Search the AI ecosystem

Openlayer helps teams define AI quality requirements, test models and agents, compare versions, monitor production behavior, and enforce release gates. It supports Git, CLI,…

Open Interpreter runs an AI coding and computer-use agent locally through terminal and desktop interfaces. The current project uses a new Rust-based repository, supports…

Open WebUI is a self-hosted, provider-agnostic AI workspace for local and remote models. It supports multi-user chat, retrieval, tools, functions, MCP and OpenAPI connections,…

OpenRouter provides one OpenAI-compatible API for hundreds of language, vision, audio, and multimodal models across many providers. It supports free models, pay-as-you-go credits, routing,…

OpenPipe helps teams collect production data, train specialized models, evaluate them, and serve them through managed inference. It supports fine-tuning, reinforcement-learning workflows, model comparison,…

OpenLIT provides open-source observability for language-model applications and agents. It captures traces, metrics, costs, prompts, evaluations, and guardrail signals through OpenTelemetry-compatible instrumentation and a…

DeepEval is an Apache 2.0 open-source Python framework for evaluating LLM applications, agents, RAG systems, and prompts. It runs locally, integrates with testing and…

TruLens is an open-source Python framework for evaluating, tracing, and comparing LLM applications and AI agents. It provides OpenTelemetry instrumentation, metrics, batch and inline…

DSPy is an open-source Python framework for expressing language-model applications as modular programs and optimizing prompts or weights against measurable objectives. It supports retrieval,…

CAMEL-AI is an Apache-2.0 open-source framework and research community for studying and building agents at scale. Its modules cover individual agents, agent societies, workforce…

SGLang is an Apache-2.0 serving framework for large language, multimodal, embedding, classification, and diffusion models. It provides OpenAI-compatible APIs, advanced scheduling, parallelism, caching, and…

Arize Phoenix is an open-source platform for tracing, evaluating, annotating, experimenting with, and debugging LLM applications and agents. Teams can run it locally, in…

ChainForge is an open-source visual programming environment for comparing prompts and models, running code and LLM scorers, inspecting responses, plotting evaluation results, managing parallel…

Traceloop combines a managed AI observability and evaluation platform with OpenLLMetry, its Apache-2.0 open-source instrumentation. Teams can trace model and agent calls, monitor quality,…

Cognee converts documents and application data into persistent, queryable agent memory. Teams can use the open-source engine locally or Cognee Cloud with APIs, MCP…

vLLM is an Apache-2.0 inference and serving engine for large language and multimodal models. It provides OpenAI-compatible APIs, continuous batching, memory-efficient attention, distributed execution,…

Ragas is an open-source Python framework for evaluating RAG pipelines and LLM applications. It provides component and end-to-end metrics, experiment workflows, integrations with popular…

Inkeep combines a visual agent builder, TypeScript SDK, MCP tooling, managed retrieval, observability, and agent UI components. Teams can self-host the open-source stack or…

Pipecat is an open Python framework for real-time voice and multimodal agents. It connects transport, speech, model, memory, and tool services, and can run…

Langfuse is an open-source AI engineering platform for tracing, evaluations, prompt management, datasets, experiments, and annotation. Teams can use Langfuse Cloud or self-host the…