@effect-uai/elevenlabs

Uai \ wai \. Mineiro Portuguese, all-purpose interjection.

Low-level primitives for building AI agents with Effect.

effect-uai is not a framework. There's no runtime to learn, no orchestrator to override, no graph to fight. You get typed streaming primitives (one turn, one tool call) and compose the loop yourself.

OpenAI Responses, Anthropic, and Gemini wire formats normalize to one TurnEvent union. State is yours. The loop is yours.

Status

While we're in 0.x, minor releases may include breaking changes. Each one ships with a migration guide and the effect-uai-migrate skill encodes the rewrites for Claude Code, so upgrades are mechanical.

Why effect-uai

Most agent libraries decide how your loop works: state shape, retry policy, tool dispatch, cancellation. When you need something they didn't plan for (approval gates, mid-stream cancel, fallback, auto-compaction), you fight the framework.

effect-uai owns the wire (HTTP, SSE, event normalization, validation). You own the policy. They meet at a Stream<TurnEvent> and a plain state record.

Features

• Explicit control. No black-box magic. You stay in full control of your agent loop.
• Built on Effect. Retries, streams, concurrency, errors: handled by Effect, not reinvented.
• Composable primitives. Small building blocks you assemble into your own agentic loops.
• Recipes for the hard parts. Copy-paste solutions for model council, auto-compaction, pause and resume, and more.
• Streaming first. Everything's a stream you can transform, filter, and collect when ready.
• Typed errors. Match RateLimited, Unavailable, or Timeout directly. No string parsing.
• Carry your own state. History, budget, scratchpad. Track whatever your agent needs. It's just a value.

Quick taste

The canonical agent loop: stream a turn, run any tools the model asks for, append the outputs, continue until it stops.

export const conversation = loop(initial, (state) =>
  Effect.gen(function* () {
    const oai = yield* Responses // swap for Anthropic / Gemini any turn
    return oai
      .streamTurn({ history: state.history, model, tools: toolkit }) // stream text, reasoning, tool events
      .pipe(
        onTurnComplete((turn) =>
          Effect.sync(() => {
            const calls = Turn.getToolCalls(turn) // approve, deny, audit, batch (it's your code)
            if (calls.length === 0) return stop() // stop on a final answer, a budget, your call
            return Toolkit.run(toolkit, calls).pipe(
              // run typed Effect tools
              Toolkit.continueWithResults(
                Toolkit.appendToolResults(state, turn), // fold results back into your state
              ),
            )
          }),
        ),
      )
  }),
)

For tools, approvals, multi-turn loops, sandboxes, and cross-provider fallback, see the docs or the recipes.

Packages

Package	What it is
@effect-uai/core	The primitives: Loop, LanguageModel, Tool, Toolkit, Items, Turn, Transcriber, SpeechSynthesizer, EmbeddingModel, MusicGenerator, WebSearch, Sandbox. No provider deps.
@effect-uai/responses	OpenAI Responses provider. Implements LanguageModel over OpenAI's /v1/responses endpoint.
@effect-uai/anthropic	Anthropic Messages provider, including extended thinking.
@effect-uai/google	Google Gemini: language model, embeddings, speech (sync STT + TTS), and Lyria music generation.
@effect-uai/mistral	Mistral: LanguageModel (chat) plus Voxtral speech: realtime + batch STT and TTS. One brand for a full STT to LLM to TTS pipeline.
@effect-uai/openai	OpenAI speech: Transcriber (sync + realtime WS) and Synthesizer (sync + chunked HTTP).
@effect-uai/elevenlabs	ElevenLabs speech: Scribe v2 Realtime STT and Flash v2.5 TTS with incremental-text-in WS.
@effect-uai/inworld	Inworld speech: first-party STT/TTS plus router-style passthroughs (AssemblyAI / Soniox / Groq Whisper).
@effect-uai/jina	Jina embeddings: dense, sparse (ELSER), and multivector (ColBERT-style) variants.
@effect-uai/perplexity	Perplexity web search: fast, current-events snippets for grounding an LLM.
@effect-uai/exa	Exa web search: neural / semantic retrieval ranked by relevance score.
@effect-uai/tavily	Tavily web search: snippets and scores with search-depth control.
@effect-uai/microsandbox	Local Firecracker microVM sandboxes via microsandbox. Run untrusted code in isolation.
@effect-uai/deno	Hosted Firecracker microVM sandboxes on Deno Deploy. No local infra to run.

Each provider is its own package - edge / browser builds only pull in what you actually use.

Repo layout

.
├── packages/
│   ├── core/                  # @effect-uai/core - primitives, no provider deps
│   └── providers/
│       ├── responses/         # @effect-uai/responses - OpenAI Responses
│       ├── anthropic/         # @effect-uai/anthropic
│       ├── google/            # @effect-uai/google - Gemini + speech + Lyria
│       ├── mistral/           # @effect-uai/mistral - LLM + Voxtral speech (STT/TTS)
│       ├── openai/            # @effect-uai/openai - speech (STT/TTS)
│       ├── elevenlabs/        # @effect-uai/elevenlabs - speech
│       ├── inworld/           # @effect-uai/inworld - speech
│       ├── jina/              # @effect-uai/jina - embeddings
│       ├── perplexity/        # @effect-uai/perplexity - web search
│       ├── exa/               # @effect-uai/exa - web search
│       ├── tavily/            # @effect-uai/tavily - web search
│       ├── microsandbox/      # @effect-uai/microsandbox - local sandboxes
│       └── deno/              # @effect-uai/deno - hosted sandboxes
├── recipes/                   # 27 worked recipes (type-checked, tested) covering
│                              # tools, approvals, fallback, voice, sandboxes, …
├── recipes-extras/            # Recipes that need extra infra to run (e.g. sandbox-code-interpreter)
├── docs/                      # Source for the docs site (concepts, recipes, providers)
├── webpage/                   # Astro/Starlight site that renders docs/
└── integration-tests/         # Live-system smoke tests; run manually, not part of CI

A recipe folder typically contains:

• index.ts - the building blocks (tools, state, body), reusable in tests
• run.ts - a runnable demo that wires real providers
• index.test.ts - vitest tests against MockProvider
• README.md - the page that's mirrored in the docs site

Docs / learn

Full docs: https://effect-uai.betalyra.com

Recommended reading order:

1. One turn is a stream - the smallest provider-agnostic primitive.
2. Basic usage - the core agent harness: state, stream, tools, continuation.
3. The loop primitive - what loop is, its shape, and streamUntilComplete.
4. Items and turns - the conversation as a flat list, the assembled turn, the event stream.
5. Tools and toolkits - Tool.make (with progress via emit), Toolkit.make, approval planners, ToolEvent.

Then dip into recipes for whatever pattern you need.

Local development

pnpm install
pnpm test          # vitest run across all workspaces
pnpm typecheck     # tsc --noEmit

To run a recipe end-to-end against real providers:

OPENAI_API_KEY=sk-... pnpm tsx recipes/basic-usage/run.ts

Nix dev shell (optional)

This repo ships a flake.nix that provides a dev shell with the exact toolchain CI uses - Node 24, the pinned pnpm version (via corepack), and Deno for the integration tests. It is 100% optional: if you already have Node and pnpm installed, ignore this entirely and use the commands above.

If you do use Nix with flakes enabled:

nix develop          # drops you into a shell with node, pnpm and deno

The repo also ships an .envrc, so with direnv installed the shell loads automatically when you cd in - just run direnv allow once. Without direnv the file is inert and ignored.

License

MIT - see LICENSE.