docs: fix benchmark data, replace placeholder links, add EN pyramid image

This commit is contained in:
chrishuan
2026-05-13 00:02:53 +08:00
parent 076fbda195
commit 3cc6d2aa75
3 changed files with 12 additions and 44 deletions
+7 -23
View File
@@ -26,13 +26,13 @@ Help your Agent remember fixed workflows, accumulate past experience, and reuse
> - **Short-term context compression**: lighten the long-task context so the Agent no longer reasons while carrying every tool log on its back. > - **Short-term context compression**: lighten the long-task context so the Agent no longer reasons while carrying every tool log on its back.
> - **Long-term personalized memory**: distill fragmented conversations into structured memories, scene blocks, and user personas. > - **Long-term personalized memory**: distill fragmented conversations into structured memories, scene blocks, and user personas.
**Plugged into OpenClaw**, it saves up to **63.59% tokens**, lifts pass rate by **+41.18%** (relative), and pushes PersonaMem accuracy from **48%** to **76%**. **Plugged into OpenClaw**, it saves up to **61.38% tokens**, lifts pass rate by **+51.52%** (relative), and pushes PersonaMem accuracy from **48%** to **76%**.
| Memory Capability | Benchmark | Openclaw Success | With Plugin | Relative Δ | Openclaw Tokens | With Plugin Tokens | Relative Δ | | Memory Capability | Benchmark | Openclaw Success | With Plugin | Relative Δ | Openclaw Tokens | With Plugin Tokens | Relative Δ |
| :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | | :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: |
| **Short-term** | WideSearch | 8.5% | **12%** | **+41.18%** | 174.31M | **63.46M** | **63.59%** | | **Short-term** | WideSearch | 33% | **50%** | **+51.52%** | 221.31M | **85.64M** | **61.38%** |
| **Short-term** | SWE-bench | 58.4% | **64.2%** | **+9.93%** | 3474.1 | **2375.4** | **33.09%** | | **Short-term** | SWE-bench | 58.4% | **64.2%** | **+9.93%** | 3474.1M | **2375.4M** | **33.09%** |
| **Short-term** | AA-LCR | 44.0% | **47.5%** | **+7.95%** | 112.0M | **77.3M** | **31%** | | **Short-term** | AA-LCR | 44.0% | **47.5%** | **+7.95%** | 112.0M | **77.3M** | **30.98%** |
| **Long-term** | PersonaMem | 48% | **76%** | **+59%** | — | — | — | | **Long-term** | PersonaMem | 48% | **76%** | **+59%** | — | — | — |
> These are long-session evaluations, not single-turn isolated runs. Multiple tasks are concatenated into the same session and executed back-to-back. For example, each SWE-bench session runs 50 tasks consecutively to simulate the context-accumulation pressure faced by a real long-horizon Agent. > These are long-session evaluations, not single-turn isolated runs. Multiple tasks are concatenated into the same session and executed back-to-back. For example, each SWE-bench session runs 50 tasks consecutively to simulate the context-accumulation pressure faced by a real long-horizon Agent.
@@ -74,7 +74,7 @@ Cross-session memory is a different problem. Raw conversation logs are a low-den
TencentDB Agent Memory uses an L0 → L3 pyramid pipeline to refine information layer by layer: TencentDB Agent Memory uses an L0 → L3 pyramid pipeline to refine information layer by layer:
<p align="center"> <p align="center">
<img src="./assets/images/memory-pyramid.png" alt="TencentDB Agent Memory L0 to L3 semantic pyramid" width="860" /> <img src="./assets/images/memory-pyramid-en.jpg" alt="TencentDB Agent Memory L0 to L3 semantic pyramid" width="860" />
</p> </p>
The upper layers help the Agent "understand you"; the lower layers back it up with factual detail. The Agent gets both the high-level read and the receipts when needed. The upper layers help the Agent "understand you"; the lower layers back it up with factual detail. The Agent gets both the high-level read and the receipts when needed.
@@ -132,21 +132,6 @@ Once enabled, TencentDB Agent Memory automatically handles conversation capture,
} }
``` ```
### 5. Common commands
```bash
# Import historical conversations and run the full L0 → L3 pipeline
openclaw memory-tdai seed --input conversations.json
# Migrate SQLite data into TCVDB
migrate-sqlite-to-tcvdb --help
# Export data from Tencent Cloud Vector Database
export-tencent-vdb --help
```
See [`CONFIGURATION.md`](./CONFIGURATION.md) for full configuration. CLI input format is in [`src/cli/README.md`](./src/cli/README.md).
