Skip to main content
OpenViking

OpenViking: The Context Database for AI Agents

English / 中文 / 日本語

Website · Live Demo · GitHub · Issues · Docs

👋 Join our Community

📱 Lark Group · WeChat · Discord · X

volcengine%2FOpenViking | Trendshift


What is OpenViking

OpenViking is an open-source context database for AI agents. It stores memories, resources, and skills as one virtual filesystem under the viking:// protocol, so an agent browses its own context with ls, tree, and find instead of querying a black-box vector store. Content is processed into three tiers — L0 abstract, L1 overview, L2 details — and loaded on demand. Every retrieval leaves a trajectory you can watch and debug. Full introduction: Getting started.

OpenViking Studio playground

The OpenViking Studio playground — a live demo you can open in the browser, no installation required.

Why OpenViking

  • One filesystem for all context. Memories, resources, and skills each get a viking:// URI. Agents locate and manipulate context deterministically, like a developer working with files. → Viking URI · Context types
  • Tiered loading cuts token spend. Every entry is processed into L0 (abstract), L1 (overview), and L2 (details) on write, then loaded only as deep as the task requires. → Context layers
  • Directory recursive retrieval. Vector search first locates the highest-scoring directory, then drills down layer by layer, so results arrive with their surrounding context intact. → Retrieval
  • Observable retrieval. Each query preserves its directory-browsing trajectory. When a result looks wrong, you can see exactly which path produced it. → Retrieval
  • Sessions become memory. After a session commits, OpenViking asynchronously extracts user preferences and agent experience into long-term memory. → Session

How the pieces fit together: Architecture. The thinking behind the design: The Database Paradigm for Context Engineering.

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.

Each directory carries its own L0/L1 layers, so relevance can be judged before any full file is read:

viking://resources/my_project/
├── .abstract               # L0: ~100 tokens - quick relevance check
├── .overview               # L1: ~2k tokens - structure and key points
└── docs/
    ├── .abstract
    ├── .overview
    └── api/
        ├── auth.md         # L2: full content, loaded on demand
        └── endpoints.md

Proof it works

OpenViking 0.3.22 has been evaluated on long-conversation user memory (LoCoMo) and multi-turn agent tasks (tau2-bench). Full results and setup details, including knowledge-base QA, are in the benchmark report; reproduction scripts live in ./benchmark.

Benchmark results. LoCoMo accuracy: OpenClaw 24.20% native vs 82.08% with OpenViking; Hermes 33.38% vs 82.86%; Claude Code 57.21% vs 80.32%. tau2-bench task success: Retail 70.94% vs 77.81%; Airline 54.38% vs 66.25%.
  • User memory (LoCoMo): with OpenViking, all three agent integrations land at 80–83% accuracy — up from 24–57% on their native memory — while input tokens drop by 34.3–91.0% and query latency by 58.45–66.10%.
  • Agent experience (tau2-bench): experience memory lifts task success by +6.87pp (retail) and +11.87pp (airline) over the same LLM without memory.

Quick start

💡 Want to see it in action first? Try OpenViking Studio — a live hosted instance with a context playground, semantic search, and a multi-agent hub. No installation required.

Requires Python 3.10 or higher.

pip install openviking --upgrade
openviking-server init      # interactive wizard: providers, models, ov.conf
openviking-server doctor    # validate setup
openviking-server           # start (background: nohup openviking-server > openviking.log 2>&1 &)

init walks you through provider setup and writes ~/.openviking/ov.conf. It supports Volcengine, OpenAI, Codex OAuth, Kimi, GLM, and local Ollama — for Ollama it can detect and install the runtime and pull models suited to your hardware. doctor checks the config file, Python version, provider connectivity, and disk space without a running server. Manual ov.conf templates, per-provider examples, environment variables, and Windows setup: Configuration guide · Quick start docs.

