TencentDB Agent Memory
Source: https://github.com/TencentCloud/TencentDB-Agent-Memory
Author: TencentCloud
Fetched: 2026-08-07 via opencli web read
Evidence: Obsidian evidence: DeepResearch/2026-08-07-morning-AgentPlugins-TeamMemory-SkillEntropy-研究材料/references/04-tencentdb-agent-memory-github.md
中文摘要
TencentDB Agent Memory 把 agent 记忆从单次对话扩展成团队级可复用资产：Chat Memory、Skill、LLM-Wiki、Code-Graph。README 强调通过自动资产抽取、跨框架共享、冷启动导入和 Memory Hub 管理，让新 agent 能继承已有项目上下文、文档、代码结构与工作流经验，减少重复解释和重复探索。它的工程重点在治理、路由和资产生命周期，而不只是“记住聊天”。
English Summary
TencentDB Agent Memory presents a team-level memory hub for AI agents. It turns conversations, documents, code, and workflows into reusable assets such as Chat Memory, Skills, LLM-Wiki, and CodeGraph, then manages and routes those assets across agents and frameworks so new sessions can inherit project context instead of rediscovering it.
原文 / Source Extract
TencentCloud/TencentDB-Agent-Memory: TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed, shared, and equipped across agents and frameworks.
原文链接: https://github.com/TencentCloud/TencentDB-Agent-Memory
https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/feat/server_team/assets/images/logo.png
Agents remember. Humans innovate.
#agents-remember-humans-innovate
https://www.npmjs.com/package/@tencentdb-agent-memory/memory-tencentdb https://github.com/TencentCloud/TencentDB-Agent-Memory/blob/feat/server_team/LICENSE https://nodejs.org/ https://github.com/openclaw/openclaw https://hermes-agent.nousresearch.com/docs/ https://discord.gg/dJQM6mKMF
Installation · What is it? · Team Play · Technical Implementation · Benchmark
- * *
Latest: Team Memory Beta is evolving quickly — install it and start exploring in minutes.
Installation
#installation
Start all three services in one go (memory-core + memory-hub + proxy):
git clone https://github.com/Tencent/TencentDB-Agent-Memory.git
cd TencentDB-Agent-Memory/deploy/global-images
cp .env.example .env
$EDITOR .env # Fill in two sets of LLM parameters (memory group + proxy group)
./start-all.sh # Launch everything with one command; when finished, it prints a one-liner you can paste directly into ClaudeOpen the panel: http://localhost:8125.
Complete installation documentation (standalone Memory Hub deployment, Proxy + Claude Code / CodeBuddy usage, stop and cleanup, port reference, etc.) is available in **INSTALL.md** (中文: INSTALL\_CN.md).
Migrating data from an older version
#migrating-data-from-an-older-version
If you're already on an older release (v1.x / v0.x) and want to bring your existing data over to v2.0.0+, we provide a migration tool:
See **Data Migration Tool (v2 → v3)** for full usage and flags. New installations can skip this.
What is TencentDB Agent Memory?
#what-is-tencentdb-agent-memory
We started from a practical question: How do you reduce repetitive work when using Agents?
If project context has already been explained, it shouldn't need to be repeated in a new session. If documents have already been read, every Agent shouldn't have to start again from page one. A workflow that already works shouldn't have to be rediscovered next time.
Memory here means more than just "remembering conversations." Any information that helps the next Agent avoid reinventing the wheel should be saved, organized, and reused.
Existing information → Reusable memory assets → Fewer turns → Less rework → More stable results and higher efficiencyLet experience accumulate, flow, and pass on to the next Agent
#let-experience-accumulate-flow-and-pass-on-to-the-next-agent
Memory Hub for Agent teams closes the loop across the entire experience lifecycle: work produces assets, assets circulate through the team, and new members can load the team's save file on day one.
