#openai

The developper starter pack for document processing

Python framework for composable LLM workflows.

An async thread-safe singleton for the OpenAI Chat (completions) client

Brigade — Your personal intelligence, built enterprise-grade

High-performance .NET BPE tokenizer — up to 618 MiB/s, competitive with Rust. Zero-allocation counting, multilingual cache, o200k/cl100k/r50k/p50k encodings + HuggingFace tokenizer.json support.

A composable framework for building reliable LLM agents on a harness you fully control. The same code runs the agentic loop on every model tier, local 4B to frontier with tool-call healing, verification, and durable crash-resume, on a typed 12-phase engine where every step emits an event you can hook into. Effect-TS, MCP-native, MIT

Frontier AI video generation for coding agents - Seedance, Runway, Veo, Kling on your own keys, behind a hard cost cap. CLI + MCP.

Turn your company's scattered knowledge into AI ready Books ✨

The agent loop for Rust — stream from 7 LLM protocols, run tools, loop until done.

Dulus Ai — Free Agentic AI, Making Gemini web cappable of running bash commands in your terminal! [Gui, Web, Cli, Telegram, 2,000 MCP, 100K Skills . LiteLLM (100+ providers), local models via Ollama, /lang in 34 languages, Mesa Redonda, I create the first utility coin that can be used 100% as AI quota or Fuel, is called $Dulus

Graph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP / LangChain.

The only fully local production-grade Super SDK that provides a simple, unified, and powerful interface for calling more than 200+ LLMs.

Production plumbing for LLM apps in TypeScript: context, cost, testing & governance primitives. Python-interoperable.

Governed, provider-agnostic Python agent SDK: cost budgets, tamper-evident audit, and PII redaction built in.

top #1 and most feature rich GPT wrapper for git — generate commit messages with an LLM in 1 sec — works with Claude, GPT and every other provider, supports local Ollama models too

🚀 One sentence → your one-person company of AI experts → complete deliverable in minutes. 267 CN + 184 EN + 5 more languages (ko/ru/pt-BR/id/ar) · zero-code YAML · auto-verified acceptance · Web Studio / Desktop / Docker · 11 LLM providers (7 key-free). 一句话组建你的「一人公司」AI 专家团队，几分钟交付完整方案；验收自动核验，网页 / 桌面 / Docker 全渠道。

Selects and Rotates Models

Power CLI and Workflow manager for LLMs (core package)

A high-performance AI Gateway written in Rust — call 100+ LLM APIs using OpenAI format

A high-performance tokenizer (BPE + SentencePiece) built with Rust with Python bindings, focused on speed, safety, and resource optimization.

Private, self-hosted AI agent — your models and data stay on your machine. A feature-rich coding + assistant toolset across eight interfaces (CLI, Web, desktop, IM, VS Code, Obsidian, SDK, Mobile), all in one fast, zero-dependency Go binary.

Self-hosted AI gateway and LLM proxy. OpenAI-compatible API for OpenAI, Anthropic, Gemini, Bedrock and 60+ providers, or serve vLLM/llama.cpp on your GPUs. Keys, budgets, guardrails, semantic cache, MCP

An async thread-safe singleton for the Azure OpenAI audio client

An async thread-safe singleton for the Azure OpenAI Chat (completions) client

Providing async thread-safe singleton Semantic Kernel instances

An enum representing various Semantic Kernel types.

Provides OpenAI-specific registration extensions for KernelPoolManager, enabling integration with local LLMs via Semantic Kernel.

Provides Azure OpenAI-specific registration extensions for KernelPoolManager, enabling integration with local LLMs via Semantic Kernel.

TypeScript SDK for BlockRun — 41+ AI models, pay-per-call with USDC. OpenAI-compatible. Zero rate limits.

Open, self-hostable agentic runtime for organizations — durable, replayable agent sessions, human approvals, governed credentials and memory, running in managed sandboxes or on your own hardware. Apache-2.0.