Agent memory is getting incredibly competitive! I have to say, the more people join this track, the better it gets! The Tencent AI team spent a full 6 months obsessing over one problem: AI agents constantly losing context in long conversations. They ended up building a memory system and open-sourcing it. After reading their breakdown, my biggest takeaway is that 99% of people are still fixated on context length, but what really gets agents back on track are these three hardcore moves.

First, real-time compression of stale context. This cuts token consumption by 61%. Before, agents would blow through the context window easily; now they slim down mid-conversation and stay sharp.

Second, drawing a structured task map for the agent using Mermaid syntax. In complex workflows with over 30 steps, the probability of derailing drops significantly. The agent is no longer like a headless chicken—it knows exactly where it is and where to go next.

Third, building dedicated Persona memory for the agent. Personality consistency jumps from 48% to 76%. It no longer swings between professional and casual; its response style and role settings are rock solid.

This isn’t just theory—it’s the result of 6 months of real-world trial and error. The repo is out there; if you’re building agents, try it out. I used to think agent memory was hard because we oversimplified the problem. The real challenge is no longer storing more information, but ensuring the agent recalls the right thing at the right time in the right way. Are you still relying on piling up tokens to solve agent memory?
Project link: https://github.com/Tencent/TencentDB-Agent-Memory…

Tencent/TencentDB-Agent-Memory

Source: https://github.com/Tencent/TencentDB-Agent-Memory

Agents remember, Humans innovate.

npm (https://www.npmjs.com/package/@tencentdb-agent-memory/memory-tencentdb) License: MIT Node (https://nodejs.org/) OpenClaw (https://github.com/openclaw/openclaw) Hermes (https://hermes-agent.nousresearch.com/docs/) Discord (https://discord.gg/kDtHb5RW2)
Highlights · Overview · Core Technology · Features · Quick Start
English · Simplified Chinese

✨ Highlights

TencentDB Agent Memory = symbolic short-term memory + layered long-term memory.

• 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.

Overview

Memory is not about hoarding everything in the AI — it is about sparing humans from having to repeat themselves. 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.

Let the Agent remember what should be remembered, so people can focus on judgment, creation, and work that truly matters.

Core Technology: Reject Flat Storage, Embrace Layering and Symbolization

Our architecture rests on two pillars: memory layering and symbolic memory. Together they ensure Agents not merely “remember more”, but “reason better”.

1. Memory Layering: Progressive Disclosure with Heterogeneous Storage

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)”.

2. Symbolic Memory: Maximum Semantics in Minimum Symbols (Mermaid Canvas)

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.

graph LR
    Log["Verbose Logs(hundreds of thousands of tokens)"] -->|"1. Offload full text"| FS[("External FS(refs/*.md)")]
    Log -->|"2. Extract relations"| MMD["Mermaid Canvas(with node_id)"]
    MMD -->|"3. Light injection"| Agent(("Agent Context(a few hundred tokens)"))
    Agent -. "4. Recall via node_id" .-> FS
    style Log fill:#f1f5f9,stroke:#94a3b8,stroke-dasharray: 5 5,color:#475569
    style FS fill:#f8fafc,stroke:#cbd5e1,stroke-width:2px,color:#334155
    style MMD fill:#eff6ff,stroke:#3b82f6,stroke-width:2px,color:#1e3a8a
    style Agent fill:#fffbeb,stroke:#f59e0b,stroke-width:2px,color:#92400e

Quick Start

🎬 Demos

OpenClaw × Agent Memory
Hermes × Agent Memory

1. OpenClaw

1.1 Install the plugin

openclaw plugins install @tencentdb-agent-memory/memory-tencentdb
openclaw gateway restart

1.2 Zero-config to enable

Defaults to a local SQLite + sqlite-vec backend.

// ~/.openclaw/openclaw.json
{
  "memory-tencentdb": {
    "enabled": true
  }
}

Once enabled, TencentDB Agent Memory automatically handles conversation capture, memory extraction, scene aggregation, persona generation, and recall before the next turn.