--- ---
## 🔧 Configurable Parameters ## 🔧 Configurable Parameters
@@ -289,7 +274,6 @@ The lower stack is the armory: stable, complete, retrievable. The upper stack is
| Document | Contents | | Document | Contents |
| :--- | :--- | | :--- | :--- |
| [`CONFIGURATION.md`](./CONFIGURATION.md) | Full configuration reference, field descriptions, and advanced parameters | | [`CONFIGURATION.md`](./CONFIGURATION.md) | Full configuration reference, field descriptions, and advanced parameters |
| [`src/cli/README.md`](./src/cli/README.md) | `openclaw memory-tdai seed` historical conversation import |
| [`scripts/README.memory-tencentdb-ctl.md`](./scripts/README.memory-tencentdb-ctl.md) | Operations & management tooling | | [`scripts/README.memory-tencentdb-ctl.md`](./scripts/README.memory-tencentdb-ctl.md) | Operations & management tooling |
| [`CHANGELOG.md`](./CHANGELOG.md) | Release notes and version history | | [`CHANGELOG.md`](./CHANGELOG.md) | Release notes and version history |
| [`openclaw.plugin.json`](./openclaw.plugin.json) | OpenClaw plugin manifest and configuration schema | | [`openclaw.plugin.json`](./openclaw.plugin.json) | OpenClaw plugin manifest and configuration schema |
@@ -300,8 +284,8 @@ The lower stack is the armory: stable, complete, retrievable. The upper stack is
We welcome every kind of contribution — bug reports, feature ideas, doc fixes, benchmark reproductions, ecosystem integrations, or a Pull Request. Agent memory is far from a solved problem, and we'd love to figure it out together. We welcome every kind of contribution — bug reports, feature ideas, doc fixes, benchmark reproductions, ecosystem integrations, or a Pull Request. Agent memory is far from a solved problem, and we'd love to figure it out together.
- 🐞 **Found a bug or have a question?** Open an issue at [GitHub Issues](https://github.com/<org>/<repo>/issues) — we respond within 24 hours. - 🐞 **Found a bug or have a question?** Open an issue at [GitHub Issues](https://github.com/Tencent/TencentDB-Agent-Memory/issues) — we respond within 24 hours.
- 💡 **Have an idea to share?** Start a thread in [GitHub Discussions](https://github.com/<org>/<repo>/discussions). - 💡 **Have an idea to share?** Start a thread in [GitHub Discussions](https://github.com/Tencent/TencentDB-Agent-Memory/discussions).
- 🛠️ **Want to contribute code?** Please read [CONTRIBUTING.md](./CONTRIBUTING.md) first. - 🛠️ **Want to contribute code?** Please read [CONTRIBUTING.md](./CONTRIBUTING.md) first.
- 💬 **Want to chat with us?** Join our [Discord community](https://discord.gg/kDtHb5RW2) and talk to the early developers directly. - 💬 **Want to chat with us?** Join our [Discord community](https://discord.gg/kDtHb5RW2) and talk to the early developers directly.
