better-mem0-mcp 1.1.4__py3-none-any.whl → 1.1.6__py3-none-any.whl

better_mem0_mcp/docs/memory.md

@@ -17,6 +17,8 @@ Save information to long-term memory. Mem0 automatically:
 {"action": "add", "content": "User prefers dark mode and uses FastAPI"}
 ```
 
+**Response:** `Saved: {results: [{id, memory, event}]}`
+
 ### search
 Semantic search across stored memories. Combines vector search with graph context.
 
@@ -24,6 +26,8 @@ Semantic search across stored memories. Combines vector search with graph contex
 {"action": "search", "query": "coding preferences", "limit": 5}
 ```
 
+**Response:** Formatted list of matching memories with optional graph context.
+
 ### list
 Get all stored memories for a user.
 
@@ -31,6 +35,8 @@ Get all stored memories for a user.
 {"action": "list"}
 ```
 
+**Response:** `Memories (N): - [id] memory text`
+
 ### delete
 Remove a memory by ID.
 
@@ -38,10 +44,17 @@ Remove a memory by ID.
 {"action": "delete", "memory_id": "abc12345-..."}
 ```
 
+**Response:** `Deleted: {memory_id}`
+
 ## Parameters
 - `action` - Required: add, search, list, delete
 - `content` - Required for add: information to remember
 - `query` - Required for search: what to search for
 - `memory_id` - Required for delete: ID of memory to remove
 - `limit` - Optional for search: max results (default: 5)
-- `user_id` - Optional: scope memories to a specific user
+- `user_id` - Optional: scope memories to a specific user (default: "default")
+
+## Technical Notes
+- Mem0 API returns `{"results": [...]}` for both `search()` and `get_all()`
+- Graph context is automatically included in search results when available
+- Embeddings use 1536 dimensions for pgvector HNSW compatibility

better_mem0_mcp/server.py

@@ -108,10 +108,10 @@ async def memory(
             if not query:
                 return "Error: 'query' required for search action"
 
-            # Vector search - returns {"memories": [...]}
+            # Vector search - returns {"results": [...]} (same as get_all)
             response = _memory.search(query, user_id=user_id, limit=limit)
             memories = (
-                response.get("memories", []) if isinstance(response, dict) else response
+                response.get("results", []) if isinstance(response, dict) else response
             )
 
             # Add graph context

{better_mem0_mcp-1.1.4.dist-info → better_mem0_mcp-1.1.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: better-mem0-mcp
-Version: 1.1.4
+Version: 1.1.6
 Summary: Zero-setup MCP Server for AI memory - works with Neon/Supabase
 Project-URL: Homepage, https://github.com/n24q02m/better-mem0-mcp
 Project-URL: Repository, https://github.com/n24q02m/better-mem0-mcp.git
@@ -29,16 +29,28 @@ Description-Content-Type: text/markdown
 
 # better-mem0-mcp
 
-**Zero-setup** MCP Server for AI memory. Works with Neon/Supabase free tier.
+**Self-hosted MCP Server for AI memory with PostgreSQL (pgvector).**
 
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
+[![PyPI](https://img.shields.io/pypi/v/better-mem0-mcp)](https://pypi.org/project/better-mem0-mcp/)
+[![Docker](https://img.shields.io/docker/v/n24q02m/better-mem0-mcp?label=docker)](https://hub.docker.com/r/n24q02m/better-mem0-mcp)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
+
+## Features
+
+- **Self-hosted PostgreSQL** - Your data stays with you (Neon/Supabase free tier supported)
+- **Graph Memory** - SQL-based relationship tracking alongside vector memory
+- **Multi-provider LLM** - Gemini, OpenAI, Anthropic, Groq, DeepSeek, Mistral
+- **Fallback chains** - Multi-key per provider + multi-model fallback
+- **Zero manual setup** - Just `DATABASE_URL` + `API_KEYS`
+
+---
 
 ## Quick Start
 
 ### 1. Get Prerequisites
 
-- **Database**: [Neon](https://neon.tech) or [Supabase](https://supabase.com) (free tier)
-- **API Key**: [Google AI Studio](https://aistudio.google.com/apikey) (free tier)
+- **Database**: [Neon](https://neon.tech) or [Supabase](https://supabase.com) (free tier works)
+- **API Key**: Any supported provider ([Google AI Studio](https://aistudio.google.com/apikey) is free)
 
 ### 2. Add to mcp.json
 
@@ -78,7 +90,7 @@ Description-Content-Type: text/markdown
 
 ### 3. Done!
 
-Ask Claude: "Remember that I prefer dark mode and use FastAPI"
+Ask your AI: "Remember that I prefer dark mode and use FastAPI"
 
 ---
 
@@ -86,22 +98,26 @@ Ask Claude: "Remember that I prefer dark mode and use FastAPI"
 
 | Variable | Required | Description |
 |----------|----------|-------------|
-| `DATABASE_URL` | Yes | PostgreSQL connection string |
-| `API_KEYS` | Yes | `provider:key,...` (multi-key per provider OK) |
-| `LLM_MODELS` | No | `provider/model,...` (fallback chain) |
-| `EMBEDDER_MODELS` | No | `provider/model,...` (fallback chain) |
+| `DATABASE_URL` | Yes | PostgreSQL with pgvector extension |
+| `API_KEYS` | Yes | `provider:key` pairs, comma-separated |
+| `LLM_MODELS` | No | Model fallback chain |
+| `EMBEDDER_MODELS` | No | Embedding model chain |
+
+### Supported Providers
+
+`gemini`, `openai`, `anthropic`, `groq`, `deepseek`, `mistral`
 
