feat(memory): Add Valkey vector memory store

docs/user_guide/en/modules/memory.md

@@ -42,13 +42,30 @@ memory:
       agent_id: my-agent
 ```
 
+### Valkey Memory Config
+```yaml
+memory:
+  - name: chatdev_memory
+    type: valkey
+    config:
+      host: localhost
+      port: 6379
+      index_name: chatdev_memory
+      ttl_seconds: 86400
+      embedding:
+        provider: openai
+        model: text-embedding-3-small
+        api_key: ${API_KEY}
+```
+
 ## 3. Built-in Store Comparison
 | Type | Path | Highlights | Best for |
 | --- | --- | --- | --- |
 | `simple` | `node/agent/memory/simple_memory.py` | Optional disk persistence (JSON) after runs; FAISS + semantic rerank; read/write capable. | Small conversation history, prototypes. |
 | `file` | `node/agent/memory/file_memory.py` | Chunks files/dirs into a vector index, read-only, auto rebuilds when files change. | Knowledge bases, doc QA. |
 | `blackboard` | `node/agent/memory/blackboard_memory.py` | Lightweight append-only log trimmed by time/count; no vector search. | Broadcast boards, pipeline debugging. |
 | `mem0` | `node/agent/memory/mem0_memory.py` | Cloud-managed by Mem0; semantic search + graph relationships; no local embeddings or persistence needed. Requires `mem0ai` package. | Production memory, cross-session persistence, multi-agent memory sharing. |
+| `valkey` | `node/agent/memory/valkey_memory.py` | HNSW vector index via Valkey Search; server-side persistence, cross-process sharing, TTL auto-expiry. Requires `valkey-glide-sync` package. | Self-hosted persistent memory, multi-process deployments, privacy-sensitive environments. |
 
 All stores register through `register_memory_store()` so summaries show up in UI via `MemoryStoreConfig.field_specs()`.
 
@@ -117,6 +134,42 @@ This schema lets multimodal outputs flow into Memory/Thinking modules without ex
 - **Persistence** – Fully cloud-managed. `load()` and `save()` are no-ops. Memories persist across runs and sessions automatically.
 - **Dependencies** – Requires `mem0ai` package (`pip install mem0ai`).
 
+### 5.5 ValkeyMemory
+- **Config** – Specify connection parameters and index settings via `ValkeyMemoryConfig`.
+  ```yaml
+  memory:
+    - name: chatdev_memory
+      type: valkey
+      config:
+        host: localhost
+        port: 6379
+        index_name: chatdev_memory
+        ttl_seconds: 86400
+        embedding:
+          provider: openai
+          model: text-embedding-3-small
+          api_key: ${API_KEY}
+  ```
+  | Field | Description | Default |
+  | --- | --- | --- |
+  | `host` | Valkey server address | `localhost` |
+  | `port` | Port (1-65535) | `6379` |
+  | `username` | ACL username | `None` |
+  | `password` | Auth password | `None` |
+  | `db` | Database index (0-15) | `0` |
+  | `use_tls` | Enable TLS encryption for the connection | `false` |
+  | `index_name` | FT index name | `memory_index` |
+  | `key_prefix` | Hash key prefix | `memory:` |
+  | `ttl_seconds` | Memory expiry in seconds; `None` means never expire | `None` |
+  | `embedding` | Nested `EmbeddingConfig` (required) | — |
+- **Index creation** – On first instantiation, automatically calls `FT.CREATE` to build an HNSW vector index (COSINE distance) with `content_summary` (TEXT), `agent_role` (TAG), `timestamp` (NUMERIC), and `embedding` (VECTOR) fields. Silently skips if the index already exists.
+- **Retrieval** – Executes a KNN query via `FT.SEARCH`, returns top-k results sorted by cosine similarity. Low-relevance results are filtered by `similarity_threshold`.
+- **Write** – `update()` encodes input text into a float32 vector and stores it as a Valkey Hash (`HSET`). When `ttl_seconds` is configured, `EXPIRE` is called to set the TTL.
+- **Persistence** – Managed by the Valkey server. `load()` and `save()` are no-ops. Data survives process restarts, and multiple processes can concurrently read/write the same index.
+- **Error handling** – If Valkey does not have the Search module loaded, initialization raises a `RuntimeError` with installation guidance.
+- **Dependencies** – Requires `valkey-glide-sync` package (`pip install 'chatdev[valkey]'`).
+- **Best for** – Self-hosted deployments needing persistence, cross-process sharing, and automatic expiry; a drop-in alternative to Mem0 when cloud services are not acceptable for privacy reasons.
+
 ## 6. EmbeddingConfig Notes
 - Fields: `provider`, `model`, `api_key`, `base_url`, `params`.
 - `provider=openai` uses the official client; override `base_url` for compatibility layers.

docs/user_guide/zh/modules/memory.md

@@ -42,13 +42,30 @@ memory:
       agent_id: my-agent
 ```
 
