kaas
Active·★ 151·MIT·Updated 2026-09-11
KaaS transforms disparate information sources like notes and documents into a structured, searchable personal wiki using a unique LLM-driven compilation pipeline. Unlike traditional RAG systems, it generates human-readable Markdown articles, making knowledge bases editable and Git-manageable, and also offers integration with AI coding agents.
#Knowledge Management#LLM Compilation#Personal Wiki#Information Retrieval#AI Agent Integration#Markdown Output#RAG System
01
Features
014-Phase Compile Pipeline
02Streaming Chat with Citations
03Multiple Input Sources
04Incremental Compilation
05Git-Friendly Markdown Output
02
Compatibility
Python
AI Engine
Verified via docs
Go
Backend
Verified via docs
Docker
Deployment
Verified via docs
Linux
OS
Verified via docs
macOS
OS
Verified via docs
OpenAI-compatible API
LLM Integration
Verified via docs
03
Quick start
1
$ curl -fsSL https://raw.githubusercontent.com/bybit-exchange/kaas/main/install.sh | sh
04
Use cases
↳Compiling scattered internal company knowledge into a central, queryable wiki.
↳Retaining institutional knowledge when team members change roles or leave.
↳Providing AI agents with a structured, grounded knowledge base for better context and answers.
↳Creating a personal or team knowledge base from various document types (notes, transcripts, docs).
05
Alternatives
salt.md★ 166
The open-source workspace for people and AI agents. Docs, databases and realtime collaboration with an MCP server in the same binary, so agents work in the same workspace on the same permissions. One Go binary, one SQLite file, self-hosted.
obsidian-everywhere★ 16
Graph + local semantic context for Obsidian, with guarded remote MCP access and edits from Codex, ChatGPT, Claude, and any MCP client.
AgenticRAG-Survey★ 1.7k
Agentic-RAG explores advanced Retrieval-Augmented Generation systems enhanced with AI LLM agents.
pipeshub-ai★ 3.8k
The open-source context layer for AI agents. PipesHub turns your company's knowledge (Slack, Drive, Jira, GitHub, Microsoft 365 and 40+ connectors) into a permission-aware workspace that agents can search, grep, navigate and cite. MCP, SDKs and built-in agents. Self-hosted.
atlas-mcp-server★ 477
A Model Context Protocol (MCP) server for ATLAS, a Neo4j-powered task management system for LLM Agents - implementing a three-tier architecture (Projects, Tasks, Knowledge) to manage complex workflows. Now with Deep Research.
Comments
Log in to leave a comment
No comments yet. Be the first!