openclaw怎么调用记忆的 - AI创想

OpenClaw memory is **plain Markdown in the agent workspace**. The files are the
source of truth; the model only "remembers" what gets written to disk.
Memory search tools are provided by the active memory plugin (default:
`memory-core`). Disable memory plugins with `plugins.slots.memory = "none"`.
## Memory files (Markdown)
The default workspace layout uses two memory layers:
- `memory/YYYY-MM-DD.md`
- Daily log (append-only).
- Read today + yesterday at session start.
- `MEMORY.md` (optional)
- Curated long-term memory.
- **Only load in the main, private session** (never in group contexts).

复制代码

These files live under the workspace (`agents.defaults.workspace`, default
`~/.openclaw/workspace`). See [Agent workspace](/concepts/agent-workspace) for the full layout.

复制代码

- Decisions, preferences, and durable facts go to `MEMORY.md`.
- Day-to-day notes and running context go to `memory/YYYY-MM-DD.md`.

复制代码

- If someone says "remember this," write it down (do not keep it in RAM).
- This area is still evolving. It helps to remind the model to store memories; it will know what to do.
- If you want something to stick, **ask the bot to write it** into memory.

复制代码

## Automatic memory flush (pre-compaction ping)
When a session is **close to auto-compaction**, OpenClaw triggers a **silent,
agentic turn** that reminds the model to write durable memory **before** the
context is compacted. The default prompts explicitly say the model _may reply_,
but usually `NO_REPLY` is the correct response so the user never sees this turn.

复制代码

This is controlled by `agents.defaults.compaction.memoryFlush`:
```json5
{
agents: {
defaults: {
compaction: {
reserveTokensFloor: 20000,
memoryFlush: {
enabled: true,
softThresholdTokens: 4000,
systemPrompt: "Session nearing compaction. Store durable memories now.",
prompt: "Write any lasting notes to memory/YYYY-MM-DD.md; reply with NO_REPLY if nothing to store.",
},
},
},
},
}

复制代码

**File:** docs/concepts/memory.md (L79-96)
```markdown
## Vector memory search
OpenClaw can build a small vector index over `MEMORY.md` and `memory/*.md` so
semantic queries can find related notes even when wording differs.
Defaults:
- Enabled by default.
- Watches memory files for changes (debounced).
- Configure memory search under `agents.defaults.memorySearch` (not top-level
`memorySearch`).
- Uses remote embeddings by default. If `memorySearch.provider` is not set, OpenClaw auto-selects:
1. `local` if a `memorySearch.local.modelPath` is configured and the file exists.
2. `openai` if an OpenAI key can be resolved.
3. `gemini` if a Gemini key can be resolved.
4. `voyage` if a Voyage key can be resolved.
5. Otherwise memory search stays disabled until configured.
- Local mode uses node-llama-cpp and may require `pnpm approve-builds`.

复制代码

### QMD backend (experimental)
Set `memory.backend = "qmd"` to swap the built-in SQLite indexer for
[QMD](https://github.com/tobi/qmd): a local-first search sidecar that combines
BM25 + vectors + reranking. Markdown stays the source of truth; OpenClaw shells
out to QMD for retrieval. Key points:
**Prereqs**
- Disabled by default. Opt in per-config (`memory.backend = "qmd"`).
- Install the QMD CLI separately (`bun install -g https://github.com/tobi/qmd` or grab
a release) and make sure the `qmd` binary is on the gateway’s `PATH`.
- QMD needs an SQLite build that allows extensions (`brew install sqlite` on
macOS).

复制代码

- `searchMode` (default `search`): pick which QMD command backs
`memory_search` (`search`, `vsearch`, `query`).
- `includeDefaultMemory` (default `true`): auto-index `MEMORY.md` + `memory/**/*.md`.
- `paths[]`: add extra directories/files (`path`, optional `pattern`, optional
stable `name`).
- `sessions`: opt into session JSONL indexing (`enabled`, `retentionDays`,
`exportDir`).
- `update`: controls refresh cadence and maintenance execution:
(`interval`, `debounceMs`, `onBoot`, `waitForBootSync`, `embedInterval`,
`commandTimeoutMs`, `updateTimeoutMs`, `embedTimeoutMs`).
- `limits`: clamp recall payload (`maxResults`, `maxSnippetChars`,
`maxInjectedChars`, `timeoutMs`).
- `scope`: same schema as [`session.sendPolicy`](/gateway/configuration#session).
Default is DM-only (`deny` all, `allow` direct chats); loosen it to surface QMD
hits in groups/channels.
- When `scope` denies a search, OpenClaw logs a warning with the derived
`channel`/`chatType` so empty results are easier to debug.

复制代码

Batch indexing (OpenAI + Gemini + Voyage):
- Disabled by default. Set `agents.defaults.memorySearch.remote.batch.enabled = true` to enable for large-corpus indexing (OpenAI, Gemini, and Voyage).
- Default behavior waits for batch completion; tune `remote.batch.wait`, `remote.batch.pollIntervalMs`, and `remote.batch.timeoutMinutes` if needed.
- Set `remote.batch.concurrency` to control how many batch jobs we submit in parallel (default: 2).
- Batch mode applies when `memorySearch.provider = "openai"` or `"gemini"` and uses the corresponding API key.
- Gemini batch jobs use the async embeddings batch endpoint and require Gemini Batch API availability.
Why OpenAI batch is fast + cheap:
- For large backfills, OpenAI is typically the fastest option we support because we can submit many embedding requests in a single batch job and let OpenAI process them asynchronously.
- OpenAI offers discounted pricing for Batch API workloads, so large indexing runs are usually cheaper than sending the same requests synchronously.
- See the OpenAI Batch API docs and pricing for details:
- [https://platform.openai.com/docs/api-reference/batch](https://platform.openai.com/docs/api-reference/batch)

复制代码

Tools:
- `memory_search` — returns snippets with file + line ranges.
- `memory_get` — read memory file content by path.

