Open-Source LLM Evaluation Tools
Test models, prompts, agents and RAG pipelines against your own cases with Promptfoo, DeepEval, Ragas or lm-evaluation-harness.
TypeScript AI agent framework that runs locally or on your server, with memory, MCP, evaluations, and models from OpenAI, Anthropic, and Gemini.
28.4KUpdated 21 hours ago
Web#Human approval#LLM tracing#MCP
Mastra is a TypeScript framework for developers building AI agents and applications on their own servers or inside existing web apps. Its server runs locally or as a standalone deployment; Mastra Cloud provides a hosted alternative. Model routing connects to providers such as OpenAI, Anthropic, and Gemini, so running the framework locally doesn't keep those model requests on your machine.
Agent FrameworksAgent MemoryAI Workflow AutomationLLM Evaluation and TestingLLM Observability and Tracing+0
An open-source LLM observability platform for tracing and evaluating AI agents. Self-host it under Apache 2.0 or use Comet's hosted service.
22.3KUpdated 1 day agoApache-2.0
Web#Guardrails#LLM tracing#Prompt versioning
Opik is an open-source LLM observability and evaluation platform for developers building AI agents and RAG applications. Its Apache 2.0 licensed platform can be self-hosted on your own hardware or servers; Comet also offers a hosted service. Self-hosting lets teams keep their observability deployment in their own environment.
Guardrails, Security and SandboxingLLM Evaluation and TestingLLM Observability and TracingPrompt Management and Playgrounds+0
A Python AI agent framework and runtime you can self-host with Docker, with database storage, a web control plane and an Apache 2.0 license.
42.4KUpdated 1 day agoApache-2.0
Docker · Web#Guardrails#Human approval#LLM tracing
Agno is a Python framework and runtime for developers building customer-facing or internal AI agents. You can run its agent platform locally with Docker, on your own servers or in your cloud. The open-source framework uses the Apache 2.0 license, and the platform keeps sessions, memory, knowledge and traces in your database.
Agent FrameworksGuardrails, Security and SandboxingLLM Evaluation and TestingLLM Observability and TracingMCP Servers and Agent Skills+0
Open-source computer-use agent tools with an MIT license, local VMs on Apple Silicon, and hosted desktop fleets across Linux, Windows, macOS, and Android.
27.3KUpdated 20 hours agoMIT
macOS · Windows · Linux#Code execution#MCP#Tool calling
Cua gives AI agents access to computers they can inspect and operate, with tools for desktop automation, local virtual machines, and hosted fleets. It's for developers building agents that work across native apps and browsers, or evaluating how well those agents complete computer tasks. You bring the agent and model.
Computer and Browser AgentsGuardrails, Security and SandboxingLLM Evaluation and TestingLLM Libraries and SDKsMCP Servers and Agent Skills+0
Trace AI agents, evaluate outputs, and manage prompts with a self-hostable LLM observability platform whose core is MIT licensed.
35.2KUpdated 2 hours ago
Docker#Agent Skills#LLM tracing#MCP
Langfuse is an open source observability and evaluation platform for teams building LLM applications and AI agents. It shows the steps behind a response so developers can investigate failures, slow requests, and cost. Teams can run its MIT-licensed core on their own servers with Docker Compose or Kubernetes, or use Langfuse Cloud as a hosted service.
LLM Evaluation and TestingLLM Observability and TracingPrompt Management and Playgrounds+0
Open source CLI and library for local LLM evaluations and security testing, with Ollama and hosted model APIs plus CI/CD integration.
25.6KUpdated 1 hour agoMIT
#AI red teaming#Git integration#MCP
Promptfoo is an open source CLI and library for testing prompts, AI agents, and RAG applications. It runs evaluations locally and helps developers compare model responses while security teams look for weaknesses in the applications built around them. The project is MIT licensed.
Guardrails, Security and SandboxingLLM Evaluation and Testing+0
An open source Python framework for AI red teaming, with automated attacks, a local web interface, and support for cloud services and custom endpoints.
