> - **Symbolic short-term memory** offloads heavy tool logs and condenses them into compact Mermaid symbols, cutting token usage and improving task success.
> - **Layered long-term memory** distills fragmented conversations into structured personas and scenes, instead of flat vector piles.
When integrated with OpenClaw, it cuts token usage by up to **61.38%**, improves pass rate by **51.52%** (relative), and raises PersonaMem accuracy from **48%** to **76%**.
> These results are measured over continuous long-horizon sessions, not isolated turns. For example, SWE-bench runs 50 consecutive tasks per session to simulate the context-accumulation pressure of real-world long-horizon agents.
In practice, we constantly re-explain the same SOPs, project background, tool conventions, and output formats to the Agent. Such information should not require repetition, nor should it be indiscriminately dumped into the context.
TencentDB Agent Memory helps the Agent learn your workflows, retain task context, and reuse past experience. We reject both brute-force history accumulation and irreversible lossy summarization. Instead, we design memory as a layered system: **symbolic memory** for in-task information overload, and **memory layering** for cross-session experience.
Our architecture rests on two pillars: **memory layering** and **symbolic memory**. Together they ensure Agents do not merely "remember more", but "reason better".
Traditional memory systems shred data into fragments and dump them into a flat vector store. Recall degenerates into a blind search across disconnected fragments, with no macro-level guidance.
Whether it is long-term knowledge, short-term tasks, or future skill capabilities, memory should never be flat — both its formation and its recall must be hierarchical. TencentDB Agent Memory adopts **layering** as its unified architectural paradigm:
***Short-term context layering.** The bottom layer archives raw tool outputs (`refs/*.md`); the middle layer extracts step-level summaries (`jsonl`); the top layer condenses state into a lightweight Mermaid canvas. The Agent only needs to attend to the top-layer structure in context, and drills down to the lower layers via `node_id` when an error occurs.
***Long-term personalization layering.** In place of flat logs, we build a semantic pyramid: **L0 Conversation** (raw dialogue) → **L1 Atom** (atomic facts) → **L2 Scenario** (scene blocks) → **L3 Persona** (user profile). The Persona layer carries day-to-day preferences; the system drills down to Atoms only when details matter.
***Skill generation layering.** Layering also applies to actions. The middle layer derives common solution patterns (**Scenario**) from bottom-layer execution traces (**Conversation**), and the top layer distills reusable Skills or standard SOPs (**Persona**).
**Heterogeneous storage and progressive disclosure.** A dual-layer storage strategy underpins this architecture. The bottom layer (facts, logs, traces) is persisted in databases for robust full-text retrieval; the top layer (personas, scenes, canvases) is stored as human-readable Markdown files for high information density and white-box inspection. **Lower layers preserve evidence; upper layers preserve structure.**
**Full traceability and lossless recovery.** Compression often sacrifices traceability. TencentDB Agent Memory avoids irreversible compression by maintaining a deterministic path from high-level abstractions back to ground-truth evidence. Whether it is an offloaded error log or a distilled user preference, the system guarantees a complete drill-down path: "top-layer symbol (Persona / canvas) → mid-layer index (Scenario / jsonl) → bottom-layer raw text (L0 Conversation / refs)".
In long tasks, the largest token consumers are verbose intermediate logs (search results, code, error traces). To address this, we combine **context offloading** with **symbolic memory**:
***Mermaid symbol graph.** Instead of verbose prose or flat JSON, we encode task state transitions in high-density Mermaid syntax — precise enough for LLMs to parse, concise enough for humans to read.
***History offloading.** Full tool logs are offloaded to external files; only a lightweight Mermaid task map remains in context.
***`node_id` tracing.** The Agent reasons over the symbol graph; to verify a detail, it greps for the `node_id` and instantly retrieves the full raw text — cutting token cost while preserving full traceability.
Once enabled, TencentDB Agent Memory automatically handles conversation capture, memory extraction, scene aggregation, persona generation, and recall before the next turn.
> 💡 The patch only needs to be applied once per OpenClaw installation. After upgrading OpenClaw, re-run the script to re-apply.
### 2. Hermes (Docker, requires version ≥ 0.3.4)
In addition to OpenClaw, this plugin also supports the [Hermes](https://github.com/NousResearch/hermes-agent) Agent. Start a memory-enabled Hermes with a single command:
```bash
docker run -d \ # Run container in detached (background) mode
--name hermes-memory \ # Container name for easy docker exec / logs / stop
--restart unless-stopped \ # Auto-restart on crash or host reboot, unless manually stopped
-p 8420:8420 \ # Map host port 8420 -> container port 8420 (Hermes Gateway)
-e MODEL_API_KEY="your-api-key"\ # LLM API key (required) — replace with your own credential
-e MODEL_BASE_URL="https://api.lkeap.cloud.tencent.com/v1"\ # LLM endpoint, defaults to Tencent Cloud LKE Auto Platform
-e MODEL_NAME="deepseek-v3.2"\ # Model identifier, defaults to DeepSeek-V3.2
-e MODEL_PROVIDER="custom"\ # Provider type: "custom" for OpenAI-compatible endpoints
-v hermes_data:/opt/data \ # Persist memory data to a named volume (survives container restarts)
agentmemory/hermes-memory:latest # Official image, supports linux/amd64 and linux/arm64
The image supports `linux/amd64` and `linux/arm64`. It ships with Tencent Cloud DeepSeek-V3.2 defaults — to use a different model, pass `MODEL_BASE_URL`, `MODEL_NAME`, and `MODEL_PROVIDER` accordingly.
The biggest risk in compression is saving tokens at the cost of losing the evidence. TencentDB Agent Memory therefore does not collapse history into an irreversible summary — it preserves a clear path from high-level abstraction back to ground-truth evidence.
The upper layers carry judgment and direction; the lower layers carry evidence and precision. Short-term compression and long-term memory form a single closed loop: **collapsible and expandable, abstract yet auditable.**
Most memory systems fall short here: when recall is wrong, all you see is a list of vector scores, with no way to tell where things went wrong. TencentDB Agent Memory keeps the key intermediates as readable files:
Debugging no longer means probing an opaque database — it becomes a deterministic walk along the chain "Persona → Scenario → Atom → Conversation" until the root cause surfaces.
**All of these layered memory artifacts live under `~/.openclaw/memory-tdai/` — feel free to open the directory and inspect each layer for yourself.**
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/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).