+5 -21
View File
@@ -1,6 +1,6 @@
<div align="center"> <div align="center">
<img src="./assets/images/logo.png" alt="TencentDB Agent Memory" width="880" /> <img src="./assets/images/logo2.png" alt="TencentDB Agent Memory" width="880" />
### 让 Agent 沉淀经验,让人专注创造。 ### 让 Agent 沉淀经验,让人专注创造。
@@ -133,7 +133,7 @@ openclaw gateway restart
启用后,TencentDB Agent Memory 会自动完成对话录制、记忆提取、场景归纳、用户画像生成和下一轮对话前召回。 启用后,TencentDB Agent Memory 会自动完成对话录制、记忆提取、场景归纳、用户画像生成和下一轮对话前召回。
### 3. 使用 TCVDB 后端(可选) ### 3. 使用 TCVDB 后端(可选,需版本号 ≥ 0.2.0
```jsonc ```jsonc
{ {
@@ -148,7 +148,7 @@ openclaw gateway restart
} }
``` ```
### 4. 启用短期记忆压缩(可选) ### 4. 启用短期记忆压缩(可选,需版本号 ≥ 0.3.0
```jsonc ```jsonc
{ {
@@ -160,21 +160,6 @@ openclaw gateway restart
} }
``` ```
### 5. 常用命令
```bash
# 导入历史对话,完整执行 L0 → L3 管线
openclaw memory-tdai seed --input conversations.json
# SQLite 数据迁移到 TCVDB
migrate-sqlite-to-tcvdb --help
# 导出腾讯云向量数据库数据
export-tencent-vdb --help
```
完整配置见 [`CONFIGURATION.md`](./CONFIGURATION.md)CLI 输入格式见 [`src/cli/README.md`](./src/cli/README.md)。
--- ---
## 🔧 可调参数 ## 🔧 可调参数
@@ -274,7 +259,6 @@ export-tencent-vdb --help
| 文档 | 内容 | | 文档 | 内容 |
| :--- | :--- | | :--- | :--- |
| [`CONFIGURATION.md`](./CONFIGURATION.md) | 完整配置参考、字段说明与高级参数 | | [`CONFIGURATION.md`](./CONFIGURATION.md) | 完整配置参考、字段说明与高级参数 |
| [`src/cli/README.md`](./src/cli/README.md) | `openclaw memory-tdai seed` 历史对话导入说明 |
| [`scripts/README.memory-tencentdb-ctl.md`](./scripts/README.memory-tencentdb-ctl.md) | 运维管理工具说明 | | [`scripts/README.memory-tencentdb-ctl.md`](./scripts/README.memory-tencentdb-ctl.md) | 运维管理工具说明 |
| [`CHANGELOG.md`](./CHANGELOG.md) | 版本变更记录 | | [`CHANGELOG.md`](./CHANGELOG.md) | 版本变更记录 |
| [`openclaw.plugin.json`](./openclaw.plugin.json) | OpenClaw 插件声明与配置 Schema | | [`openclaw.plugin.json`](./openclaw.plugin.json) | OpenClaw 插件声明与配置 Schema |
@@ -284,8 +268,8 @@ export-tencent-vdb --help
我们欢迎一切形式的贡献——Bug 反馈、功能建议、文档勘误、Benchmark 复现、生态集成,或者一个 Pull Request 都可以。Agent 记忆这件事远未有定论,希望和大家一起把它做出来。 我们欢迎一切形式的贡献——Bug 反馈、功能建议、文档勘误、Benchmark 复现、生态集成,或者一个 Pull Request 都可以。Agent 记忆这件事远未有定论,希望和大家一起把它做出来。
- 🐞 **发现 Bug 或有疑问?** 欢迎到 [GitHub Issues](https://github.com/<org>/<repo>/issues) 提交,我们会在 24 小时内响应。 - 🐞 **发现 Bug 或有疑问?** 欢迎到 [GitHub Issues](https://github.com/Tencent/TencentDB-Agent-Memory/issues) 提交,我们会在 24 小时内响应。
- 💡 **有想法想交流?** 欢迎在 [GitHub Discussions](https://github.com/<org>/<repo>/discussions) 发起讨论。 - 💡 **有想法想交流?** 欢迎在 [GitHub Discussions](https://github.com/Tencent/TencentDB-Agent-Memory/discussions) 发起讨论。
- 🛠️ **想贡献代码?** 请先阅读 [CONTRIBUTING.md](./CONTRIBUTING.md)。 - 🛠️ **想贡献代码?** 请先阅读 [CONTRIBUTING.md](./CONTRIBUTING.md)。
- 💬 **想加入交流群?** 扫码加入 **Agent Memory 微信社群**,与早期开发者直接对话。 - 💬 **想加入交流群?** 扫码加入 **Agent Memory 微信社群**,与早期开发者直接对话。
<img width="200" height="146" alt="766450d8a7b30aa7e67121b4981f1810" src="https://github.com/user-attachments/assets/7cbbb57a-ec81-4f92-b0bd-7f3c5d760c1e" /> <img width="200" height="146" alt="766450d8a7b30aa7e67121b4981f1810" src="https://github.com/user-attachments/assets/7cbbb57a-ec81-4f92-b0bd-7f3c5d760c1e" />
Binary file not shown.

After

Width:  |  Height:  |  Size: 664 KiB