Self-hosted AI agents.
The self-hosted AI agents we follow, with GitHub stars and the CVEs NIST NVD lists for each, refreshed every 6 hours from GitHub, NVD and CISA KEV.
By GitHub stars
Self-hosted AI agent at the centre of the January 2026 security crisis. Its tool sandbox is off by default: the main session's tools run on the host until you configure one.
Agent from Nous Research (MIT, Python). Runs shell commands on the host by default, with an approval step for dangerous ones; Docker and cloud sandboxes are options. Works with many LLM providers.
Personal AI agent in Python (MIT) with a browser UI and chat apps. Native Anthropic, OpenAI and OpenRouter providers plus local servers; its shell sandbox is off until you switch it on.
Single Rust binary from ZeroClaw Labs, MIT or Apache-2.0. Works with Anthropic, OpenAI, Ollama and about twenty other providers, and turns on an OS sandbox it detects.
Small TypeScript agent (MIT) built on Anthropic's Claude Agent SDK. Every agent runs in its own Docker container, on macOS, Linux or Windows through WSL2.
Rust agent from NEAR AI, MIT or Apache-2.0. Untrusted tools run in a WebAssembly sandbox with declared capabilities, and secrets are injected outside them.
Cloudflare's experimental package that runs OpenClaw inside a Cloudflare Sandbox container behind a Worker. Needs the Workers Paid plan.
Managed assistant built on OpenClaw, in Telegram and Discord: $20 a month self-serve, or $100 with setup and a monthly call. AI credits included.
Managed OpenClaw hosting, live on Telegram (Discord and WhatsApp "Soon"). $19 or $49 a month, $14 or $37 billed yearly. Your own model API key.
Managed OpenClaw hosting for Telegram, Discord and WhatsApp. No free plan: $20, $49 or $200 a month, with model usage bought separately as credits.
Stats refreshed every 6 hours from GitHub API + NVD CVE feed + CISA KEV. See our methodology for the full pipeline.