1. Automatic asset extraction: Extract Chat Memory and Skills from conversations and tasks; convert documents and code into Wiki and CodeGraph; then manage, review, and route them consistently. 2. Portable & multi-Agent compatible: Memory assets are decoupled from Agent frameworks — they can move across frameworks and be shared and maintained by multiple Agents and team members. 3. Cold-start friendly: Import existing documents, codebases, and Agent conversation sessions. New Agent teams can start from existing experience instead of learning from scratch.
🧠 A brain that remembers people and context
#-a-brain-that-remembers-people-and-context
- Chat Memory retains preferences, facts, decisions, and interaction history.
- Each Agent automatically gets its own memory when created — no need to re-introduce yourself next time.
- L0 Conversation → L1 Atom → L2 Scenario → L3 Persona — raw conversations are distilled layer by layer.
"Don't refactor the old auth module — mobile is still using it." — Context this costly shouldn't depend on humans repeating it every time.
⚡ A Skill library that accumulates expertise
#-a-skill-library-that-accumulates-expertise
- After completing complex work, Agents can extract and manage reusable Skills from conversations and tool calls, and import them into the context of a designated Agent when needed.
- A Skill isn't just a prompt snippet; it has versions, resource files, trigger boundaries, execution steps, and validation rules.
- Personal Skills are private by default; after review, they can be shared with the team and assigned to other Agents.
Troubleshooting, code review, release checklists — learn it once, and the whole team can use it.
📖 A knowledge map that reads both docs and code
#-a-knowledge-map-that-reads-both-docs-and-code
- Wiki turns product docs, design specs, and ops runbooks into structured pages with a link graph. (Inspired by Karpathy's LLM knowledge base.)
- CodeGraph indexes code symbols, files, call relationships, and impact paths.
- Agents can search, read, inspect callers/callees, and perform impact analysis before modifying code.
Wiki keeps Agents from reading every file list before getting to work. CodeGraph doesn't just tell them "the code is here" — it tells them "changing this might affect those."
🛡️ A team memory panel controlled by humans
#️-a-team-memory-panel-controlled-by-humans
- Create teams and Agents in Memory Hub; review, share, and equip memory assets.
- Manage ownership, versions, status, visibility, usage counts, and Agent bindings in one place.
privatebelongs strictly to the Owner;teamis visible to all team members;restrictedgrants precise access via User / Role / Agent ACLs.- Two role layers: global System Admin manages users and teams (creating teams, adding members) and can also use Wiki, CodeGraph, Skill, and other asset management features; Team-level roles include Admin (team manager) and Member (regular member), responsible for asset collaboration and access control within a team. Asset ownership is tracked via Owner — the Owner automatically has management permissions for their assets.
Cold Start: Load the Save File, Then Get to Work
#cold-start-load-the-save-file-then-get-to-work
Most Agents' first task is re-learning your project. TencentDB Agent Memory turns the learning cost you've already paid into a save file:
Specifically, these existing assets can be imported directly and processed automatically in the panel:
- Codebases: Import existing repositories — CodeGraph automatically indexes symbols, files, call relationships, and impact paths.
- Documents & files: Import relevant docs and files — Wiki automatically generates structured pages with a link graph.
- Conversation sessions: Import past Agent conversation sessions — Skills and Chat Memory are automatically extracted as reusable assets.
Stop retraining every Agent. Give it the save file.
One Play Style: Build a Growing Agent Team for a One-Person Company
#one-play-style-build-a-growing-agent-team-for-a-one-person-company
Open Memory Hub and create a team:
Tiny but Serious Inc.
├── 👤 You · Set goals / Make decisions
├── 🔭 Scout · Research / Find opportunities
├── 🛠 Builder · Write code / Build products
├── 🧪 Reviewer · Test / Find issues
└── 🧠 Agent Memory · Preserve the team's experienceYou're not opening four disconnected chat windows — you're assembling a squad with different roles that can inherit the team's accumulated experience.
Recruit first, then equip
#recruit-first-then-equip
🔭 Scout
├── User interview Chat Memory
├── Market research Wiki
└── Competitive analysis Skill
🛠 Builder
├── Product Wiki
├── Project CodeGraph
└── Feature Delivery Skill
🧪 Reviewer
├── Historical incident Chat Memory
├── Project CodeGraph
└── Release Checklist SkillDifferent roles, different loadouts. Less noise — give each Agent the memory assets it actually needs to get work done.
