Awesome Ai Sdks
Section: Links
Entry
Appears in 10 awesome lists
LLM engineering platform for model tracing, prompt management, and application evaluation. Langfuse helps teams collaboratively debug, analyze, and iterate on their LLM applications such as chatbots or AI agents. (Demo, Source Code, Clients) MIT Docker
Section: Links
Section: Developer tools · Open-source LLM engineering platform that helps teams collaboratively debug, analyze, and iterate on their LLM applications. #opensource
Section: Monitoring · Open-source LLM observability platform that helps teams collaboratively debug, analyze, and iterate on their LLM applications.
Section: Large Language Models (LLMs) · Open source LLM engineering platform: Observability, metrics, evals, prompt management, playground, datasets. Integrates with LlamaIndex, Langchain, OpenAI SDK, LiteLLM, and more. #opensource
Section: Testing and Monitoring (Observability) · Traces, evals, prompt management, and metrics to debug and improve your LLM application.
Section: Observability · Open-source LLM observability platform that helps teams collaboratively debug, analyze, and iterate on their LLM applications.
Section: Software Development - IDE & Tools · LLM engineering platform for model tracing, prompt management, and application evaluation. Langfuse helps teams collaboratively debug, analyze, and iterate on their LLM applications such as chatbots or AI agents. (Demo, Source Code, Clients) MIT Docker
Section: Evaluation and Observability · Open-source LLM observability, self-hostable.
Section: LLM 评测与治理 (LLM Evaluation & Harness) · 全链路观测。开源/闭源观测与评估平台,支持 Trace、Prompt 管理及评估。
Section: Developer tools · An open-source LLM engineering platform for tracing, evaluation, prompt management, and metrics. #opensource
is an ecosystem of open-source chatbots trained on a massive collections of clean assistant data including code, stories and dialogue based on LLaMa.
The most widely adopted self-hostable LLM observability platform: traces every agent step, manages prompt versions, and runs evals in one tool. Preferred over cloud-only alternatives when data residency or cost control is a constraint.
Terminal-based AI coding agent with REPL mode for planning and executing complex tasks across multiple files, 2M token context.
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, and other large language models. (Source Code) MIT Docker/Python
The Pinecone vector database makes it easy to build high-performance vector search applications. Developer-friendly, fully managed, and easily scalable without infrastructure hassles.
The agent simulation, evaluation, and observability platform helping product teams ship their AI applications with the quality and speed needed for real-world use.
Keploy is an open-source testing platform that helps developers automate and streamline their testing process. It provides API, and integration testing agents, generating tests, mocks/stubs for APIs that actually work. Additionally, Keploy offers an AI-powered Unit Testing Agent that generates…