openbkn-ai /bkn-foundry
BKN Foundry is the Ontology back-end foundation of OpenBKN. It transforms ontology-driven business semantics into runtime services: data, logic, actions, security governance, and observability.
★ 1,400⑂ 139👁 20⑃ 2,066● 1,182▤ 5
1,400
stars
139
forks
20
watchers
2,066
prs
1,182
issues
5
releases
README
BKN Foundry 中文 | English 🌐 Website: openbkn.ai --- ▶ Watch the full 3-minute OpenBKN video on YouTube --- OpenBKN is an ontology-driven business knowledge network platform. Through ontology modeling, it turns the data and logic scattered across documents, systems, processes, rules, and expert experience into a business knowledge network that agents can understand, execute, and verify — so agents land accurately, safely, and reliably in real business environments, not just generating answers but continuously creating executable, traceable, and verifiable business value. BKN Foundry is the technical foundation of OpenBKN, providing that business knowledge network with unified data access, safe execution, and governance. On this page: 📚 Quick links · 🚀 Quick start · 🛠️ OpenBKN SDK · 🛡️ Administration · 🏗️ BKN Foundry · 📐 BKN Lang · 📊 Benchmarks Note: BKN Foundry is a backend-only framework — it does not include a web UI. All interactions are through the CLI, SDK, or API. 📚 Quick Links - 🛠️ OpenBKN SDK - End-user / agent BKN CLI, TypeScript SDK, and the AI agent skill - 🤝 Contributing - Guidelines for contributing to the project - 🚢 Deployment - One-click deploy to Kubernetes - 📘 Documentation - Product documentation and usage guides (EN / 中文) - 📖 API Reference - OpenAPI docs for every service (YAML source + rendered Markdown / interactive HTML) - 📦 Samples - Runnable end-to-end walkthroughs, in their own repo - 🧾 Release Notes - All notable changes 🚀 Quick Start 1. Prerequisites & planning — read the Deployment Guide and satisfy its prerequisites. Linux is the supported target for full installs; macOS local dev (kind) is optional — see Mac install (dev) (中文). 2. Pre-install host check / fix with preflight.sh (recommended) On the target install host, run a system check before deploy.sh. It verifies kernel / sysctl / containerd / kubectl / helm / Node / BKN CLIs and can fix what's missing (each fix is opt-in unless -y): bash git clone https://github.com/openbkn-ai/openbkn-deploy.git cd openbkn-deploy chmod +x preflight.sh deploy.sh onboard.sh sudo bash ./preflight.sh check-only (default) sudo bash ./preflight.sh --fix check + interactive fixes sudo bash ./preflight.sh --fix -y auto-approve every fix sudo bash ./preflight.sh --list-fixes preview which fixes would run, no changes sudo bash ./preflight.sh --help all flags (--role, --skip, --report, --output=json, …) Exit codes: 0 OK, 1 any FAIL, 2 only WARN. Use --report=/tmp/preflight.txt to keep a full log. 3. Run installation scripts: bash (Same openbkn-deploy directory as step 2) Install the full BKN Foundry stack ./deploy.sh openbkn install Or specify addresses explicitly (skips interactive prompts): --access_address Address for clients to reach OpenBKN services (can be IP or domain) --api_server_address IP bound to a local network interface for K8s API server (must be a real NIC IP) ./
Top issues
#747[Epic][0.1.4] BKN Trace 与可观测性:调用事实、Trace 分析、业务溯源、日志与归档8 comments · 2026-08-08#82[agent-retrieval] agent 可发现性/聚合查询能力:query_object_instance 聚合 + run_sql 列级 schema5 comments · 2026-06-27#746test(bkn-trace): BKN Trace 端到端安装部署与持久化验收3 comments · 2026-08-08#2962feat(bkn-project): 0.2.2 modeling flow from sources to concepts to models2 comments · 2026-11-06#2952feat(bkn-project): 0.2.2 knowledge-base flow a knowledge engineer can finish alone2 comments · 2026-11-05#2951feat(bkn-project): 0.2.2 published networks answer with evidence and clean schemas2 comments · 2026-11-05#2950feat(bkn-project): 0.2.2 reliable knowledge-base builds and refresh2 comments · 2026-11-05#724[Bug] 行动类对聚合消息按实例重复执行,且任务列表返回完整 results 导致响应膨胀2 comments · 2026-08-07
Latest release
v0.2.0 v0.2.0 2026-10-16BKN Foundry 0.2.0 Tag v0.2.0 · commit 81d5752 Versioned API documentation · Full changelog Highlights - Row-level authorization and self-service access requests. Row filters apply across object reads, with fixed-condition predicates, policy management, permission guidance and permission-request workflows (1689, 1690, 1696, 1727, 1810, 1831, 1910, 1943). - Compact MCP entry. /mcp-compact/ provides an on-demand gateway, including sandbox execution and schema information from the top search result. Schema and network summaries carry less repeated content (1756, 1776, 1801, 1812, 1849). - Kaf