TencentDB Agent Memory: A Team-Level Memory Hub, Not Just Per-Agent Recall

Tencent Cloud released TencentDB Agent Memory, an MIT-licensed memory hub for AI agent teams that converts conversations, documents, and code into four shareable memory assets—Chat Memory, Skill, Wiki, and CodeGraph—using a layered L0-L3 distillation pipeline. The project, which has over 10,600 GitHub stars and is labeled 'Team Memory Beta,' reports a +59% PersonaMem score improvement, addressing the problem of repetitive work in agent workflows by enabling team-level memory sharing rather than per-agent recall.

TencentDB Agent Memory: A Team-Level Memory Hub, Not Just Per-Agent Recall TencentDB Agent Memory is Tencent's MIT-licensed memory hub for AI agent teams, turning conversations, docs, and code into four governed, shareable memory assets — Chat Memory, Skill, Wiki, and CodeGraph — with a layered L0-L3 distillation pipeline and a reported +59% PersonaMem score. - ⭐ 10663 - Node.js - MIT - Updated 2026-08-02 AI Agent Memory: Letta vs Mem0 vs A-Mem https://dibi8.com/resources/llm-frameworks/ai-agent-memory-persistence-letta-mem0-a-mem-2026/ • Hermes Agent: Self-Improving AI Agent https://dibi8.com/resources/llm-frameworks/hermes-agent-self-improving-ai-agent/ Project banner — from github.com/TencentCloud/TencentDB-Agent-Memory What Is TencentDB Agent Memory? what-is-tencentdb-agent-memory TencentDB Agent Memory starts from a specific question the maintainers state directly: “How do you reduce repetitive work when using Agents?” If project context has already been explained once, a new session shouldn’t need it re-explained. If a document’s already been read, the next agent shouldn’t start from page one. TencentDB Agent Memory’s answer is a Memory Hub that extracts, governs, and routes four types of reusable memory assets across a team of agents — not just a single agent’s own conversation history. 🔗 GitHub : https://github.com/TencentCloud/TencentDB-Agent-Memory https://github.com/TencentCloud/TencentDB-Agent-Memory MIT licensed, at 10,600+ GitHub stars , with a commit from July 29, 2026 , it’s a Tencent Cloud project still explicitly labeled “Team Memory Beta” — evolving quickly rather than a finished, stable product. Four Memory Assets, Not One Chat Log four-memory-assets-not-one-chat-log | Chat History | Standard RAG | TencentDB Agent Memory | | |---|---|---|---| | Cross-session user understanding | Partial | Partial | Chat Memory | | Distilled executable experience | No | No | Skill | | Document structure & relationships | No | Chunk retrieval only | Wiki + Link Graph | | Code call graphs & impact scope | No | Text match only | CodeGraph | | Ownership / Version / Status | No | No | Yes | | Team sharing & Agent loadout | No | No | Yes | | Private / Team / ACL | No | Partial | Yes | The framing the maintainers draw: RAG answers “what can be found?” — TencentDB Agent Memory also answers “who can use it, which version is valid, and which Agent should receive it.” The four asset types the-four-asset-types 🧠 Chat Memory — preferences, facts, decisions, and interaction history. Each agent gets its own automatically on creation. Distilled layer by layer: L0 Conversation → L1 Atom → L2 Scenario → L3 Persona. ⚡ Skill — a reusable procedure extracted from completed work, with versions, resource files, trigger boundaries, execution steps, and validation rules — private by default, shareable with the team after review. 📖 Wiki — documents, specs, and runbooks turned into structured, link-graphed pages, explicitly inspired by Andrej Karpathy’s “LLM Wiki” concept https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f . 🕸️ CodeGraph — indexes code symbols, files, call relationships, and impact paths, so an agent can check callers/callees and impact scope before modifying code. Installation installation git clone https://github.com/TencentCloud/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 Launches memory-core + memory-hub + proxy in one command start-all.sh starts all three services memory-core , memory-hub , proxy together and prints a one-liner you can paste directly into Claude when it finishes. The panel is then reachable at http://localhost:8125 . Migrating from an older v1.x/v0.x install has a dedicated tool v2 → v3 ; new installs can skip it. Cold Start: Import What You Already Have cold-start-import-what-you-already-have Rather than starting a new agent team from zero, existing assets can be imported directly: Cold-start import flow — from github.com/TencentCloud/TencentDB-Agent-Memory Codebases → CodeGraph automatically indexes symbols, files, call relationships, and impact paths Documents & files → Wiki automatically generates structured, link-graphed pages Conversation sessions → Skills and Chat Memory are automatically extracted as reusable assets Team Play: Building an Agent Team, Not Four Chat Windows team-play-building-an-agent-team-not-four-chat-windows The README’s own worked example is a “one-person company” with role-specific agents: 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 experience Each role gets a different loadout of memory assets — not everything, just what that role needs: 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 Skill The pitch: you’re not opening four disconnected chat windows, you’re assembling a squad that inherits the team’s accumulated experience — and a small team’s experience can keep compounding rather than resetting with every new session. Governance: Private by Default, Sharing Is Explicit governance-private-by-default-sharing-is-explicit | Visibility | Semantics | |---|---| private | Only the Owner can read — not even team admins | team | Team members can read; Owner/Admin can manage | restricted | Precise access via User / Role / Agent ACL | agent | Targeted equipping of specific agents on the same team | New Chat Memory and Skills