HN Showcase
Back to browse
Ryvos – Autonomous AI assistant in Rust(15MB RAM,50 tools,16 providers)

Ryvos – Autonomous AI assistant in Rust(15MB RAM,50 tools,16 providers)

by aayush-mishraaa·Feb 26, 2026·2 points·0 comments
Visit ProjectView on HN

AI Analysis

●●●BangerWizardryShip ItSolve My Problem

SecurityGate + sandboxed Lua/Rhai execution makes this safer than Claude or Continue for untrusted tools.

Strengths
  • •5-tier SecurityGate with regex pattern detection (rm -rf, DROP TABLE, curl|bash) blocks catastrophic AI mistakes before execution
  • •Legit multi-channel (Telegram, Discord, Slack, web, CLI) with single 20MB binary and 15–30MB RAM footprint—actually runs everywhere
  • •MCP-native + drop-in Lua/Rhai skills without system code exposure; genuine architectural choice that mitigates the real risk everyone ignores
Weaknesses
  • •No evidence of red-team testing or CVE disclosure policy; security claims need independent validation beyond regex patterns
  • •Community adoption unclear—GitHub stars, production users, or case studies would validate the 'secured by default' positioning
Target Audience

Developers building AI agents, teams running autonomous systems, security-conscious engineers

Similar To

Claude Desktop · Continue.dev · Ollama with tooling

Post Description

Hi HN,

I've been building Ryvos for the past few months — an open-source autonomous AI assistant written in Rust. It's the thing I wished existed: always-on, multi-channel, and actually secure.

The core idea: every tool call passes through a SecurityGate — 5 tiers of classification, 9 dangerous pattern regexes (rm -rf, DROP TABLE, curl|bash, etc.), Docker sandboxing, and human-in-the-loop approval for anything risky. Skills run in Lua/Rhai sandboxes, not raw system code. We've all seen what happens when AI assistants run community code without any vetting.

What it does: - Talk to it on Telegram, Discord, Slack, web dashboard, or terminal - 50 built-in tools (shell, file I/O, web search, grep, edit, browser...) - 16 LLM providers (Anthropic, OpenAI, Ollama, Groq, Gemini, Azure, Cohere, Mistral...) - MCP-native (stdio + SSE/Streamable HTTP) - Drop-in skills in Lua/Rhai with sandboxed execution - Ships as a single ~20MB static binary - 15-30MB RAM idle

Quick install: curl -fsSL https://raw.githubusercontent.com/Ryvos/ryvos/main/install.s... | sh

I'm a solo founder, built the entire 10-crate Rust workspace myself. Would love feedback — especially from people who've tried running personal AI assistants and hit security or performance walls.

GitHub: https://github.com/Ryvos/ryvos Website: https://ryvos.dev

Similar Projects