+### Valkey Memory 配置
+```yaml
+memory:
+  - name: chatdev_memory
+    type: valkey
+    config:
+      host: localhost
+      port: 6379
+      index_name: chatdev_memory
+      ttl_seconds: 86400
+      embedding:
+        provider: openai
+        model: text-embedding-3-small
+        api_key: ${API_KEY}
+```
+
 ## 3. 内置 Memory Store 对比
 | 类型 | 路径 | 特点 | 适用场景 |
 | --- | --- | --- | --- |
 | `simple` | `node/agent/memory/simple_memory.py` | 运行结束后可选择落盘（JSON）；使用向量搜索（FAISS）+语义重打分；支持读写 | 小规模对话记忆、快速原型 |
 | `file` | `node/agent/memory/file_memory.py` | 将指定文件/目录切片为向量索引，只读；自动检测文件变更并更新索引 | 知识库、文档问答 |
 | `blackboard` | `node/agent/memory/blackboard_memory.py` | 轻量附加日志，按时间/条数裁剪；不依赖向量检索 | 简易广播板、流水线调试 |
 | `mem0` | `node/agent/memory/mem0_memory.py` | 由 Mem0 云端托管；支持语义搜索 + 图关系；无需本地 embedding 或持久化。需安装 `mem0ai` 包。 | 生产级记忆、跨会话持久化、多 Agent 记忆共享 |
+| `valkey` | `node/agent/memory/valkey_memory.py` | 使用 Valkey Search 的 HNSW 向量索引；服务端持久化、跨进程共享、支持 TTL 自动过期。需安装 `valkey-glide-sync` 包。 | 自托管持久记忆、多进程部署、隐私敏感环境 |
 
 > 所有内置 store 都会在 `register_memory_store()` 中注册，摘要可通过 `MemoryStoreConfig.field_specs()` 在 UI 中展示。
 
@@ -119,6 +136,42 @@ nodes:
 - **持久化**：完全由云端托管。`load()` 和 `save()` 为空操作（no-op）。记忆在不同运行和会话间自动持久化。
 - **依赖**：需安装 `mem0ai` 包（`pip install mem0ai`）。
 
