Self-hosted AI agents.
Every meaningful self-hosted AI agent in 2026 — stars, releases, open CVEs, AI security verdict. Refreshed every 6 hours from GitHub + NVD + CISA KEV.
By star count
The original viral self-hosted AI agent. Post-crisis 2026.4 line is genuinely safer; pre-2026.3 is genuinely dangerous.
4,000-line Python agent designed to be auditable in an afternoon. Trust through verification.
Post-OpenClaw safe default. Docker-sandboxed by default, multi-LLM, opinionated. The agent we'd hand a colleague today.
Privacy-first. Local LLMs only. Network egress denied at iptables. AGPL-3.0.
macOS-only opinionated fork. Apple containers + Claude. Sub-second boot.
Self-hosted AI agent on Cloudflare Workers. Free at low volume. Workers runtime constraints apply.
Stripped-down ZeroClaw fork for resource-constrained hosts. Phi-3 mini default, runs comfortably on a Pi 5.
Enterprise zero-trust agent. gVisor + audit logs + RBAC + SAML. $750/seat/year.
First managed-Hermes-Agent service. $19/month for a hosted Hermes deployment with dashboard, SSO and CVE monitoring.
Managed self-hosted-AI hosting service starting at $20/month. Bundled AI credits. White-glove setup tier at $100/month.
Managed multi-channel hosting from $19/month. "Deploy in 60 seconds" pitch — Telegram, Discord, WhatsApp.
Self-serve managed agent deployment. Free tier (1 agent, 50 messages/day) + paid tiers from $9/month.
Stats refreshed continuously from GitHub API + NVD CVE feed + CISA KEV. See our methodology for the full pipeline.