pi-fabric
MCP Servermonotykamary/pi-fabric
Pi-fabric provides a programmable tool and agent runtime for Pi, allowing language models to execute complex workflows and tool calls via type-checked TypeScript code.
98 12MITUpdated 2026-08-13
77
GreatOverview
Pi-fabric streamlines agent-human interactions by consolidating multiple tool calls, MCP servers, and agent routines into a single programmable execution environment called `fabric_exec`. Running securely in a QuickJS sandbox by default, the agent writes concise TypeScript programs to handle looping, branching, and data flow, returning only the final results to the primary conversation context.
Capabilities
- ▸TypeScript-based code mode for LLM tool execution
- ▸Capability routing for core tools, MCP, and extensions
- ▸Multi-agent orchestration, actors, and councils
- ▸Durable workflows and mesh coordination
- ▸QuickJS sandboxing with unsafe Node-process fallback
- ▸Live TUI dashboard, topology viewer, and activity widgets
Best for
Executing parallel code audits, migrations, and research tasks, Managing multi-agent swarms, councils, and persistent actors, Running long-horizon tasks and background supervisors, Complex workflow orchestration across MCP servers and core tools
Works with
Claude CodeCursorGitHub Copilot
Evoa Score breakdown= Σ (score × weight)
77Task 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%30 → +3.6
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%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%95 → +9.5
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%52 → +4.2
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%75 → +3.8
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 total77.0 / 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
Executes LLM-generated TypeScript programs inside a QuickJS sandbox by default, with an optional unsafe Node-process executor for trusted workloads.
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.