What Tablif read on KYB - Shared Memory for AI Agents's site
KYB - Shared Memory for AI Agents describes itself as: “KYB - Shared Memory for AI Agents”
- Stage: Live, no waitlist
- How it differs: “KYB is not an MCP alternative — it speaks Model Context Protocol natively.”
What it is
Calls itself “shared memory”.
- Calls itself: shared memory
“…shared memory”
Where it puts itself
Its one line of difference: “KYB is not an MCP alternative — it speaks Model Context Protocol natively.”
“KYB is not an MCP alternative — it speaks Model Context Protocol natively.”
What it costs
No free plan.
- Free plan: no
“Open source · Rust · MIT”
Who it sells to
Sells to developers.
- Sells to: developers
“Give Claude Code, Codex and other agents one shared knowledge base.”
How it runs
A API and command-line tool for Linux and macOS. Runs locally and works offline. Can be self-hosted. Offers an API. Open source. AI is the core of the product. Built with Google Analytics.
- Kind: api · cli
- Runs on: Linux · macOS
- Runs where: on the device, offline · self-hosted
- API: yes
- Open source: yes
- AI role: core to the product
- Analytics: Google Analytics
“Self-hosted, open source, with a CLI and MCP interface.”
“Docker”
What it works with
Names Antigravity, Claude Code and 4 more on its pages.
- Names: Antigravity · Claude Code · Codex · +3
“Multiple agents — Claude Code, Codex, Antigravity — on multiple machines rediscover the same infrastructure over and over”
“Give Claude Code, Codex and other agents one shared knowledge base.”
What it offers as proof
Live, no waitlist. Publishes a blog.
“Open source · Rust · MIT · kybmemory.com”
“Blog -> https://kybmemory.com/blog/”
Sources
Tablif read these pages, last on 13 Oct 2026. Everything above is what the product says about itself; Tablif does not verify every claim.
Similar products in Tablif Town
- Kepos : Shared memory for teams and their AI agents
- Kumiho Memory: Shared memory for agent teams, with the why intact
- Zekra: Long-term memory for AI agents, over MCP
- ResumeContext: Shared memory for coding agents.
- kadence: Shared memory for coding agents, kept in your git repo
- Agent Memory: Your AI forgets. AgentMemory doesn’t.
- Context Hub: Long-term memory and shared context for your AI agents.
- AI Context Flow: Universal AI memory and prompt optimization