The best library to work with LLMs
Anthropic (Claude) LlmClient adapter for slowcook — implements the core LlmClient interface, provider-specific pricing, and Anthropic-tuned system prompts + tool defs for refine / testgen / brew / sift / investigate agents
Shared helpers for warehouse MCP servers, recipes, and forged apps. Includes the cost-wrapped llmClient() that every emitted app MUST use per ADRs 0007 + 0010.
OpenAI-compatible LLMClient implementation for OpenExpertise — wraps any OpenAI-API endpoint (OpenAI, Azure, self-hosted).
Agent runtime + CLI. Library exports AgentSession, AgentStrategy, ToolRegistry, LlmClient, MetricsCollector, SandboxObserver. Ships an `agent` binary with NDJSON output, --json stdin, --dry-run, schema introspection, and inverse-mode MCP serve. Domain-agn
On-device LLM engine. Wraps @huggingface/transformers + ONNX Runtime Web behind a narrow Engine surface. Presets ship Gemma 4 (E2B/E4B) configurations. Adapters in subpaths satisfy @inbrowser/relay's InferenceProvider and @inbrowser/agent's LlmClient so a
Dazzle SDK for React Native — embedded in-process database with HNSW vector search and a ChatAgent runtime for on-device LLM agents. Includes five swappable LLMClient adapters (LlamaCpp, LiteRT-LM, FoundationModels, OpenAI-compatible, Anthropic). Same lib
A TypeScript library for LLM clients
AI runtime for agent-driven products — agents, memory, LLM providers (Inference Snaps, Ollama, OpenAI-compatible), tools, and orchestration. Anthropic-SDK-free.
The **[Portkey provider](https://sdk.vercel.ai/providers/community-providers/portkey)** for the [Vercel AI SDK](https://sdk.vercel.ai/docs) contains language model support for the Portkey chat and completion APIs.
BlockRun SDK - Pay-per-request AI (LLM, Image, Video, Music, Voice) via x402 on Base and Solana
Provider-agnostic LLM client for the Murmuration Harness — SecretValue auth, per-call cost hook, pluggable ProviderRegistry (ADR-0025).
Core functionality for AI Repo Adventures
Core types and LLM client for AgenticFORGE
Unified LLM API client for Epic Flow with multi-provider support
Software factory capabilities for the [Substrate](https://github.com/johnplanow/substrate) platform — the graph execution engine, scenario-based validation, convergence loops, digital twin orchestration, LLM client with middleware, and pipeline template l
Framework-agnostic server primitives for agent-remote.
AI-driven VSCode extension E2E testing framework — YAML test plans + Playwright + LLM verification
LICOS Dev SDK for server-side model capability calls
Personal Data Hub — UnifiedSchema + validators + KG ingest helpers for the data-back-to-the-individual middleware
Anthropic Claude client used by vctools — structured output via tool_use.
A unified LLM client with multi-provider support, concurrency control, priority queuing, and comprehensive token tracking.
Send requests to multiple LLMs concurrently
Cost-tracking middleware for @diabolicallabs/llm-client. Async fire-and-forget ingestion to Agent Spend Dashboard. © Diabolical Labs
Rust LLM client - Gemini, OpenAI, Claude, Mistral, DeepSeek, Groq
Unified Rust SDK for LLM APIs: Tongyi, DeepSeek, Wenxin, Hunyuan, GLM, Volcengine, OpenAI, Claude, Gemini, Mistral
A lightweight agent SDK for Rust: build tool-using LLM agents that run on any provider.
Get structured, validated data out of LLMs as native Rust structs and enums. Derive a type and rstructor generates the JSON Schema, prompts the model, parses the reply, and retries on validation errors — across OpenAI, Anthropic Claude, Google Gemini, and xAI Grok. The Rust answer to Python's Pydantic + Instructor.
Next-generation Rust library for LLM protocol abstraction with native multi-modal support. Supports 12+ providers (OpenAI, Anthropic, Google, Aliyun, Zhipu, Ollama, Tencent, Volcengine, LongCat, Moonshot, DeepSeek, Xiaomi) with clean Protocol/Provider separation, type-safe interface, and universal streaming.
deepwiki-rs(also known as Litho) is a high-performance automatic generation engine for C4 architecture documentation, developed using Rust. It can intelligently analyze project structures, identify core components, parse dependency relationships, and leverage large language models (LLMs) to automatically generate professional architecture documentation.
Standalone ReAct agent loop — LlmClient + Engine with no platform dependencies
Rust SDK for Chinese LLM APIs including Tongyi, DeepSeek, Wenxin，hunyuan, and Xinghuo
Agent Development Kit (ADK) for building powerful, interoperable AI agents with the Agent-to-Agent (A2A) protocol
SDK for interacting with various Large Language Model (LLM) APIs using a common interface
Google Gemini API client for Miyabi LLM - Provider-specific implementation
AgentLoop and LlmClient trait for motosan-chat
No description provided.
No description provided.
No description provided.