AI & Machine Learning

LangChain is an open-source Python framework that provides composable building blocks for chaining LLM calls, tools, retrievers, and memory into production AI applications. It includes LangGraph for stateful multi-agent orchestration and 1000+ integrations with model providers and data stores.

Open-source data annotation platform for computer vision datasets. CVAT supports image, video, and 3D labeling workflows, team review, REST API automation, and self-hosted or managed deployment.

Commercial customer service platform with helpdesk, omnichannel messaging, knowledge base, and AI support agents. Intercom combines ticketing, outbound messaging, reporting, and developer APIs for web and mobile support workflows.

Open-source data labeling platform for multimodal machine learning workflows. Label Studio supports annotation for text, images, audio, video, time series, and LLM evaluation tasks with API, SDK, and storage integrations.

Open-source computer vision data curation and model evaluation platform. It helps teams inspect multimodal datasets, manage annotation workflows, and analyze model behavior through a Python-native interface and visual app.

Open-source dataset management framework for computer vision datasets. Datumaro provides Python and CLI workflows for converting, validating, merging, filtering, and analyzing labeled data across many annotation formats.

Open-source serverless platform for event-driven function execution on Docker and Kubernetes. Nuclio packages code into containerized functions and exposes them through HTTP, cron, and stream-based triggers.

Open-source MCP gateway and Docker CLI plugin for running, grouping, and exposing MCP servers through Docker-managed profiles and catalogs. It powers Docker Desktop's MCP Toolkit and also runs independently against a Docker engine.

AGPL-3.0 hybrid platform combining LLM gateway, MCP orchestrator, and chat UI into one Kubernetes-native stack. Orchestrator spawns each MCP server as an isolated K8s pod — strong isolation, but K8s-only in practice.

Open-source gateway and registry for MCP servers, A2A agents, and REST or gRPC APIs. It centralizes discovery, auth, routing, and observability for agent tool access across local, container, and Kubernetes deployments.

Open-source MCP gateway for routing and governing Model Context Protocol servers. It proxies configured MCP servers, applies security plugins to requests and responses, and can scan server reputation before loading them.

MIT AI gateway from Portkey AI that routes traffic across 1,600+ LLM endpoints through one OpenAI-compatible API. Combines routing, virtual keys, guardrails, caching, observability, and MCP gateway support in a Node.js / Go proxy that runs on Docker or Kubernetes.

LLM gateway from Maxim AI written in Go, with OpenAI-compatible routing, virtual keys, budgets, MCP client and server, and a plugin-based governance pipeline. Apache 2.0 core with a commercial Bifrost Enterprise tier.

Open-source LLM observability platform from Helicone that proxies requests to 20+ providers while capturing traces, cost data, prompts, and user analytics. Self-hostable via Docker Compose with ClickHouse, Postgres, MinIO, and a web UI.

AI gateway from LangDB implemented in Rust, with multi-provider routing, virtual keys, semantic caching, and structured observability. Published under the Elastic License v2 — source-available with a restriction on managed-service redistribution.

Open-source LLM gateway from songquanpeng that proxies 30+ providers behind an OpenAI-compatible API with built-in user accounts, token wallets, and hard quota enforcement. MIT-licensed with active feature development continuing in the new-api fork.

AGPL-3.0 LLM gateway from QuantumNous, forked from one-api and extended with OIDC SSO, expanded provider coverage, and a redesigned admin UI. Proxies 40+ providers via OpenAI-compatible API with a token-wallet and quota system.

Apache 2.0 Kong Gateway plugin suite for multi-provider LLM routing, prompt guardrails, token-based rate limiting, and MCP exposure. Core and several plugins are OSS; AI Rate Limiting Advanced, Semantic Routing, and OIDC auth are Kong Enterprise.

Apache 2.0 LLM extensions for Envoy Gateway from the Envoy Proxy community, with CEL-based routing, JWT authentication, token metrics, and MCP OAuth 2.1 support. Kubernetes Gateway API is the primary deployment target.

Apache 2.0 AI-native API gateway from Alibaba, built on Envoy, with multi-provider LLM routing, built-in MCP hosting, OpenAPI-to-MCP conversion, and token rate limiting. Runs as a single Docker container or on Kubernetes via Helm.

Open-source MCP aggregator from metatool-ai that federates upstream MCP servers into namespaced endpoints for MCP clients. Three-level hierarchy of Servers, Namespaces, and Endpoints, with per-endpoint tool ACLs and generic OIDC discovery for admin login.

Lightweight MPL-2.0 MCP gateway that aggregates upstream servers under one API-key-authenticated endpoint. YAML config file, no database required for basic deployments, single Docker container.

Apache 2.0 Rust agent gateway covering MCP, A2A, and LLM protocols, governed by the Linux Foundation with AWS, Cisco, IBM, Microsoft, Red Hat, and Solo.io participating. Kubernetes Gateway API-first with a standalone binary mode stabilizing through pre-1.0.

Apache 2.0 Rust LLM gateway from TensorZero Inc. that routes traffic across providers and stores every inference in ClickHouse with typed schemas, driving experimentation, evaluation, and fine-tuning workflows from captured data.

Self-hostable LLMOps platform from LangGenius with a visual agent builder, RAG pipeline, multi-provider gateway, and prompt management. Uses the Dify Open Source License — modified Apache 2.0 with a non-compete clause prohibiting multi-tenant SaaS resale.

Self-hostable web UI for LLMs from the Open WebUI project. Multi-user chat with generic OIDC authentication, shared workspaces, document RAG, MCP client support, and Python-based Pipelines and Functions for custom extensions.

Open-source AI chat platform from Danny Avila that mirrors the ChatGPT interface with multi-provider routing, plugins, MCP client, and OpenID Connect login. Docker Compose reference deployment uses MongoDB with optional MeiliSearch for conversation search.

MIT LLM engineering platform from Langfuse for tracing, prompt management, evaluation, and datasets, captured via SDK instrumentation or gateway integration. Core including OIDC SSO is in OSS; advanced RBAC, audit retention, and SCIM sit in the Enterprise tier.

Python-based AI gateway from BerriAI that proxies 100+ LLM providers behind one OpenAI-compatible API with virtual keys, hard-enforced budgets, cost dashboards, and an MCP federation endpoint. Core is MIT; SSO, JWT-to-key mapping, and audit retention sit in LiteLLM Enterprise.

Open-source runtime for ONNX models with hardware-specific optimizations for CPUs, GPUs, and edge devices. Supports inferencing and training across multiple ML frameworks.

Web-based notebook environment that combines live code, equations, narrative text, and rich output. Supports 40+ programming languages with modular architecture for data science and scientific computing.

Open-source high-level neural networks API that supports multiple backends. Designed for fast prototyping, readability, and production deployment.

An end-to-end open-source platform for machine learning with comprehensive tools, libraries, and community resources for building and deploying ML-powered applications.

Open-source machine learning framework developed by Meta and hosted by the Linux Foundation. Provides tensors and dynamic neural networks with strong GPU acceleration.

Open-source toolkit that accelerates AI inference with lower latency and higher throughput while maintaining accuracy. Supports computer vision, LLMs, and generative AI models from TensorFlow, PyTorch, and ONNX.