复制代码

- Set `agents.defaults.memorySearch.provider = "local"`.
- Provide `agents.defaults.memorySearch.local.modelPath` (GGUF or `hf:` URI).
- Optional: set `agents.defaults.memorySearch.fallback = "none"` to avoid remote fallback.
### How the memory tools work
- `memory_search` semantically searches Markdown chunks (~400 token target, 80-token overlap) from `MEMORY.md` + `memory/**/*.md`. It returns snippet text (capped ~700 chars), file path, line range, score, provider/model, and whether we fell back from local → remote embeddings. No full file payload is returned.

复制代码

### What gets indexed (and when)
- File type: Markdown only (`MEMORY.md`, `memory/**/*.md`).
- Index storage: per-agent SQLite at `~/.openclaw/memory/<agentId>.sqlite` (configurable via `agents.defaults.memorySearch.store.path`, supports `{agentId}` token).
- Freshness: watcher on `MEMORY.md` + `memory/` marks the index dirty (debounce 1.5s). Sync is scheduled on session start, on search, or on an interval and runs asynchronously. Session transcripts use delta thresholds to trigger background sync.
- Reindex triggers: the index stores the embedding **provider/model + endpoint fingerprint + chunking params**. If any of those change, OpenClaw automatically resets and reindexes the entire store.

复制代码

### Hybrid search (BM25 + vector)
When enabled, OpenClaw combines:
- **Vector similarity** (semantic match, wording can differ)
- **BM25 keyword relevance** (exact tokens like IDs, env vars, code symbols)
If full-text search is unavailable on your platform, OpenClaw falls back to vector-only search.
#### Why hybrid?
Vector search is great at “this means the same thing”:
- “Mac Studio gateway host” vs “the machine running the gateway”
- “debounce file updates” vs “avoid indexing on every write”
But it can be weak at exact, high-signal tokens:
- IDs (`a828e60`, `b3b9895a…`)
- code symbols (`memorySearch.query.hybrid`)
- error strings (“sqlite-vec unavailable”)
BM25 (full-text) is the opposite: strong at exact tokens, weaker at paraphrases.
Hybrid search is the pragmatic middle ground: **use both retrieval signals** so you get
good results for both “natural language” queries and “needle in a haystack” queries.

复制代码

```bash
openclaw memory status
openclaw memory status --deep
openclaw memory status --deep --index
openclaw memory status --deep --index --verbose
openclaw memory index
openclaw memory index --verbose
openclaw memory search "release checklist"

复制代码

- `--agent <id>`: scope to a single agent (default: all configured agents).
- `--verbose`: emit detailed logs during probes and indexing.

复制代码

### Memory keeps forgetting things How do I make it stick
Ask the bot to **write the fact to memory**. Long-term notes belong in `MEMORY.md`,
short-term context goes into `memory/YYYY-MM-DD.md`.
This is still an area we are improving. It helps to remind the model to store memories;
it will know what to do. If it keeps forgetting, verify the Gateway is using the same
workspace on every run.
Docs: [Memory](/concepts/memory), [Agent workspace](/concepts/agent-workspace).

复制代码

### Does memory persist forever What are the limits
Memory files live on disk and persist until you delete them. The limit is your
storage, not the model. The **session context** is still limited by the model
context window, so long conversations can compact or truncate. That is why
memory search exists - it pulls only the relevant parts back into context.
Docs: [Memory](/concepts/memory), [Context](/concepts/context).

复制代码

# 记忆
OpenClaw 记忆是**智能体工作空间中的纯 Markdown 文件**。这些文件是唯一的事实来源；模型只"记住"写入磁盘的内容。
记忆搜索工具由活动的记忆插件提供（默认：`memory-core`）。使用 `plugins.slots.memory = "none"` 禁用记忆插件。
## 记忆文件（Markdown）
默认工作空间布局使用两个记忆层：
- `memory/YYYY-MM-DD.md`
- 每日日志（仅追加）。
- 在会话开始时读取今天和昨天的内容。
- `MEMORY.md`（可选）
- 精心整理的长期记忆。
- **仅在主要的私人会话中加载**（绝不在群组上下文中加载）。
这些文件位于工作空间下（`agents.defaults.workspace`，默认 `~/.openclaw/workspace`）。完整布局参见[智能体工作空间](/concepts/agent-workspace)。

复制代码

# `openclaw memory`
管理语义记忆的索引和搜索。
由活跃的记忆插件提供（默认：`memory-core`；设置 `plugins.slots.memory = "none"` 可禁用）。
相关内容：
- 记忆概念：[记忆](/concepts/memory)
- 插件：[插件](/tools/plugin)
## 示例
```bash
openclaw memory status
openclaw memory status --deep
openclaw memory status --deep --index
openclaw memory status --deep --index --verbose
openclaw memory index
openclaw memory index --verbose
openclaw memory search "release checklist"
openclaw memory status --agent main
openclaw memory index --agent main --verbose

复制代码