tankwork
AgentTankOS/tankwork
TankWork is an open-source desktop agent framework that enables AI to perceive and control your computer via computer vision and system-level interactions. It supports voice and text commands, real-time screen analysis, and customizable AI personalities.
98 19MITUpdated 2025-01-17
54
FairOverview
Designed for developers and researchers, TankWork integrates advanced computer vision, voice processing via ElevenLabs, and system-level control to create autonomous desktop agents. It features distinct operational modes including Computer Use for direct command execution and Assistant Mode for real-time visual analysis and feedback, powered by configurable multi-modal models.
Capabilities
- ▸Computer screen perception and real-time vision analysis
- ▸Direct computer control and operating system task execution
- ▸Voice interaction and intent recognition via ElevenLabs
- ▸Configurable multi-agent personalities and specialized skill routing
- ▸Continuous audio-visual feedback and action logging
Best for
Executing direct operating system tasks and browsing via natural language voice or text commands, Performing real-time screen analysis and market or crypto ticker evaluation using specialized AI agents, Building and customizing distinct voice-enabled AI assistants with tailored personalities and skills
Evoa Score breakdown= Σ (score × weight)
54Task usefulness20%88 → +17.6
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%80 → +12.0
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%25 → +3.8
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%45 → +5.4
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%15 → +2.3
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%53 → +4.2
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%0 → +0.0
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 total53.7 / 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
Granting an AI framework direct computer control and system-level interaction capabilities poses inherent security risks regarding automated execution of unintended or malicious commands. Proper sandboxing and monitoring of API keys and agent permissions are strongly advised.
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.