frona
fronalabs/frona
Frona is a self-hosted personal AI assistant platform built in Rust that lets you create autonomous agents with sandboxed code execution, web browsing, and credential management.
198 20No licenseUpdated 2026-07-10
66
GoodOverview
Frona provides a secure, self-hosted platform for deploying autonomous AI agents that can execute shell commands, manage files, browse the web, and connect to various messaging channels. It features a robust policy engine, per-principal sandboxing, secure credential vaults, and Model Context Protocol (MCP) support, all packed into a single-container deployment.
Capabilities
- ▸Autonomous multi-step task execution
- ▸Per-principal sandboxed Linux process isolation
- ▸Credential management with vault integration
- ▸Model Context Protocol (MCP) server support with bridge mode
- ▸Headless browser automation and web search
- ▸Cross-conversation persistent memory and context spaces
Best for
Building and deploying web applications autonomously, Running scheduled monitoring and background tasks via cron, Performing secure web research and browser automation, Delegating multi-step tasks across specialized agent networks
Works with
CursorClaude CodeCodexChatGPTGemini CLIGitHub CopilotOpenCode
Evoa Score breakdown= Σ (score × weight)
66Task usefulness20%100 → +20.0
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%85 → +12.8
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%49 → +5.9
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%50 → +7.5
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%85 → +8.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%59 → +4.7
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%100 → +5.0
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total77.8 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Frona implements strict per-principal sandboxing, policy-driven syscall filtering, a secure credential vault, and dual LLM dispatch to isolate untrusted inbound messages and limit potential blast radiuses.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.