 ### Examples
 
-**Minimal (Gemini only):**
-```
+**Single provider:**
+```bash
 API_KEYS=gemini:AIza...
 ```
 
 **Multi-key with fallback:**
-```
+```bash
 API_KEYS=gemini:AIza-1,gemini:AIza-2,openai:sk-xxx
-LLM_MODELS=gemini/gemini-2.5-flash,openai/gpt-4o-mini
+LLM_MODELS=gemini/gemini-3-flash-preview,openai/gpt-4o-mini
 EMBEDDER_MODELS=gemini/gemini-embedding-001,openai/text-embedding-3-small
 ```
 
@@ -109,7 +125,7 @@ EMBEDDER_MODELS=gemini/gemini-embedding-001,openai/text-embedding-3-small
 
 | Setting | Default |
 |---------|---------|
-| `LLM_MODELS` | `gemini/gemini-2.5-flash` |
+| `LLM_MODELS` | `gemini/gemini-3-flash-preview` |
 | `EMBEDDER_MODELS` | `gemini/gemini-embedding-001` |
 
 ---
@@ -118,32 +134,41 @@ EMBEDDER_MODELS=gemini/gemini-embedding-001,openai/text-embedding-3-small
 
 | Tool | Description |
 |------|-------------|
-| `memory` | `action`: add, search, list, delete |
-| `help` | Detailed documentation |
+| `memory` | Memory operations: `add`, `search`, `list`, `delete` |
+| `help` | Get full documentation for tools |
 
-### Usage
+### Usage Examples
 
 ```json
 {"action": "add", "content": "I prefer TypeScript over JavaScript"}
-{"action": "search", "query": "preferences"}
+{"action": "search", "query": "programming preferences"}
 {"action": "list"}
 {"action": "delete", "memory_id": "abc123"}
 ```
 
 ---
 
-## Why better-mem0-mcp?
+## Build from Source
+
+```bash
+git clone https://github.com/n24q02m/better-mem0-mcp
+cd better-mem0-mcp
 
-| Feature | Official mem0-mcp | better-mem0-mcp |
-|---------|-------------------|-----------------|
-| Storage | Mem0 Cloud | **Self-hosted PostgreSQL** |
-| Graph Memory | No | **Yes (SQL-based)** |
-| LLM Provider | OpenAI only | **Any (Gemini/OpenAI/Ollama/...)** |
-| Fallback | No | **Yes (multi-key + multi-model)** |
-| Setup | API Key | **DATABASE_URL + API_KEYS** |
+# Setup (requires mise: https://mise.jdx.dev/)
+mise run setup
+
+# Run
+uv run better-mem0-mcp
+```
+
+**Requirements:** Python 3.13+
 
 ---
 
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md)
+
 ## License
 
-MIT
+MIT - See [LICENSE](LICENSE)

{better_mem0_mcp-1.1.4.dist-info → better_mem0_mcp-1.1.6.dist-info}/RECORD

@@ -3,10 +3,10 @@ better_mem0_mcp/__main__.py,sha256=IeeRidmZF4oBaamjQM6FUbhXpsSdE4sQF_6y_D2GEE4,1
 better_mem0_mcp/config.py,sha256=vgKLIw3jHyeBLTzzBnuHV5x6Nra0Rbav1IJRL8rLCuk,5576
 better_mem0_mcp/graph.py,sha256=rE9z6XECiAktEqDNgmwqCpFpvKSn3azO9H4sRBhj8UU,6195
 better_mem0_mcp/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-better_mem0_mcp/server.py,sha256=feOliZQqPYqACXIrWCnxqO9mGk1KzR9OAGAo-vh2Cnc,5483
-better_mem0_mcp/docs/memory.md,sha256=jqoxBYHVh2N9TZbt77qY5zhL1vSU-Ro-yuaczT1r7Mo,1126
-better_mem0_mcp-1.1.4.dist-info/METADATA,sha256=WJcMNmrNrKmC_vCE2_qnsEGd1XVH_SShaYEKououjJk,3888
-better_mem0_mcp-1.1.4.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-better_mem0_mcp-1.1.4.dist-info/entry_points.txt,sha256=2b7E3D6yo94mQXP2Ms0bhUlWkK9f664f0GrstImOq30,57
-better_mem0_mcp-1.1.4.dist-info/licenses/LICENSE,sha256=d7xQ6sRyeGus6gnvwgqiQtSY7XdFw0Jd0w5-Co_xHnk,1064
-better_mem0_mcp-1.1.4.dist-info/RECORD,,
+better_mem0_mcp/server.py,sha256=QYLP46pz0U9gkxQKB_g8FMga77ywElMMjSCU-hGZQ-M,5499
+better_mem0_mcp/docs/memory.md,sha256=198dDuAGccG5Ca7rhEXIU03ZhxNKK44B_Brl2glurGc,1608
+better_mem0_mcp-1.1.6.dist-info/METADATA,sha256=g0v4rbGy4eUlqCMCgxOSralR0r80Lmp4RU97oDTjYL4,4540
+better_mem0_mcp-1.1.6.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+better_mem0_mcp-1.1.6.dist-info/entry_points.txt,sha256=2b7E3D6yo94mQXP2Ms0bhUlWkK9f664f0GrstImOq30,57
+better_mem0_mcp-1.1.6.dist-info/licenses/LICENSE,sha256=d7xQ6sRyeGus6gnvwgqiQtSY7XdFw0Jd0w5-Co_xHnk,1064
+better_mem0_mcp-1.1.6.dist-info/RECORD,,