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.
★ 30,923⑂ 3,028👁 89⑃ 1,423● 529▤ 22
More from this author
+22
Daily
+531
Weekly
+3,029
Monthly
30,923
stars
3,028
forks
89
watchers
1,423
prs
529
issues
22
releases
README
Agents remember. Humans innovate. Installation · Supported Agents · Best Practices · What is it? · Team Play · Technical Implementation · Benchmark · Roadmap English · 简体中文 --- Installation Start all three services in one go (memory-core + memory-hub + proxy): bash 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 Launch everything with one command; when finished, it prints a one-liner you can paste directly into Claude Open 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). The MongoDB storage backend is experimental (off by default); see INSTALL.md · MongoDB storage backend. 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. All Agents Share the Same Memory Server One Proxy, unchanged protocol, zero-code integration — point the Agent's base URL to the Proxy and configure its User Key. Most clients don't require a plugin, hook, or MCP server. DeepSeek Harness Claude Code Codex CodeBuddy WorkBuddy Hermes OpenClaw More frameworks coming soon... OpenCode Pi See INSTALL.md for links to the exact configuration steps of each client. OpenCode has a ready-to-use adapter configuration, and Pi uses the pi-plugin extension to connect through OpenAI Chat Completions. After binding a session, you can save a Team, Agent, and Task combination as the default for new sessions. Don't see your favorite Agent? You can try adapting it yourself with the Generic integration guide — and we'd love a PR adding native support for it. See CONTRIBUTING.md to get started. Best Practices Once you've deployed the stack and connected your Agents, use the guide to set up a team, import and assign memory assets, and see how well they work on a real task. See the Best Practices guide. 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. text Existing information → Reusable memory assets → Fewer turns → Less rework → More stable results and higher eff
Top issues
#1289[Bug] L0 conversation only records user messages — assistant messages skipped during tool-call sessions13 comments · 2026-09-08#761[Bug] `./start-all.sh` 无法完成部署:三处脚本缺陷导致 init-admin 阶段中断(v2.0.0, macOS + podman)3 comments · 2026-08-04#106Suggestion: Add reproducible memory evaluation benchmarks5 comments · 2026-05-28#1321[Bug] 移除成员/删除用户后其 Agent 成为孤儿,任何角色(含 admin)均无法删除10 comments · 2026-09-10#1545hermes-plugin: agent_id lookup ignores agent_identity, so calls are attributed to the default agent7 comments · 2026-09-27#1343[Bug] store-pool.ts drops sendDimensions when building the embedding service — all embeddings fail silently and retrieval degrades to keyword-only7 comments · 2026-09-11#927[Bug] L0 embedding timeout silently degrades to metadata-only write with code:0 — MAX_RETRIES=0 leaves retry scaffold disabled7 comments · 2026-08-10#420v1.0.0 tag: OTel SDK version mismatch — `new Resource()` not compatible with `resources@^2.x`7 comments · 2026-07-07
Discussions
#1995Brand identity & domain suggestion for TencentDB-Agent-Memory (airam.cloud / AI RAM concept)0 comments · 2026-11-14#1921Aungko1 comments · 2026-10-29#1920Aungko0 comments · 2026-10-29#1730Kilo code getting query from the Memory Proxy0 comments · 2026-10-18#1644Code_Graph注册仓库是否支持subversion1 comments · 2026-10-14#1638不同团队之间的知识共享0 comments · 2026-10-12#1565[Question][v2.0.1][MemoryCore L0] Message ID、写入确认、timestamp 与 ID 格式 Contract 确认0 comments · 2026-09-30#1524这个适合给win配置吗0 comments · 2026-09-26
Latest release
v2.0.3 v2.0.3 2026-10-26[2.0.3] - 2026-10-26 v2.0.3 发布,相比 v2.0.3-beta.1 新增会话默认绑定与 Wiki 富文档,并把未单独配置超时的上游等待时间从 10 分钟改为 1 小时。同时修复 DeepSeek Harness 辅助接口、历史记忆时间格式、安装脚本、面板交互、Knowledge 启动,以及代理在 Redis 中断后不能自行恢复的问题。 产品定位:让 Agent 的经验、文档、代码沉淀成可复用资产,让下一位 Agent 直接读档。详见 README_CN.md。 🔁 会话默认绑定 - 用户可为自己保存 Team、Agent、Task 的默认组合。新会话会直接使用该组合,不再每次弹出选择 - 未设置时仍走原来的选择流程;默认组合失效时自动回到原流程,并说明原因 - 可在会话中锁定或解锁该默认组合,避免后续会话被意外改掉 📄 Wiki 富文档 - Wiki 新增 Word、Excel、PowerPoint、PDF 等富文档的导入、预览和内容抽取 - 原有 Markdown、文本和 HTML 导入保持可用;修复 Markdown 粘贴在部分情况下导入失败的问题 ⏱️ 长回复不再被提前截断 - 未单独配置超时时,上游等待时间由 10 分钟改为 1 小时;已填写 forwardTimeoutMs 的配
相关报道 (7)
腾讯网腾讯云数据库 Agent Memory 开源 80 天 Star 破万,全新发布 Team Memory2026-08-06腾讯网TencentDB Agent Memory 全球正式开源:让 Agent 沉淀经验,让人专注创造2026-05-14新浪网腾讯云开源TencentDB Agent Memory 最高降低61%的Token消耗2026-05-14腾讯新闻TencentDB Agent Memory 适配 JEV 决策模型:让 Agent 按需调用团队经验2026-10-13QQ NewsTencentDB Agent Memory 新增DeepSeek Harness 桌面端接入支持2026-10-09InfoQ.cnAgent 记忆,不能只靠聊天记录2026-08-04Pasquale PillitteriTencentDB Agent Memory:AI 智能体的本地记忆2026-07-08
News & coverage (5)
Hacker NewsTencentDB Agent Memory: A team-level memory hub for AI agents▲ 2 · 0 comments · 2026-08-05precedenceresearchTencentDB Agent Memory Tops 20,000 GitHub Stars in 90 Days, Launches Team Memory for Multi-Agent Alliance2026-08-16irblog.prnewswire.comTencentDB Agent Memory Tops 20,000 GitHub Stars in 90 Days, Launches Team Memory for Multi-Agent Collaboration2026-08-13Pasquale PillitteriTencentDB Agent Memory: Local Memory for AI Agents2026-07-08MarkTechPostTencent Open-Sources TencentDB Agent Memory: A 4-Tier Local Memory Pipeline for AI Agents2026-05-23