The install already includes the ov client CLI. With the server running:

ov status
ov add-resource https://github.com/volcengine/OpenViking # --wait
ov ls viking://resources/
ov tree viking://resources/volcengine -L 2
# wait some time for semantic processing if not --wait
ov find "what is openviking"
ov grep "openviking" --uri viking://resources/volcengine/OpenViking/docs/en

Next steps:

  • Client configuration (ov config), standalone CLI installs (npm / cargo), and advanced usage such as index rebuilding: CLI setup
  • Docker and production deployment: Deployment guide

Use it with your agent

Integrations inject OpenViking recall into your agent's context and auto-commit session memory:

Setup instructions for each agent: Agent integrations overview.

OpenViking Helper (Beta)

OpenViking Helper is a desktop console, currently in beta for macOS and Windows x64:

  • Visual local agent setup: detects OpenViking CLI, Claude Code, Codex, Cursor, Trae, and OpenCode, then configures supported plugin, MCP, Hook, and CLI integrations.
  • Session trace inspection: parses Claude Code, Codex, and Trae sessions to show OpenViking recall, prompt injection, MCP calls, capture, and commit events.
  • Local memory and skill management: views local memory / rule files and SKILL.md skills, then syncs them to OpenViking.

Download:

VikingBot

VikingBot is an AI agent framework built on top of OpenViking:

pip install "openviking[bot]"
openviking-server --with-bot
ov chat   # in another terminal

The official Docker image bundles VikingBot and starts it by default alongside the server and console UI. Details: VikingBot guide.

Deploy in production

For production, run OpenViking as a standalone HTTP service — see Server deployment and the Deployment guide.

Prefer not to operate it yourself? OpenViking Personal is officially hosted and ready to use, scales far beyond local hardware with VikingDB, and includes a free trial for up to 50 files; existing open-source users can move over with the migration tool. → openviking.ai

Research

OpenViking open-sources a subset of the core capabilities described in the VikingMem paper:

VikingMem: A Memory Base Management System for Stateful LLM-based Applications Jiajie Fu, Junwen Chen, Mengzhao Wang, Aoxiang He, Maojia Sheng, Xiangyu Ke, Yifan Zhu, and Yunjun Gao. arXiv:2605.29640, 2026. Accepted by VLDB 2026. 📄 Read the paper on arXiv

Community & contributing

OpenViking is still in its early stages, and there is plenty left to build.

Security and privacy

This project takes security seriously. For vulnerability reporting and supported versions, see SECURITY.md

License

The OpenViking project uses different licenses for different components:

  • Main Project: AGPLv3 - see the LICENSE file for details
  • crates/ov_cli: Apache 2.0 - see the LICENSE for details
  • examples: Apache 2.0 - see the LICENSE for details
  • third_party: Respective original licenses of third-party projects

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

openviking-0.4.11.tar.gz (57.7 MB view details)

Uploaded Source

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

openviking-0.4.11-cp310-abi3-win_amd64.whl (25.0 MB view details)

Uploaded CPython 3.10+Windows x86-64

openviking-0.4.11-cp310-abi3-manylinux_2_31_x86_64.whl (22.6 MB view details)

Uploaded CPython 3.10+manylinux: glibc 2.31+ x86-64

openviking-0.4.11-cp310-abi3-manylinux_2_31_aarch64.whl (20.1 MB view details)

Uploaded CPython 3.10+manylinux: glibc 2.31+ ARM64

openviking-0.4.11-cp310-abi3-macosx_15_0_x86_64.whl (21.3 MB view details)

Uploaded CPython 3.10+macOS 15.0+ x86-64

openviking-0.4.11-cp310-abi3-macosx_14_0_arm64.whl (19.0 MB view details)

Uploaded CPython 3.10+macOS 14.0+ ARM64

File details

Details for the file openviking-0.4.11.tar.gz.

File metadata

  • Download URL: openviking-0.4.11.tar.gz
  • Upload date:
  • Size: 57.7 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for openviking-0.4.11.tar.gz
Algorithm Hash digest
SHA256 4c18cb5c01b737b8ec9d0e9212c0ad54ef29f7f244aa7da79ffc21259d886317
MD5 51e0f3f341a99474b9a4dea9826dfd93
BLAKE2b-256 4007f2a02e74784810f56a76f15115a7a5d1ac6ca4a982970540de4734e5cae3

See more details on using hashes here.

