agent-squad-swift

2FastLabs · Данни и AIЕзик на описанието

Use when building or modifying a Swift app that uses the AgentSquad Swift framework — on-device multi-agent orchestration for iOS 16+ / macOS 14+: orchestrator, agents (Agent, GroundedAgent), classifier routing, LLM clients (OpenAI-compatible), tools (native + MCP), tool UIs/widgets, on-device stora

Оригинален текст · няма потвърден превод на български

Платформи: Не са посочениНиво: Не е посоченоВ индекса: 21.09.2026 г.Обновен в GitHub: 18.09.2026 г.

Теми: agentic-ai · agents · ai-agents · ai-agents-framework · anthropic · anthropic-claude · aws · aws-bedrock · aws-cdk · aws-lambda · chatbot · framework · generative-ai · machine-learning · openai

Първо прочетете инструкцията.

Файлът се зарежда от посочения източник само по ваше действие. Можете да го прочетете тук, да го копирате или да го запазите като .md.

Оригинален SKILL.md

GitHub хранилище

Звезди на репото: 7766
Лиценз: Apache-2.0
Последна проверка на записа: 21.09.2026 г.

Добавете в своя инструмент.

Командата отваря избора на skills от репозитория. Прочетете файла и условията на автора преди изпълнение.

npx skills add 2FastLabs/agent-squad

Страницата копира текст. Не инсталира и не изпълнява нищо на устройството ви.

Откъс от SKILL.md

Началото на файла на автора, без превод.

AgentSquad Swift — assistant guide

Protocol-driven, on-device multi-agent framework (Swift 6.2, iOS 16+ / macOS 14+; persistence via FileChatStorage on iOS 16+, DeviceChatStorage on iOS 17+). This is guidance and a map — not an API reference. Read the exact signatures from the source (swift/Sources/AgentSquad/) and the worked recipes from the docs site sources (docs/src/content/docs/swift/); this file tells you what to use, when, and what to watch out for.

When to use what

One assistant → an Agent (or GroundedAgent) + an Orchestrator with no classifier. No routing hop.
Several specialists → multiple agents + an LLMClassifier; the orchestrator routes each turn.
Answers must not drift from data (prices, stock, balances) → GroundedAgent: a Brain calls tools, an isolated Presenter speaks only from the curated results (it can be a smaller/local model).
Voice → a VoiceAssistant (a peer of the orchestrator, not an agent): OpenAIVoiceAssistant (single LLM + tools, speaks directly — the spoken analog of Agent) or OpenAIGroundedVoiceAssistant (Brain → Presenter, can't drift from data — analog of GroundedAgent).

Every component is a Sendable protocol with one built-in implementation — swap in your own anywhere.

Modules (import only what you use)

Import	Pulls in	Contents
`AgentSquad`	nothing external	protocols, `Agent`, `GroundedAgent`, `Orchestrator`, `LLMClassifier`, `ChatCompletionsClient`, `DakeraRetriever`, `FileChatStorage`, `DeviceChatStorage`, `InMemoryChatStorage`, `TransformingChatStorage`, `SummarizingChatStorage`, `OSLogTracer`, OTLP export
`AgentSquadMCP`	MCP Swift SDK	`MCPServer` (= `MCPToolProvider`), `SDKMCPClient`
`AgentSquadAudio`	AVFoundation	`VoiceProcessedAudioIO` (capture+playback, one engine, AEC — the recommended wiring), `MicCapture` (voice-processed/AEC by default), `AudioPlayback`, `VoiceProcessing`, `AudioSessionPolicy` (needs `NSMicrophoneUsageDescription`)

SwiftPM: .package(url: "https://github.com/2FastLabs/agent-squad", branch: "main").

How a turn works

Two peer runtimes share contracts but not a control loop: a turn-based Orchestrator (classify? → run agent → stream → persist) and a long-lived VoiceAssistant for voice. Either way you consume an AsyncThrowingStream<AgentEvent, any Error> — the one idiom worth memorizing:

Целият SKILL.md в GitHub