+### 5.5 ValkeyMemory
+- **配置**：通过 `ValkeyMemoryConfig` 指定连接参数和索引设置。
+  ```yaml
+  memory:
+    - name: chatdev_memory
+      type: valkey
+      config:
+        host: localhost
+        port: 6379
+        index_name: chatdev_memory
+        ttl_seconds: 86400
+        embedding:
+          provider: openai
+          model: text-embedding-3-small
+          api_key: ${API_KEY}
+  ```
+  | 字段 | 说明 | 默认值 |
+  | --- | --- | --- |
+  | `host` | Valkey 服务器地址 | `localhost` |
+  | `port` | 端口（1-65535） | `6379` |
+  | `username` | ACL 用户名 | `None` |
+  | `password` | 认证密码 | `None` |
+  | `db` | 数据库索引（0-15） | `0` |
+  | `use_tls` | 启用 TLS 加密连接 | `false` |
+  | `index_name` | FT 索引名称 | `memory_index` |
+  | `key_prefix` | Hash key 前缀 | `memory:` |
+  | `ttl_seconds` | 记忆过期时间（秒），`None` 表示永不过期 | `None` |
+  | `embedding` | `EmbeddingConfig` 嵌套配置（必须提供） | — |
+- **索引创建**：首次实例化时自动调用 `FT.CREATE` 创建 HNSW 向量索引（COSINE 距离），包含 `content_summary`（TEXT）、`agent_role`（TAG）、`timestamp`（NUMERIC）、`embedding`（VECTOR）字段。若索引已存在则静默跳过。
+- **检索**：使用 `FT.SEARCH` 执行 KNN 查询，返回 top-k 结果并按余弦相似度排序。通过 `similarity_threshold` 过滤低相关结果。
+- **写入**：`update()` 将输入文本编码为 float32 向量，存储为 Valkey Hash（`HSET`）。若配置了 `ttl_seconds`，同时调用 `EXPIRE` 设置过期时间。
+- **持久化**：由 Valkey 服务端管理。`load()` 和 `save()` 为空操作（no-op）。数据在进程重启后自动保留，多进程可并发读写同一索引。
+- **错误处理**：若 Valkey 未加载 Search 模块，初始化时抛出 `RuntimeError` 并给出安装提示。
+- **依赖**：需安装 `valkey-glide-sync` 包（`pip install 'chatdev[valkey]'`）。
+- **适用场景**：需要持久化、跨进程共享、自动过期的自托管部署；隐私敏感环境中 Mem0 云服务不可用时的替代方案。
+
 ## 6. EmbeddingConfig 提示
 - 字段：`provider`, `model`, `api_key`, `base_url`, `params`。
 - `provider=openai` 时使用 `openai.OpenAI` 客户端，可配置 `base_url` 以兼容兼容层。

entity/configs/node/memory.py

@@ -189,6 +189,155 @@ def from_dict(cls, data: Mapping[str, Any], *, path: str) -> "SimpleMemoryConfig
     }
 
