@DanKornas: Your team’s knowledge shouldn’t be trapped across 50+ apps. Onyx is a knowledge and context layer for teams and AI agen…
Summary
Onyx 推出团队知识与上下文层,通过索引 50+ 应用的内容、元数据与权限,为搜索、研究和 AI 代理响应提供支撑,并提供基于 MIT 许可的免费社区版。
View Cached Full Text
Cached at: 10/10/26, 02:53 PM
Your team’s knowledge shouldn’t be trapped across 50+ apps.
Onyx is a knowledge and context layer for teams and AI agents.
It helps you ground search, research, and agent responses in connected organizational knowledge by indexing content, metadata, and permissions from 50+ applications, then retrieving relevant documents for downstream tasks.
Key features:
• Knowledge indexing – brings content, metadata, and permissions from connected sources into one internal representation • Agentic RAG – combines a hybrid index with a custom agent harness for information retrieval • Deep Research – runs a multi-step flow to produce in-depth reports • Custom agents and actions – create agents with selected knowledge, instructions, and the ability to take external actions • Multiple access points – use the web or desktop app, Slack/Discord bot, MCP server, Chrome extension, or embeddable widget
The Community Edition is available freely under the MIT license.
Link in the reply 👇
Similar Articles
@hasantoxr: Nobody is talking about this. There's an open-source AI platform with 17.3K stars that connects to 40+ of your internal…
Onyx is an open-source AI platform that self-hosts and connects to 40+ internal tools, offering companies a private alternative to ChatGPT Enterprise.
@Cander_zhu: https://x.com/Cander_zhu/status/2077409094567166271
This article introduces how to use AI (Codex and GBrain) to automate the Inbox processing and knowledge flywheel of Obsidian knowledge base, realizing a closed loop from knowledge input, processing, connection to output, and enhancing the vitality of personal knowledge system.
@Pluvio9yte: Tencent quietly open-sourced an enterprise-level knowledge platform, WeKnora. Its core concept is: turning a pile of raw documents into truly usable, inferable, and self-growing knowledge assets. It mainly does three things: RAG intelligent Q&A — fast and accurate ordinary semantic retrieval with support for hybrid search; ReAct autonomous A…
Tencent open-sourced the enterprise knowledge platform WeKnora, featuring three key capabilities: RAG intelligent Q&A, ReAct autonomous Agent, and self-maintaining Wiki + knowledge graph, transforming raw documents into inferable and growing knowledge assets.
@yunxi0623: https://x.com/yunxi0623/status/2068171252595147166
Introduces how to use Obsidian and Claude Code to build a local AI knowledge base, by creating folder structures, writing CLAUDE.md rule files, and step-by-step importing and organizing materials, to achieve long-term portable personal knowledge management.
@BolanHsiao: https://x.com/BolanHsiao/status/2073053624880738610
Introduces the method of combining Obsidian with WorkBuddy to build a second brain, noting that foreign AI tools like Claude and Codex paired with Obsidian present barriers for domestic users.