISO 8601).
+
+</details>
+
+<details>
+<summary><code>memory_session_end</code></summary>
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `id` | string | Yes | Session ID to end |
+| `summary` | string | No | Summary of what was accomplished (max 10K chars) |
+
+Returns: `id`, `ended_at`, `duration_minutes`, `memories_count`.
+
+</details>
+
+<details>
+<summary><code>memory_session_list</code></summary>
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `limit` | number | No | Max sessions (default 20, max 100) |
+| `client` | string | No | Filter by client |
+| `project` | string | No | Filter by project |
+| `active_only` | boolean | No | Only return sessions that haven't ended (default false) |
+
+Returns: array of sessions with `id`, `client`, `project`, `started_at`, `ended_at`, `summary`, `memories_count`.
+
+</details>
+
 ## How It Compares
 
 | | **mnemon-mcp** | mem0 | basic-memory | Anthropic KG |
@@ -412,7 +462,7 @@ Returns: status (`healthy` / `warning` / `degraded`), per-layer stats, expired e
 ```bash
 npm run dev        # run via tsx (no build step)
 npm run build      # TypeScript → dist/
-npm test           # vitest (182 tests)
+npm test           # vitest (194 tests)
 npm run bench      # performance benchmarks
 npm run db:backup  # backup database
 ```