Provenance

The following attestation bundles were made for openviking-0.4.11.tar.gz:

Publisher: release.yml on volcengine/OpenViking

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file openviking-0.4.11-cp310-abi3-win_amd64.whl.

File metadata

  • Download URL: openviking-0.4.11-cp310-abi3-win_amd64.whl
  • Upload date:
  • Size: 25.0 MB
  • Tags: CPython 3.10+, Windows x86-64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for openviking-0.4.11-cp310-abi3-win_amd64.whl
Algorithm Hash digest
SHA256 858f3d7bf2ecb102744d6de704551f9df9b4fa4ab9adc2bdcdd500f8881bf6c8
MD5 f93a1f86b9cfa099c7b04b84e20e65ba
BLAKE2b-256 58a1e2c41af0a5672ec79afe0e7e858a03d1c7edb513a81f0a69d1a0f32a096f

See more details on using hashes here.

Provenance

The following attestation bundles were made for openviking-0.4.11-cp310-abi3-win_amd64.whl:

Publisher: release.yml on volcengine/OpenViking

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file openviking-0.4.11-cp310-abi3-manylinux_2_31_x86_64.whl.

File metadata

File hashes

Hashes for openviking-0.4.11-cp310-abi3-manylinux_2_31_x86_64.whl
Algorithm Hash digest
SHA256 db7d58a9689651cabe3978caca089eb3fee62cf8ea6521492309f25c56dc0d05
MD5 ee3594bec1780a1ac75dbeb263668359
BLAKE2b-256 8d9aa0ab4a57ea6363b4849169d1ec282012ed60ea65e984007f50ce5a64deaa

See more details on using hashes here.

Provenance

The following attestation bundles were made for openviking-0.4.11-cp310-abi3-manylinux_2_31_x86_64.whl:

Publisher: release.yml on volcengine/OpenViking

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file openviking-0.4.11-cp310-abi3-manylinux_2_31_aarch64.whl.

File metadata

File hashes

Hashes for openviking-0.4.11-cp310-abi3-manylinux_2_31_aarch64.whl
Algorithm Hash digest
SHA256 ae67550704e2d30d1bc1b0f38c35101dc55b0492834021dcd1aee9792e78de2c
MD5 a93072e398bafc21225e35aa1e2c50ac
BLAKE2b-256 199e648b9528f157691f2df0c3673298af55390e85640bbb9405b28cbb21d5fd

See more details on using hashes here.

Provenance

The following attestation bundles were made for openviking-0.4.11-cp310-abi3-manylinux_2_31_aarch64.whl:

Publisher: release.yml on volcengine/OpenViking

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file openviking-0.4.11-cp310-abi3-macosx_15_0_x86_64.whl.

File metadata

File hashes

Hashes for openviking-0.4.11-cp310-abi3-macosx_15_0_x86_64.whl
Algorithm Hash digest
SHA256 f3ed8d86917fe3cd94421019fb997bb874ef1f95fd97bada614a10b1516aba77
MD5 a29437cbf9346b11e7b0e263730bf28d
BLAKE2b-256 9cdb5bce6b007e0645c6c541974eb14b35329a5a0db6b96561df675c37d94d25

See more details on using hashes here.

Provenance

The following attestation bundles were made for openviking-0.4.11-cp310-abi3-macosx_15_0_x86_64.whl:

Publisher: release.yml on volcengine/OpenViking

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file openviking-0.4.11-cp310-abi3-macosx_14_0_arm64.whl.

File metadata

File hashes

Hashes for openviking-0.4.11-cp310-abi3-macosx_14_0_arm64.whl
Algorithm Hash digest
SHA256 4a0389f2c3de0eb41cc2f26ccedb89566d8719393c3ab37d2ee2895cf9a8ebee
MD5 3a373bdb09956c613cad644d43238c98
BLAKE2b-256 a083ea2dbb9fb03218785c81f0b1b380024e22d6af75d06bd42c91e43aa180e7

See more details on using hashes here.

Provenance

The following attestation bundles were made for openviking-0.4.11-cp310-abi3-macosx_14_0_arm64.whl:

Publisher: release.yml on volcengine/OpenViking

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page