 
+@dataclass
+class ValkeyMemoryConfig(BaseConfig):
+    """Configuration for Valkey-backed memory store."""
+
+    host: str = "localhost"
+    port: int = 6379
+    username: str | None = None
+    password: str | None = None
+    db: int = 0
+    use_tls: bool = False
+    index_name: str = "memory_index"
+    key_prefix: str = "memory:"
+    ttl_seconds: int | None = None
+    embedding: EmbeddingConfig | None = None
+
+    @classmethod
+    def from_dict(cls, data: Mapping[str, Any], *, path: str) -> "ValkeyMemoryConfig":
+        mapping = require_mapping(data, path)
+        host = optional_str(mapping, "host", path) or "localhost"
+
+        port_value = mapping.get("port", 6379)
+        if not isinstance(port_value, int) or port_value < 1 or port_value > 65535:
+            raise ConfigError("port must be a valid port number (1-65535)", extend_path(path, "port"))
+
+        username = optional_str(mapping, "username", path)
+        password = optional_str(mapping, "password", path)
+
+        db_value = mapping.get("db", 0)
+        if not isinstance(db_value, int) or db_value < 0 or db_value > 15:
+            raise ConfigError("db must be a valid database index (0-15)", extend_path(path, "db"))
+
+        use_tls = bool(mapping.get("use_tls", False))
+
+        index_name = optional_str(mapping, "index_name", path) or "memory_index"
+
+        key_prefix = optional_str(mapping, "key_prefix", path) or "memory:"
+
+        ttl_seconds: int | None = None
+        ttl_raw = mapping.get("ttl_seconds")
+        if ttl_raw is not None:
+            if not isinstance(ttl_raw, int) or ttl_raw <= 0:
+                raise ConfigError("ttl_seconds must be a positive integer", extend_path(path, "ttl_seconds"))
+            ttl_seconds = ttl_raw
+
+        embedding_cfg = None
+        if "embedding" in mapping and mapping["embedding"] is not None:
+            embedding_cfg = EmbeddingConfig.from_dict(mapping["embedding"], path=extend_path(path, "embedding"))
+
+        return cls(
+            host=host,
+            port=port_value,
+            username=username,
+            password=password,
+            db=db_value,
+            use_tls=use_tls,
+            index_name=index_name,
+            key_prefix=key_prefix,
+            ttl_seconds=ttl_seconds,
+            embedding=embedding_cfg,
+            path=path,
+        )
+
+    FIELD_SPECS = {
+        "host": ConfigFieldSpec(
+            name="host",
+            display_name="Host",
+            type_hint="str",
+            required=False,
+            default="localhost",
+            description="Valkey server hostname or IP address",
+        ),
+        "port": ConfigFieldSpec(
+            name="port",
+            display_name="Port",
+            type_hint="int",
+            required=False,
+            default=6379,
+            description="Valkey server port",
+        ),
+        "username": ConfigFieldSpec(
+            name="username",
+            display_name="Username",
+            type_hint="str",
+            required=False,
+            description="Valkey ACL username (required for ACL-based auth)",
+            advance=True,
+        ),
+        "password": ConfigFieldSpec(
+            name="password",
+            display_name="Password",
+            type_hint="str",
+            required=False,
+            description="Valkey server password",
+            default="${VALKEY_PASSWORD}",
+            advance=True,
+        ),
+        "db": ConfigFieldSpec(
+            name="db",
+            display_name="Database Index",
+            type_hint="int",
+            required=False,
+            default=0,
+            description="Valkey database index",
+            advance=True,
+        ),
+        "use_tls": ConfigFieldSpec(
+            name="use_tls",
+            display_name="Use TLS",
+            type_hint="bool",
+            required=False,
+            default=False,
+            description="Enable TLS encryption for the Valkey connection",
+            advance=True,
+        ),
+        "index_name": ConfigFieldSpec(
+            name="index_name",
+            display_name="Index Name",
+            type_hint="str",
+            required=False,
+            default="memory_index",
+            description="Name of the Valkey Search index for vector similarity queries",
+        ),
+        "key_prefix": ConfigFieldSpec(
+            name="key_prefix",
+            display_name="Key Prefix",
+            type_hint="str",
+            required=False,
+            default="memory:",
+            description="Prefix for all keys stored in Valkey",
+            advance=True,
+        ),
+        "ttl_seconds": ConfigFieldSpec(
+            name="ttl_seconds",
+            display_name="TTL (seconds)",
+            type_hint="int",
+            required=False,
+            description="Time-to-live for memory entries in seconds (no expiry if omitted)",
+        ),
+        "embedding": ConfigFieldSpec(
+            name="embedding",
+            display_name="Embedding Configuration",
+            type_hint="EmbeddingConfig",
+            required=False,
+            description="Optional embedding configuration for vector similarity search",
+            child=EmbeddingConfig,
+        ),
+    }
+
+
 @dataclass
 class FileMemoryConfig(BaseConfig):
     index_path: str | None = None

pyproject.toml

@@ -43,6 +43,9 @@ dependencies = [
     "mem0ai>=1.0.9",
 ]
 
+[project.optional-dependencies]
+valkey = ["valkey-glide-sync>=2.4"]
+
 [build-system]
 requires = ["hatchling"]
 build-backend = "hatchling.build"

runtime/node/agent/memory/builtin_stores.py

@@ -5,6 +5,7 @@
     FileMemoryConfig,
     Mem0MemoryConfig,
     SimpleMemoryConfig,
+    ValkeyMemoryConfig,
     MemoryStoreConfig,
 )
 from runtime.node.agent.memory.blackboard_memory import BlackboardMemory
@@ -48,6 +49,19 @@ def _create_mem0_memory(store):
 )
 
 
+def _create_valkey_memory(store):
+    from runtime.node.agent.memory.valkey_memory import ValkeyMemory
+    return ValkeyMemory(store)
+
+
+register_memory_store(
+    "valkey",
+    config_cls=ValkeyMemoryConfig,
+    factory=_create_valkey_memory,
+    summary="Valkey-backed memory store with vector similarity search",
+)
+
+
 class MemoryFactory:
     @staticmethod
     def create_memory(store: MemoryStoreConfig) -> MemoryBase: