diff --git a/README.md b/README.md index e7e23f8..dd2616b 100644 --- a/README.md +++ b/README.md @@ -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. > - **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 | | :--- | :--- | :---: | :---: | :---: | :---: | :---: | :---: | -| **Short-term** | WideSearch | 8.5% | **12%** | **+41.18%** | 174.31M | **63.46M** | **−63.59%** | -| **Short-term** | SWE-bench | 58.4% | **64.2%** | **+9.93%** | 3474.1 | **2375.4** | **−33.09%** | -| **Short-term** | AA-LCR | 44.0% | **47.5%** | **+7.95%** | 112.0M | **77.3M** | **−31%** | +| **Short-term** | WideSearch | 33% | **50%** | **+51.52%** | 221.31M | **85.64M** | **−61.38%** | +| **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** | **−30.98%** | | **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. @@ -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 L0 to L3 semantic pyramid + TencentDB Agent Memory L0 to L3 semantic pyramid

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 @@ -289,7 +274,6 @@ The lower stack is the armory: stable, complete, retrievable. The upper stack is | Document | Contents | | :--- | :--- | | [`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 | | [`CHANGELOG.md`](./CHANGELOG.md) | Release notes and version history | | [`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. -- 🐞 **Found a bug or have a question?** Open an issue at [GitHub Issues](https://github.com///issues) — we respond within 24 hours. -- 💡 **Have an idea to share?** Start a thread in [GitHub Discussions](https://github.com///discussions). +- 🐞 **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/Tencent/TencentDB-Agent-Memory/discussions). - 🛠️ **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. diff --git a/README_CN.md b/README_CN.md index 7d13961..917c80c 100644 --- a/README_CN.md +++ b/README_CN.md @@ -1,6 +1,6 @@
-TencentDB Agent Memory +TencentDB Agent Memory ### 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。 -### 3. 使用 TCVDB 后端（可选） +### 3. 使用 TCVDB 后端（可选，需版本号 ≥ 0.2.0） ```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 { @@ -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 @@ -274,7 +259,6 @@ export-tencent-vdb --help | 文档 | 内容 | | :--- | :--- | | [`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 | | [`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 | @@ -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。 -- 🐞 **发现 Bug 或有疑问？** 欢迎到 [GitHub Issues](https://github.com///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///discussions) 发起讨论。 +- 🐞 **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/Tencent/TencentDB-Agent-Memory/discussions) 发起讨论。 - 🛠️ **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。 766450d8a7b30aa7e67121b4981f1810 diff --git a/assets/images/memory-pyramid-en.jpg b/assets/images/memory-pyramid-en.jpg new file mode 100644 index 0000000..ffaf274 Binary files /dev/null and b/assets/images/memory-pyramid-en.jpg differ