are private by default — sharing is an explicit action, not a default leak. This matters once a “memory hub” is holding real decisions and preferences: you can assign a Release Skill only to the Release Agent, an Architecture Wiki to all development agents, and CodeGraph specifically to Coder and Reviewer agents. Technical Implementation technical-implementation Technical architecture overview — from github.com/TencentCloud/TencentDB-Agent-Memory The stated design goal isn’t “store everything” — it’s what’s worth keeping, who can use it, and how to retrieve less while retrieving the right thing. Layered memory, not flat records layered-memory-not-flat-records | Layer | What it stores | Primary use | |---|---|---| | L0 Conversation | Raw conversations, full context | Verify exact wording, timestamps, sources | | L1 Atom | Extracted facts, preferences, constraints, events | Precise recall of actionable information | | L2 Scenario | Knowledge blocks organized by project/scenario | Quickly restore a working context | | L3 Core / Persona | Long-term profiles, stable patterns | Rapid entry into a user’s/team’s context | Retrieval is layered too: L2/L3 provide a fast context bootstrap by default; when specific facts are needed, it falls back to BM25 + vector retrieval + RRF Reciprocal Rank Fusion across L1/L0, with results capped by item count, character budget, and timeout to keep memory from overwhelming the context window. Memory as loadout, not global prompt injection memory-as-loadout-not-global-prompt-injection Chat Memory, Skill, Wiki, and CodeGraph are all registered uniformly as Memory Assets , and access is resolved via Fixed Binding + ACL — narrowing by Team, User, Agent, and visibility first, then retrieving based on the current query. Switching an agent or framework means re-equipping assets, not retraining. Tool-based access, not wholesale injection tool-based-access-not-wholesale-injection Agents discover capabilities via /v3/tools/list , then call /v3/tools/call to read specific Wiki pages, source code, or impact paths — documents and code are part of memory, but they stay as on-demand tools rather than being dumped into context wholesale. Benchmark benchmark | Benchmark | Without | With | Relative improvement | |---|---|---|---| PersonaMem | 48% | 76% | +59% | PersonaMem tests whether an agent correctly understands and applies user information after extended interactions. This is a single benchmark reported by the maintainers , not an independently reproduced result — a useful signal, not a guarantee it generalizes to your own workload. Limitations From the Project’s Own Notes limitations-from-the-projects-own-notes Async processing delay — Wiki and CodeGraph build asynchronously; allow time before they reach ready status CodeGraph is public-repo-first — private repositories and SSH credentials are “still being refined,” not fully supported yet Manual asset binding — the Hub supports manual binding today; fully automated memory routing is still under iteration Limited framework support today — OpenClaw, Hermes Agent, and SDK integration are supported now; broader cross-framework migration is on the roadmap, not shipped Use Cases use-cases 1. Onboarding a New Agent or Teammate Without Re-Explaining Everything 1-onboarding-a-new-agent-or-teammate-without-re-explaining-everything Import existing docs, codebase, and past agent conversation sessions once — new team members and new agents both start from the “save file” instead of relearning the project from scratch. 2. Role-Scoped Agent Teams 2-role-scoped-agent-teams Give a Reviewer agent CodeGraph and historical-incident Chat Memory, but not the Scout’s market-research Wiki — the loadout model keeps each agent’s context relevant instead of dumping everything into every agent. 3. Governed Knowledge Sharing Across a Team 3-governed-knowledge-sharing-across-a-team private / team / restricted / agent visibility lets an individual’s working notes stay private by default while explicitly promoting genuinely reusable Skills and Wiki pages to the team. 4. Pre-Change Impact Analysis 4-pre-change-impact-analysis CodeGraph’s call-relationship and impact-path indexing lets an agent check what else might break before modifying shared code — closer to what a careful human reviewer would do than a plain text-match RAG lookup. Related Repositories related-repositories | Repository | Purpose | |---|---| | CodeGraph colbymchenry https://github.com/colbymchenry/codegraph Related Articles related-articles AI Agent Memory: Letta vs Mem0 vs A-Mem https://dibi8.com/resources/llm-frameworks/ai-agent-memory-persistence-letta-mem0-a-mem-2026/ — for comparing single-agent memory frameworks against this team-level hub approach Hermes Agent: Self-Improving AI Agent https://dibi8.com/resources/llm-frameworks/hermes-agent-self-improving-ai-agent/ — one of the frameworks TencentDB Agent Memory integrates with directly Conclusion conclusion TencentDB Agent Memory targets a problem most agent-memory tools don’t: not “how does one agent remember one user,” but “how does a team of agents share governed, versioned experience without leaking everything to everyone.” The L0-L3 layered distillation, the four distinct asset types especially Skill and CodeGraph, which go beyond what chat-log RAG models , and the explicit-sharing-by-default governance make it a more structured answer than most single-agent memory libraries — at the cost of currently narrower framework support OpenClaw, Hermes, SDK and features still labeled beta or roadmap. Best for : Teams running multiple agents or agent + human teams who need governed, shareable memory — not solo users who just want one agent to remember one conversation history. GitHub : https://github.com/TencentCloud/TencentDB-Agent-Memory https://github.com/TencentCloud/TencentDB-Agent-Memory Last updated: 2026-08-02