WebAssembly

<!-- Project Info -->
<a href="https://github.com/kreuzberg-dev/liter-llm/blob/main/LICENSE">
	<img src="https://img.shields.io/badge/License-MIT-007ec6" alt="License" />
</a>
<a href="https://docs.liter-llm.kreuzberg.dev">
	<img src="https://img.shields.io/badge/Docs-liter--llm-007ec6" alt="Docs" />
</a>

Universal LLM API client for browsers and WebAssembly runtimes. Access 143 LLM providers with portable deployment across browsers, Deno, and Cloudflare Workers.

What This Package Provides

• One provider surface — chat, streaming, embeddings, images, audio, search, OCR, tools, and structured output across the provider registry.
• Provider/model routing — call models with the provider/model convention and keep provider-specific request code out of application paths.
• Production controls — retries, fallback, rate limits, cache layers, budgets, health checks, OpenTelemetry spans, and redacted secrets.
• Same core as every binding — Rust, Python, Node.js, Go, Java, PHP, Ruby, .NET, Elixir, WASM, Kotlin Android, Swift, Dart, Zig, and C FFI use the same Rust implementation.
• WASM package — browser and edge-compatible client for provider calls from WebAssembly runtimes.

Installation

Package Installation

Install via one of the supported package managers:

npm:

npm install @kreuzberg/liter-llm-wasm

pnpm:

pnpm add @kreuzberg/liter-llm-wasm

yarn:

yarn add @kreuzberg/liter-llm-wasm

System Requirements

• Modern browser with WebAssembly support, or Deno 1.0+, or Cloudflare Workers
• API keys via environment variables or runtime configuration

Quick Start

Basic Chat

Send a message to any provider using the provider/model prefix:

import init, { createClient, WasmChatCompletionRequest } from "@kreuzberg/liter-llm-wasm";

await init();

const client = createClient(process.env.OPENAI_API_KEY!);

const request = WasmChatCompletionRequest.default();
request.model = "openai/gpt-4o";
request.messages = [{ role: "user", content: "Hello!" }];

const response = await client.chat(request);
console.log(response.choices[0].message.content);

Common Use Cases

Streaming Responses

Stream tokens in real time:

import init, { createClient, WasmChatCompletionRequest } from "@kreuzberg/liter-llm-wasm";

await init();

const client = createClient(process.env.OPENAI_API_KEY!);

const request = WasmChatCompletionRequest.default();
request.model = "openai/gpt-4o";
request.messages = [{ role: "user", content: "Tell me a story" }];
request.stream = true;

const stream = await client.chatStream(request);
while (true) {
  const chunk = await stream.next();
  if (chunk === null) {
    break;
  }
  process.stdout.write(chunk.choices?.[0]?.delta?.content ?? "");
}
console.log();

Next Steps

• Provider Registry - Full list of supported providers
• GitHub Repository - Source, issues, and discussions

Features

Supported Providers (143)

Route to any provider using the provider/model prefix convention:

| Provider | Example Model | | ------------------ | ------------------------------------------------------------- | | OpenAI | openai/gpt-4o, openai/gpt-4o-mini | | Anthropic | anthropic/claude-3-5-sonnet-20241022 | | Groq | groq/llama-3.1-70b-versatile | | Mistral | mistral/mistral-large-latest | | Cohere | cohere/command-r-plus | | Together AI | together/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | | Fireworks | fireworks/accounts/fireworks/models/llama-v3p1-70b-instruct | | Google Vertex | vertexai/gemini-1.5-pro | | Amazon Bedrock | bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0 |

Complete Provider List

Key Capabilities

• Provider Routing -- Single client for 143 LLM providers via provider/model prefix
• Local LLMs — Connect to locally-hosted models via Ollama, LM Studio, vLLM, llama.cpp, and other local inference servers
• Unified API -- Consistent chat, chat_stream, embeddings, list_models interface
• Streaming -- Real-time token streaming via chat_stream
• Tool Calling -- Function calling and tool use across all supporting providers
• Type Safe -- Schema-driven types compiled from JSON schemas
• Secure -- API keys never logged or serialized, managed via environment variables
• Observability -- Built-in OpenTelemetry with GenAI semantic conventions
• Error Handling -- Structured errors with provider context and retry hints

Performance

Built on a compiled Rust core for speed and safety:

• Provider resolution at client construction -- zero per-request overhead
• Configurable timeouts and connection pooling
• Zero-copy streaming with SSE and AWS EventStream support
• API keys wrapped in secure memory, zeroed on drop

Provider Routing

Route to 143 providers using the provider/model prefix convention:

openai/gpt-4o
anthropic/claude-3-5-sonnet-20241022
groq/llama-3.1-70b-versatile
mistral/mistral-large-latest

See the provider registry for the full list.

Proxy, MCP Server & Plugin

Beyond the SDK, the liter-llm CLI ships an OpenAI-compatible proxy and a Model Context Protocol (MCP) server:

brew install kreuzberg-dev/tap/liter-llm   # or: cargo install liter-llm-cli
liter-llm api --config liter-llm-proxy.toml   # OpenAI-compatible proxy
liter-llm mcp --transport stdio               # MCP tool server

# or run the proxy without installing:
docker run -p 4000:4000 -e LITER_LLM_MASTER_KEY=sk-your-key ghcr.io/kreuzberg-dev/liter-llm

To use the MCP server inside a coding agent, install the liter-llm plugin from the kreuzberg-dev/plugins marketplace — it auto-registers the server. See the MCP server and proxy server guides for configuration, CLI usage, and agent integration.

Documentation

• Documentation -- Full docs and API reference
• GitHub Repository -- Source, issues, and discussions
• Provider Registry -- 143 supported providers

Part of Kreuzberg.dev

• Kreuzberg — document intelligence: text, tables, metadata from 91+ formats with optional OCR.
• Kreuzberg Cloud — managed extraction API with SDKs, dashboards, and observability.
• kreuzcrawl — web crawling and scraping with HTML→Markdown and headless-Chrome fallback.
• html-to-markdown — fast, lossless HTML→Markdown engine.
• liter-llm — universal LLM API client with native bindings for 14 languages and 143 providers.
• tree-sitter-language-pack — tree-sitter grammars and code-intelligence primitives.
• alef — the polyglot binding generator that produces every per-language binding across the 5 polyglot repos.
• Discord — community, roadmap, announcements.

Contributing

Contributions are welcome! See CONTRIBUTING.md for guidelines.

Join our Discord community for questions and discussion.

License

MIT -- see LICENSE for details.