4.6KUpdated 19 hours agoMIT
Web#AI red teaming#OpenAI-compatible API
PyRIT is an MIT-licensed, open source Python framework for security professionals and engineers assessing generative AI systems. It combines automated attack testing with human-led investigations through CoPyRIT, a web interface served locally. The framework runs locally, but prompts go to the target services you choose; cloud targets and cloud-based scorers process requests outside your machine.
Guardrails, Security and SandboxingLLM Evaluation and Testing+0
A self-hosted LLM routing framework in Python that connects to Ollama and cloud models through LiteLLM. Open source under Apache 2.0.
5.6KUpdated 2 years agoApache-2.0
#Ollama integration#OpenAI-compatible API
RouteLLM is a self-hosted Python framework for developers who want to split requests between a stronger LLM and a cheaper model. It judges which prompts need the stronger model, so an application doesn't have to send every request to its most expensive provider. You control the cost-quality tradeoff through a routing threshold.
LLM Evaluation and TestingLLM Gateways and RoutersLLM Libraries and SDKs+0
Python toolkit for semantic search and RAG with BGE embedding models, multilingual rerankers, fine-tuning and evaluation. MIT licensed.
12.2KUpdated 1 month agoMIT
#Multilingual#Multimodal input#Semantic search
FlagEmbedding is an open-source Python toolkit for developers building semantic search or retrieval-augmented generation (RAG) into their own applications. It runs BGE embedding and reranking models, with tools to fine-tune both and evaluate retrieval results. The library uses the MIT license.
Embedding and Reranker ModelsFine-Tuning and TrainingInference Libraries and BindingsLLM Evaluation and TestingRAG and Vector Search+0
A coding assistant CLI that writes and runs code from plain-language requests. Runs locally or in Docker, with local models or OpenAI and Anthropic APIs.
55.1KUpdated 2 years agoMIT
Windows · Docker#Code execution#Multimodal input
gpt-engineer is a locally run coding assistant for developers who want to experiment with AI code generation and build their own agents. It can create software from plain-language descriptions or make requested changes to an existing codebase. The project is archived and no longer maintained. Its Python code is open source under the MIT license.
Autonomous Coding AgentsLLM Evaluation and TestingPrompt-to-App BuildersTerminal Coding Agents+0
Discourse’s bundled AI plugin adds forum assistants, semantic search, summaries and moderation. Configure a self-hosted model service or cloud provider.
47.9KUpdated 1 day agoGPL-2.0
Linux · Web#LLM tracing#Multi-user access#Structured output
Discourse AI is the official AI plugin bundled with Discourse. Forum administrators can enable its features independently, including an AI bot, semantic search, topic and chat summaries, spam detection and writing assistance. It runs inside a Discourse community, which you can host on your own server.
AI Bots for Chat AppsLLM Evaluation and TestingWebsite and Support Chatbots+0
An open-source LLM fine-tuning tool with a browser interface. Runs on Ubuntu with NVIDIA GPUs or in Docker, under the Apache 2.0 license.
5.2KUpdated 4 days agoApache-2.0
Linux · Docker · Web#Hugging Face integration#LoRA#Quantization
H2O LLM Studio is a self-hosted tool for teams that want to adapt language models to their own datasets without writing training code. Its browser interface brings training experiments, evaluation, and model testing into one place. The project is open source under Apache 2.0.
Experiment Tracking and MLOpsLLM Evaluation and TestingLLM Fine-Tuning+0
A self-hosted LLM evaluation tool with a local dashboard, custom checks and root cause analysis. Apache 2.0 licensed; model grading can call cloud APIs.
2.4KUpdated 2 years agoApache-2.0
Docker · Web#Hugging Face integration#Ollama integration
UpTrain is an open source LLM evaluation tool for developers who need to measure answer quality and investigate failures in their AI applications. Its self-hosted web dashboard runs on your machine through Docker, with a Python package for evaluations inside application code. The dashboard requires no coding.
LLM Evaluation and Testing+0
LLM API benchmarking library in Python, licensed under Apache 2.0. Tests OpenAI-compatible endpoints and cloud providers. Archived and unmaintained.
