volcengine /OpenViking
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
★ 42,264⑂ 3,493👁 111⑃ 5,771● 1,808▤ 118
context-databaseagentic-ragagent-memoryself-evolvingagent-pluginsdsh-pluginagent-contextmemory-management
More from this author
+31
Daily
+420
Weekly
42,264
stars
3,493
forks
111
watchers
5,771
prs
1,808
issues
118
releases
README
The Context Database for AI Agents
English / 中文 / 日本語
Website · Live Demo · GitHub · Issues · Docs · Blog
Lark ·
WeChat ·
Discord ·
X
What is OpenViking
OpenViking is an open-source context database for AI agents — one filesystem for everything an agent knows: knowledge, memory, and skills.
Most agent memory is a black box: text goes in, embeddings come out, and nobody can see what was actually stored. OpenViking organizes context as a virtual filesystem under viking:// instead. Agents navigate it like files — ls, tree, read, write, grep — and you can open any directory to inspect and edit what your agent knows. Every directory carries a generated summary, so agents can scan summaries first and decide what to read.
Try OpenViking Studio in your browser, no installation required. Self-host Web Studio.
Why OpenViking
- One filesystem for knowledge, memory, and skills. Resources hold documents and code; memories retain user preferences and experience; skills define how to perform tasks — not just extracted facts, but the full context, each with a viking:// URI for browsing and retrieval. → Viking URI · Context types
- Search a directory, not the whole index. Scope semantic search to a project or memory subtree instead of scanning a flat vector pool. find runs a query directly; search plans retrieval from session context. → Retrieval
- Read the summary before the source. Generated directory abstracts (L0) and overviews (L1) let agents judge relevance before opening full content (L2). → Context layers
- Sessions become files you can read. Committing a session archives the conversation and extracts memories as Markdown you can inspect, edit, and merge. With VikingBot enabled, ov compile organizes source material into a wiki, knowledge graph, or report. → Sessions · Context compilation
Architecture · Design rationale
viking://
├── resources/ Resources: project docs, repos, web pages, etc.
│ └── my_project/
│ ├── docs/
│ │ ├── api/
│ │ └── tutorials/
│ └── src/
└── user/
└── {user_id}/
├── memories/
│ └── preferences/
│ ├── writing_style
│ └── coding_habits
├── resources/
│ └── private_project/
├── skills/
│ ├── search_code
│ └── analyze_data
└── peers/
└── web-visitor-alice/
The three loading tiers:
- L0 (Abstract): a one-sentence summary for quick relevance checks.
- L1 (Overview): core information and usage scenarios for planning.
- L2 (Details): the full original data, read only when needed.
Semantically processed directories carry L0/L1 summaries, so agents can judge relevance before reading full files:
viking://resources/my_project/
├── .abstract.md L0: quick relevance check
├── .overview.md L1: structure and key points
└── docs/
├── .abstract.md
├── .overviTop issues
#4043[Bug]: preferences 按 LLM 推断的 user 字段分裂成多个用户名子目录10 comments · 2026-08-16#3508[Bug]: memory extraction fails with llama.cpp when LLM returns list instead of dict (adds always empty)10 comments · 2026-07-24#6262[Feature]: Use-based lifecycle for Experiences and Session Skills (count recall exposure, archive what never gets used)9 comments · 2026-10-19#5038[Question]: Performance bottlenecks in Agent execution & file processing + Questions on Bulk URL uploads & PDF page tracking9 comments · 2026-09-15#4612[Bug]: v0.4.17.1 L0 directory abstracts not generated — Lock error wrapping + missing parent rollup8 comments · 2026-09-02#5841[Bug]: /mcp answers unknown methods (including the 2026-07-28 server/discover probe) with -32602, so modern MCP clients re-probe 17× before falling back7 comments · 2026-10-09#5828[Bug]: entities category guidance is language-branched and freely invented, splitting one topic into multiple category directories7 comments · 2026-10-09#5894Memory extraction fails with `parse_error` on large sessions — no size-based auto-chunking; chunking the same content succeeds 100%6 comments · 2026-10-11
Discussions
#7700RFC:OVSA 控制台 API 与选配功能(OVSA-CONSOLE-001)0 comments · 2026-11-14#7691A curious visitor hoping to meet the Agent Hub residents0 comments · 2026-11-14#7428Proposal: Weekly Stable Releases with Major Bug-Fix Exceptions | 建议:每周发布稳定版(重大 Bug 修复除外)0 comments · 2026-11-11#7335RFC:Agent 密钥“可用不可见”:Gateway 封存 + 插件在执行边界代入1 comments · 2026-11-10#7215实测:给记忆系统降推理档,账本上通常不省钱(24h 观测 + 三臂对照)1 comments · 2026-11-08#7213RFC:新增 `ov privacy run`,让 agent 默认不把密钥带进上下文4 comments · 2026-11-07#7098[RFC] An explicit evidence contract for text, image hits and Ragas evaluation0 comments · 2026-11-05#6967OV Web Clipper: a local-first Chrome extension for clipping webpages directly into OpenViking0 comments · 2026-11-03
Latest release
v0.5.5 v0.5.5 2026-11-13中文 主要更新 - PostgreSQL 部署选项:新增 pgvector 向量后端(storage.vectordb.backend: "pgvector",支持精确检索和 HNSW 检索,需要安装 openviking[pgvector])和 PostgreSQL PathLock(storage.agfs.pathlock.provider: "postgres")。多进程、多主机部署不依赖 Redis,也可以共享向量数据和路径锁租约。7516、7481 - 多节点协调:新增 storage.agfs.coordination(memory / sqlite / cache),统一负责 Watch 选主和语义任务版本;只有已持久化的工作才会取代旧任务,按 key 的状态保留一天后过期。7466 - 快照路径历史索引:snapshot/log?paths=... 改用派生索引查找改动过指定路径的提交,默认为 SQLite,多实例部署可选 MySQL,设为 none 则保持原来的扫描方式。快照提交、文件内容和 API 响应都不变。7505 - Gateway Context Profile:新增 recall_peer_scope(all / actor),可把召回限制在当前 peer;新增 capture_memory_types,限制 capture 抽取的记忆类型;c
相关报道 (11)
blog.csdnOpenViking 记忆插件共享库深度解析:工作区 Peer 身份、召回隔离与分层配置2026-09-10blog.csdn为 OpenClaw 安装 OpenViking 插件:长期记忆、知识库检索与 RAG 上下文完整接入指南2026-09-10bilibiliOpenViking:Agent 的记忆、RAG 与 Skills 为什么要合成一层2026-08-23cyberqGitHub 趨勢周報 Vol.29:代理記憶與程式碼圖譜補上長期脈絡,資安技能庫規模化2026-08-2151CTOOpenViking 实战教程:搭建多仓库代码语义检索系统,赋能 AI 助手 & OpenClaw 记忆插件 2.0 升级2026-03-27腾讯网给“龙虾”AI Agent装上记忆功能!字节开源了AI 上下文数据库:OpenViking2026-03-13csdn重磅!OpenClaw+OpenViking 正式登陆鲲鹏,打造端到端AI Agent最佳实践2026-03-11新浪新闻_手机新浪网DeepSeek Harness不可错过的12款神器!还有崔添翼推荐的2026-10-21InfoQ.cnOpenViking x OpenClaw:开箱即用,解决 Agent 的长期记忆困局2026-03-17www.80aj.comOpenViking 深度解析:字节跳动如何用"文件系统"思维重新定义 AI Agent 的记忆2026-02-20