The company can be tiny. Experience can compound forever.
Memory Assets, Not a Chat Log Warehouse
#memory-assets-not-a-chat-log-warehouse
RAG answers "what can be found?" Team Memory also answers "who can use it, which version is valid, and which Agent should receive it."
| | Chat History | Standard RAG | TencentDB Agent Memory | | :-- | :-: | :-: | :-: | | Cross-session user understanding | △ | △ | ✅ Chat Memory | | Distilled executable experience | — | — | ✅ Skill | | Document structure & relationships | — | △ Chunk retrieval | ✅ Wiki + Link Graph | | Code call graphs & impact scope | — | △ Text match | ✅ CodeGraph | | Ownership / Version / Status | — | — | ✅ | | Team sharing & Agent loadout | — | — | ✅ | | Private / Team / ACL | — | △ | ✅ |
Memory Hub Is Not a Display Board — It's a Control Panel
#memory-hub-is-not-a-display-board--its-a-control-panel
| Play Style | What you do in the Hub | | :-- | :-- | | Team Up | Create teams, add people and Agents, define sharing boundaries | | Asset Library | Browse, search, review, and manage Chat Memory, Skills, Wiki, and CodeGraph | | Agent Loadout | Bind different memory assets to different Agents; adjust priority and usage mode | | Knowledge Workshop | Build Wiki and CodeGraph; monitor processing status and asset metadata | | Access Control | Switch between private, team, and ACL-based access; revoke sharing when needed |
When you open an asset, what matters is not just "what it says," but also "where it came from, which version it is, who it's assigned to, and whether it's been used recently."
Every Loop Gains Experience
#every-loop-gains-experience
Memory doesn't run the Agent loop; it ensures the next iteration inherits the previous one's results: valuable interactions stay in Chat Memory, proven workflows are distilled into Skills, and document/code changes are updated through Wiki ingest and CodeGraph sync.
Without Memory, loops may just repeat faster. With inherited memory, each iteration has the chance to be better than the last.
One Agent Team: Shared Experience, Not Shared Privacy
#one-agent-team-shared-experience-not-shared-privacy
New Chat Memory and Skills are private by default. Sharing is an explicit action, not a default leak.
| Visibility | Semantics | | :-- | :-- | | private | Only the Owner can read — not even team admins | | team | Team members can read; the Owner / Admin can manage | | restricted | Precise access via User / Role / Agent ACL | | agent | For targeted equipping of Agents within the same team |
You can assign the "Release Skill" to the Release Agent, the "Architecture Wiki" to all development Agents, and CodeGraph to Coder and Reviewer.
Technical Implementation
#technical-implementation
TencentDB Agent Memory doesn't aim to "store everything." It solves three problems: what's worth keeping, who can use it, and how to retrieve less while retrieving the right things next time.
1\. Memory isn't flat records — it grows in layers
#1-memory-isnt-flat-records--it-grows-in-layers
Conversations are first saved as L0, then refined by an async pipeline into multiple levels of granularity:
| Layer | What it stores | Primary use | | :-- | :-- | :-- | | L0 Conversation | Raw conversations with full context | Verify exact wording, timestamps, and sources | | L1 Atom | Facts, preferences, constraints, and events extracted from conversations | Precise recall of actionable information | | L2 Scenario | Knowledge blocks organized around projects or scenarios | Quickly restore a working context | | L3 Core / Persona | Long-term profiles, stable patterns, and high-level cognition | Let Agents rapidly enter a user's and team's context |
Both generation and retrieval are layered: normally, L2/L3 provide a quick context bootstrap; when specific facts are needed, BM25 + vector retrieval + RRF fall back to L1/L0. Results are further capped by item count, character budget, and timeout limits to prevent memory from overwhelming the context window.
2\. Memory isn't a global prompt — it's the Agent's loadout
<!-- truncated for AAIF content page; source URL above contains full original -->