📡 MCP Radar

bybit-exchange/kaas

Turn scattered notes, docs and transcripts into a queryable Markdown wiki — an LLM knowledge-base compiler with MCP access, no embeddings, self-hosted.

82 stars
11 forks
Python
momentum ▲ 186.0
created 2026-07-29
on radar since 2026-07-31
star trend 43 → 82 since 2026-07-31
ai-agentsclaude-codegolangknowledge-baseknowledge-managementllmmarkdownmcpmodel-context-protocolopenai-apipersonal-knowledge-managementpythonragreactsecond-brainself-hostedsqlitetypescriptwiki
View on GitHub ↗Homepage ↗

About kaas

Turn scattered notes, documents, and transcripts into a searchable, queryable personal Wiki — powered by LLM-driven knowledge compilation.

KaaS started as an internal tool. Our knowledge lived scattered across documents, meetings, and email — and every time someone changed roles or left, the context they'd built up walked out with them. New people spent weeks piecing it back together.

A distillation pipeline fixed that. It compiles each person's scattered material into a wiki tied to their role rather than their identity — so when someone moves on, the raw data goes but the distilled judgment stays for whoever fills the seat next.

The payoff is the same either way: the organization stops re-answering the same questions. That's what convinced us it was worth open-sourcing.

Unlike typical RAG systems that chunk and embed raw text, KaaS compiles your content through a 4-phase LLM pipeline:

The result is human-readable Markdown articles — not a black-box vector store. You can read, edit, and git-manage your knowledge base.

Already living in a coding agent (Claude Code, Codex, openclaw, …)? Skip Docker. Copy this and paste it to your agent — it will install kb-ai, ask what to distill, build the wiki, and wire up MCP so you can query it in any later session:

Prefer a web UI, or want the full backend? Use the Docker path below.

KaaS calls LLMs through any OpenAI-compatible API (OpenAI, DeepSeek, Ollama, vLLM, Azure OpenAI, etc.). Pick either method below:

From the project README.

Maintaining this server?

Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:

[![On MCP Radar](https://mcp.liqiwa.com/badge.svg)](https://mcp.liqiwa.com/s/bybit-exchange--kaas.html)

Related MCP servers

rwnalds/engram

Self-hosted MCP server + dashboard giving Claude Code, Cursor & Hermes agents shared long-term memory over a git-backed markdown vault. Agent-native, Obsidian-compatible second brain — markdown RAG, n

⭐ 4TypeScript
docouno/notarium

File-first knowledge base for humans and AI agents — self-hosted Markdown notes with a web editor and a built-in MCP server.

⭐ 3TypeScript
vinodborole/okf-kit

Turn any website into a portable, agent-ready Open Knowledge Format (OKF) bundle — no LLM required. Crawl, sync, chat offline, and serve docs to coding agents over MCP.

⭐ 5Python
do-md/homekb

Local-first personal Markdown knowledge base with semantic search, AI Q&A, MCP, desktop/web clients, and a self-hostable zero-data-at-rest relay.

⭐ 6TypeScript
ozankasikci/global-agent-memory

Local-first, project-aware memory MCP server for Claude Code, Codex, and other AI agents, with Obsidian and an owner dashboard.

⭐ 11Python
FaramarzKowsari/ai-api-playbook

Companion source code for AI APIs in Practice, a visual engineering book on multimodal AI, agents, RAG, evaluation, governance, and production-ready products. Book DOI: 10.5281/zenodo.21431944 · Softw

⭐ 4Python

📬 Get the weekly radar in your inbox

The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.