Organization repository on GitHub
Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.
- Forks
- 3.1k
- Last pushed
- Updated Oct 2026
Repo stats from the GitHub API, cached Oct 2026.Homepage
CommunityJev Integrations & Adapters
OpenViking
Volcengine's agent context database that unifies memory, knowledge RAG and skills under a viking:// virtual filesystem; it ships a Jev rerank client that scores candidate documents against api.typesafe.ai and treats the probability as relevance.
- Stars
- 39.6k
- Language
- Python
- License
- AGPL-3.0
- Published by
- Community
- Last verified
- Oct 2026
About this project
Website · Live Demo · GitHub · Issues · Docs · Blog. Lark · WeChat · Discord · X. OpenViking is an open-source context database for AI agents — one filesystem for everything an agent knows: knowledge, memory, and skills.
Quoted from the project's README. Read the full README.
Highlights
- 39,589 stars and AGPL-3.0; context is browsable with ls, tree, read, write, grep and find over viking:// URIs
- Three loading tiers: L0 one-sentence abstracts, L1 overviews and L2 full content, so agents judge relevance before reading files
- LoCoMo long-conversation accuracy rose to 80-83% from 24-57% native memory, with input tokens down 34.3-91.0%
- Version 0.3.22; tau2-bench experience memory added +6.87pp retail and +11.87pp airline task success
- The Jev rerank client scores each candidate with jev-latest against api.typesafe.ai because TypeSafe exposes no native rerank endpoint per the catalog summary
Watch out
AGPL-3.0. A large, fast-moving project; the Jev usage is a reranking client inside a broader retrieval system, and self-hosting needs an embedding and VLM provider.
Questions about this entry
Short answers drawn from the linked project or page.
It replaces opaque agent memory with an inspectable filesystem: knowledge, memories and skills each get viking:// URIs, and committed sessions become Markdown files you can read, edit and merge.
Yes. OpenViking Studio runs in the browser at openviking.ai/studio with no installation, and there is a Volcengine-hosted service with the first 50 files free.
The server is Python-based: uv plus Python 3.10 or newer, and a model provider that offers both an embedding model and a VLM. Install with `uv tool install openviking --upgrade` then run `openviking-server init`, which writes ~/.openviking/ov.conf. The server runs in the foreground, so keep that terminal open.
`openviking-server init` supports Volcengine, OpenAI, Codex OAuth, Kimi, GLM and a local Ollama instance. The configuration guide documents each path, and the wizard writes the chosen provider into ~/.openviking/ov.conf.
Yes. OpenViking Service is the same service run by Volcengine; the first 50 files are free, and you activate it from the Volcengine console. The README also points to OpenViking Studio in the browser, which needs no installation at all.
OpenViking stores each semantically processed directory with generated summaries: L0 is a one-sentence abstract for a quick relevance check, L1 is an overview of structure and key points, and L2 is the full original content, read only on demand. Agents scan L0 and L1 before opening L2.
AGPLv3, per the repository's license badge and LICENSE file. That is a strong copyleft license, so modifying OpenViking and offering it over a network brings the AGPL's source-availability obligations to your modified version.
More Jev resources like this
10GitHub stars
Local-first knowledge search with seven selectable pipelines: BM25 plus Jev reranking is the default vector-free path, plus agentic, embedding-hybrid, taxonomy, gate and line-search modes. Reranks up to 30 candidates in one batched set of Jev Noul relevance questions and streams cited answers from a configurable model.
Jev Integrations & Adapters#community#rag#retrieval
Community
aifabrice/jev-ragPython
aifabrice/jev-ragPython1GitHub stars
Precision-first RAG orchestrator that wires Jev as a System 1 gate around an LLM: it routes chitchat, triages retrieved chunks with relevance and answer-evidence Nouls, then verifies each claim and withholds drafts whose claims are unsupported.
Jev Integrations & Adapters#community#rag#hallucination
Community
david96182/cribrixPython
david96182/cribrixPython224GitHub stars
A Jev harness for PostgreSQL: 41 semantic operators plus a native Rust extension evaluate row-level predicates with Noul questions and keep the returned probabilities for explicit decision thresholds, leaving joins and aggregation to SQL.
Jev Integrations & Adapters#community#postgresql#nl2sql
Community
Sheltercosmo/jev4pgPython
Sheltercosmo/jev4pgPython255GitHub stars
Graph RAG framework over Milvus vector search with no graph database required: Jev Noul judgments select graph relations and rerank full source passages alongside vector-search candidates, reaching 86.07% average Recall@5 on 1,000 MuSiQue and 1,000 2Wiki queries in the two-stage evaluation.
Jev Integrations & Adapters#community#rag#retrieval
Community
zilliztech/vector-graph-ragPython
zilliztech/vector-graph-ragPython187.5kGitHub stars
Autonomous agent platform with 187,504 stars for building and running agents from plain English or a visual builder. Its platform features first-class TypeSafe Jev decision blocks for typed routing, filtering, scoring and confidence-gated next-action dispatching.
Jev Integrations & Adapters#community#autonomous-agents#platform
Community
Significant-Gravitas/AutoGPTPython
Significant-Gravitas/AutoGPTPython46.7kGitHub stars
Privacy-first, self-hosted personal knowledge management system with block-level references and a local-first Markdown editor; the project integrates Jev's decision model for high-speed document classification, flashcard intent categorization and automated tag routing.
Jev Integrations & Adapters#community#note-taking#knowledge-base
Community
siyuan-note/siyuanTypeScript
siyuan-note/siyuanTypeScriptFrom the Jev community
Posts from builders shipping with Jev right now.