1.1KUpdated 2 years agoApache-2.0
#OpenAI-compatible API
LLMPerf is a Python library for developers comparing LLM API performance and checking basic response correctness. The project is archived and no longer maintained. Its open-source code uses the Apache License 2.0.
LLM Evaluation and Testing+0
A desktop local LLM evaluation tool for macOS, Windows and Linux. Compare models through local or remote Ollama servers. Open source under MIT.
953Updated 3 weeks agoMIT
macOS · Windows · Linux#Ollama integration
Ollama Grid Search is a desktop app for comparing LLM responses across models, prompts and inference settings. It runs on macOS, Windows and Linux, and suits developers or anyone choosing a model and prompt combination for a particular task. You can inspect the responses together rather than repeat each test by hand.
LLM Evaluation and TestingPrompt Management and Playgrounds+0
Open-source LLM observability software with self-hosting via Docker, OpenTelemetry traces, and Python and TypeScript SDKs.
1.2KUpdated 10 months agoAGPL-3.0
Docker · Web#LLM tracing#Ollama integration
Langtrace is an open-source observability tool for developers who need to debug LLM applications and track their performance. You can run it locally or on your own servers with Docker and Docker Compose. Its traces follow OpenTelemetry standards.
LLM Evaluation and TestingLLM Observability and Tracing+0
Self-hosted LLM observability platform for agent tracing, chatbot analytics and prompt management, with Docker, Kubernetes and a cloud offering.
lunary.aiLLM Evaluation and Testing
Docker · Web#LLM tracing#Multi-user access#Prompt versioning
Lunary is a self-hosted LLM observability and prompt management platform for teams building chatbots and AI agents. It brings production traces, user conversations and prompt versions into one place so developers can investigate errors and teams can assess response quality. You can host it in your own infrastructure or use its cloud service.
LLM Evaluation and TestingLLM Observability and TracingPrompt Management and Playgrounds+0
Self-hosted LLM gateway with evaluation, A/B testing, and Ollama support. Open source under Apache 2.0; archived and no longer maintained.
11.7KUpdated 4 months agoApache-2.0
Docker · Web#Batch processing#LLM tracing#Multimodal input
TensorZero is a self-hosted platform for developers building LLM applications. The project is archived and no longer maintained. It combines a model gateway with tools for inspecting responses, evaluating workflows, and improving prompts using production data and human feedback.
LLM Evaluation and TestingLLM Fine-TuningLLM Gateways and RoutersLLM Observability and TracingPrompt Management and Playgrounds+0
AI agent framework for Python with local and distributed runtimes, a browser-based prototyping UI, and OpenAI and Azure OpenAI integrations.
61.2KUpdated 6 months agoCC-BY-4.0
Web#Code execution#MCP#Multi-agent workflows
AutoGen is a framework for developers building AI agents that work together or alongside people. Its agent runtime can run locally or across distributed systems, while model integrations such as OpenAI and Azure OpenAI send requests to external services. It's community-managed and in maintenance mode, with no further features or enhancements planned.
Agent FrameworksLLM Evaluation and TestingVisual AI App Builders+0
Self-hosted AI agent framework in C# for Windows, Linux and macOS, with LLamaSharp and cloud provider plugins. Apache 2.0 licensed.
3.1KUpdated 2 days agoApache-2.0
macOS · Windows · Linux · Web#Code execution#MCP#Multi-agent workflows
BotSharp is a self-hosted framework for .NET developers building AI agents into business applications. Written in C#, it runs on Windows, Linux and macOS and is open source software under Apache 2.0. Its plugin design lets teams choose their model provider, storage and interface while keeping agent coordination in the same framework.
Agent FrameworksLLM Evaluation and TestingRAG Frameworks and Pipelines+0
An open source LLM evaluation framework for local models and hosted APIs, with GGUF, Hugging Face transformers and llama.cpp support. MIT licensed.
