Show HN: Nerve – self hosted runtime for AI agents
Nerve is a self-hosted runtime designed for AI agents, enabling personal assistants and autonomous workers. It features persistent memory, task management, and the ability to communicate through various channels. Users can deploy agents that evolve over time, manage tasks, and require human approval for actions.
- ▪Nerve is built around the Claude Agent SDK and offers a setup guide for users.
- ▪The platform supports two modes: Personal Mode for individual assistants and Worker Mode for task-focused agents.
- ▪Agents can remember user preferences, develop personalities, and autonomously manage tasks with human oversight.
Opening excerpt (first ~120 words) tap to expand
Nerve A home for your agents. Self-hosted AI agent runtime — personal assistants, autonomous workers, and everything in between. Setup Guide · Architecture · Configuration · Worker Guide · API Reference Nerve is a self-hosted runtime for AI agents, built around the Claude Agent SDK. It gives agents everything they need to be useful long-term: persistent memory, scheduled execution, task management, learnable skills, and channels to reach you through — web UI, Telegram, or autonomous cron jobs. Ship a personal assistant that develops a personality, remembers your preferences, and manages your inbox. Or deploy a worker agent that monitors your CI, reviews PRs, and fixes flaky tests — all plan-driven with human approval. Same engine, different mission.
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at GitHub.