1.3 Enable short-term compression (optional, requires version ≥ 0.3.4)

{
  "memory-tencentdb": {
    "config": {
      "offload": {
        "enabled": true
      }
    }
  }
}

Step 1 — Register the slot in your plugin config

Add the slots field so OpenClaw routes context-offload requests to this plugin:

{
  "plugins": {
    "slots": {
      "contextEngine": "openclaw-context-offload"
    }
  }
}

Step 2 — Apply the runtime patch

For the best results, run the patch script below. It hooks after-tool-call messages so they can be offloaded and recovered correctly:

bash scripts/openclaw-after-tool-call-messages.patch.sh

💡 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 Hermes (https://github.com/NousResearch/hermes-agent) Agent. You can launch a memory-enabled Hermes with a single command:

# ============ Configuration Parameters ============
# MODEL_API_KEY LLM API key (required) — replace with your own credential
# MODEL_BASE_URL LLM endpoint, defaults to Tencent Cloud LKE (Large Model Knowledge Engine)
# MODEL_NAME Model name, defaults to DeepSeek-V3.2
# MODEL_PROVIDER Provider type: "custom" works for any OpenAI-compatible endpoint
MODEL_API_KEY="your-api-key"
MODEL_BASE_URL="https://api.lkeap.cloud.tencent.com/v1"
MODEL_NAME="deepseek-v3.2"
MODEL_PROVIDER="custom"

# ============ docker run Flags ============
# -d Run container in detached (background) mode
# --name hermes-memory Container name, for later docker exec / logs / stop
# --restart unless-stopped Auto-restart on crash or host reboot
# -p 8420:8420 Host port ↔ container port (Hermes Gateway)
# -e MODEL_* Inject the config parameters above as env vars
# -v hermes_data:/opt/data Persist memory data to a named volume (survives restart)

# Build
docker build -f Dockerfile.hermes -t hermes-memory .

# Run
docker run -d \
  --name hermes-memory \
  --restart unless-stopped \
  -p 8420:8420 \
  -e MODEL_API_KEY="your-api-key" \
  -e MODEL_BASE_URL="https://api.lkeap.cloud.tencent.com/v1" \
  -e MODEL_NAME="deepseek-v3.2" \
  -e MODEL_PROVIDER="custom" \
  -v hermes_data:/opt/data \
  hermes-memory

# Verify the Gateway
curl http://localhost:8420/health

# Enter the Hermes interactive shell
docker exec -it hermes-memory hermes

The image ships with Tencent Cloud DeepSeek-V3.2 as the default. If you use this model, omit MODEL_BASE_URL / MODEL_NAME / MODEL_PROVIDER and pass only MODEL_API_KEY.

🔧 Configurable Parameters

Every field has a sensible default — it runs with zero configuration. When you want to tune, peel back the layers based on how deep you go.

🟢 Level 1 · Daily tuning (covers 90% of use cases)

🟡 Level 2 · Advanced tuning (long task / long session)

🔴 Level 3 · Full parameter reference (ops / custom models / remote embedding)
For all fields, types, and constraints see openclaw.plugin.json。

• embedding.* — remote embedding service (OpenAI-compatible API)
• llm.* — standalone LLM mode (bypass OpenClaw’s built-in model and run L1/L2/L3 with a designated API)
• offload.backendUrl / backendApiKey — offload the L1/L1.5/L2/L4 flow to a backend service
• report.* — metrics reporting

🤔 Features

1. Macro Personas + Micro Facts: A Unified Drill-Down Mechanism

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.

2. White-Box Debuggability: Memory Is Not a Black Box

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:

• L2 Scenario blocks are plain Markdown — open them and inspect.
• L3 Persona lives in persona.md and traces back to the Scenarios that produced it.
• Short-term task canvases are Mermaid — readable by both humans and Agents.
• Raw payloads, summaries, and nodes are linked by result_ref and node_id.

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.

3. Production-Ready Engineering: Not a Demo

Documentation