I built an open-source AI control plane with 26K+ MCP servers and persistent memory tiers (TormentNexus)
Summary
A developer built an open-source AI control plane called TormentNexus that integrates over 26,000 MCP servers and supports persistent memory tiers.
Similar Articles
I got tired of re-explaining my project to every AI tool, so I built a local memory layer for them
The author built mem-port, a local MCP server that gives AI copilots (ChatGPT, Claude Code, Cursor, Windsurf) shared long-term memory via embedded SurrealDB, solving context drift between AI tools.
I built an open-source MCP server that gives AI agents persistent memory for videos
A developer introduces Watch Skill, an open-source MCP server that gives AI agents persistent memory for videos by creating local indexes of transcripts, OCR, and visual observations for efficient retrieval.
I built an open-source platform for creating and managing AI agents (MIT licensed, free to self-host)
The author built an open-source, MIT-licensed platform for creating and managing AI agents, featuring provider-agnostic support, MCP integration, memory, skills, scheduled triggers, and Kanban boards, deployable via Docker Compose.
I gave my AI agents a shared memory via MCP — here's how
Nexus Memory is an MCP-native memory server that allows AI agents to share context via a unified protocol, enabling persistent and coordinated memory across different agents without custom integration.
I built a free open-source HQ to run OpenCode agents as a team (MCP)
The author created Cognitive Lead HQ, a free open-source tool for coordinating multiple AI agents with structured workflows, FastMCP servers, and reusable skills.