conduit
cogwheel0/conduit
Conduit is a native Flutter client for iOS and Android designed to connect with self-hosted Open WebUI servers, direct API endpoints, and Hermes agents.
1.9k 193GPL-3.0Updated 2026-08-10
83
GreatOverview
Conduit bridges the gap for mobile users interacting with self-hosted AI models by providing a robust native client. It supports multiple authentication types (including complex reverse proxies and SSO), offers reliable real-time streaming, local chat persistence via Drift, and rich rendering of markdown, LaTeX, and Mermaid diagrams on mobile devices.
Capabilities
- ▸Real-time token streaming over WebSocket
- ▸Native rendering of code blocks, Mermaid diagrams, and LaTeX
- ▸Multiple connection methods (Open WebUI, Direct API, Hermes Agent)
- ▸Secure credential storage using Keychain and Keystore
- ▸Reverse proxy and SSO authentication support
- ▸Workspace, notes, and local file management
Best for
Connecting to self-hosted Open WebUI instances on mobile devices, Interacting directly with OpenAI-compatible, Ollama, or OpenRouter models, Managing self-hosted Hermes agent workflows and scheduled tasks, Offline note-taking and AI-assisted chat sessions on iOS and Android
Works with
CursorGitHub Copilot
Evoa Score breakdown= Σ (score × weight)
83Task 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%100 → +15.0
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%38 → +4.6
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%80 → +12.0
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%84 → +6.7
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%50 → +2.5
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 total82.8 / 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
Credentials and auth tokens are stored securely using platform secure storage (Keychain/Keystore). Model outputs and webviews should be treated as untrusted data pipelines.
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.