parallelclaw
Local-first personal AI ops layer. Shared verbatim memory across your agents (Claude Code, Cursor, OpenClaw, Hermes, Obsidian, Telegram) in one SQLite + FTS5 c…
AI & MLnpx -y parallelclaw{
"mcpServers": {
"parallelclaw": {
"command": "npx",
"args": [
"-y",
"parallelclaw"
]
}
}
}parallelclaw is a community MCP server that connects AI assistants like Claude to local-first personal ai ops layer. shared verbatim memory across your agents (claude code, cursor, openclaw, hermes, obsidian, telegram) in one sqlite + fts5 c…. It runs locally on your machine, keeping your data private and giving you full control over the connection. AI engineers can use it to chain models and pipelines into more powerful workflows.
About parallelclaw
Overview
Local-first personal AI ops layer. Shared verbatim memory across your agents (Claude Code, Cursor, OpenClaw, Hermes, Obsidian, Telegram) in one SQLite + FTS5 corpus — plus a coordination layer where any of your agents can delegate tasks to any other. Sear
Links
Topics
mcp, mcp-server, claude, claude-code, claude-cowork, cursor, parallelclaw, memex, memory, ai-memory, agent-coordination, agent-orchestration, personal-ai-ops, agent-delegation, local-first, verbatim, chat-archive, fts5, sqlite, telegram, openclaw, hermes
Who Should Use parallelclaw?
- 1Chain AI models and pipelines through a unified MCP interface
- 2Let Claude orchestrate other AI tools and models
- 3Integrate embeddings, image generation, or speech APIs into your workflow
- 4Build multi-model workflows without writing custom integration code
How to Install parallelclaw
Before you start
You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.
- 1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
- 2Paste the install command above and press Enter — Node.js will download and run the server automatically.
- 3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.
The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.