14.1KUpdated 2 weeks agoMIT
macOS#Batch processing#GGUF#Hugging Face integration
lm-evaluation-harness lets researchers and model developers compare language models using shared academic benchmarks and public prompts. It runs evaluations against local models and benchmarks, or sends requests to a hosted model API. EleutherAI's Python framework is open source under the MIT license and powers Hugging Face's Open LLM Leaderboard.
LLM Evaluation and Testing+0
An open-source toolkit for building and evaluating LLM apps locally, with Python workflows, a VS Code designer and optional Azure AI collaboration.
11.2KUpdated 5 months agoMIT
VS Code#Code execution#LLM tracing#Visual workflows
Prompt flow is an MIT-licensed, open-source toolkit for developers who build LLM applications and need to test their behavior before deployment. Its development tools run locally, while an optional cloud version in Azure AI supports team collaboration. Feature development has ended.
LLM Evaluation and TestingLLM Libraries and SDKsLLM Observability and TracingVisual AI App Builders+0
An open-source LLM evaluation platform under Apache 2.0 that compares Hugging Face models and cloud APIs across reasoning, coding, safety and other tasks.
7.5KUpdated 2 days agoApache-2.0
#Distributed execution#Hugging Face integration#OpenAI-compatible API
OpenCompass is an open-source LLM evaluation platform for researchers, model developers and teams comparing models for their applications. Its Python framework evaluates local models and cloud APIs within the same experiment, so teams can compare candidates on shared benchmarks. It uses the Apache 2.0 license.
LLM Evaluation and Testing+0
An open-source AI agent observability platform with Docker self-hosting, Apache 2.0 licensing, automated failure detection, and regression evals.
3.3KUpdated 2 weeks agoApache-2.0
Docker · Web#LLM tracing#MCP
Laminar is an open-source platform for developers who need to see why an AI agent failed and check whether a fix worked. You can self-host it with Docker or on Kubernetes, including AWS and GCP, or use its managed cloud service. It uses the Apache 2.0 license.
Data Labeling and AnnotationLLM Evaluation and TestingLLM Observability and TracingMCP Servers and Agent Skills+0
An open-source Python library for AI agent evaluation and red teaming, licensed under Apache 2.0, with a hosted or on-premise security platform.
5.8KUpdated 1 day agoApache-2.0
#AI red teaming
Giskard is an open-source Python library for testing AI agents, paired with a commercial security platform and assessment service. It's for developers checking agent behavior and security teams assessing deployment risks. The library runs in your own environment under Apache 2.0; Giskard Hub is available hosted or on-premise.
Guardrails, Security and SandboxingLLM Evaluation and Testing+0
An open-source Python toolkit for evaluating embedding models and retrieval systems, with Sentence Transformers support and an interactive leaderboard.
3.4KUpdated 22 hours agoApache-2.0
Docker · Web#Multilingual#Multimodal input
MTEB is an Apache 2.0 Python toolkit for evaluating embedding models and retrieval systems. It runs evaluations through Python or a command-line interface and publishes an interactive leaderboard.
LLM Evaluation and Testing+0
Self-hosted LLM observability and evaluation platform under Apache 2.0. Monitor Ollama, vLLM and coding agents with portable OpenTelemetry traces.
2.8KUpdated 1 day agoApache-2.0
Windows · Linux · Docker · Web#LLM tracing#Ollama integration#Prompt versioning
OpenLIT is a self-hosted platform for developers who need to understand how their LLM applications and AI agents behave. It connects model calls with tool activity, retrieval and agent steps, so teams can investigate errors and compare cost, latency and output quality across a workflow.
GPU Management and MonitoringLLM Evaluation and TestingLLM Observability and TracingPrompt Management and Playgrounds+0
An open-source LLM training and deployment platform under Apache 2.0. Build specialized models on your own infrastructure or use its hosted service.
9.4KUpdated 2 days agoApache-2.0
Docker#Distributed execution#LoRA#Multimodal input
Oumi builds specialized AI models for teams that want control over their training data, model weights, and deployment. Its Apache 2.0 open-source stack runs on laptops, clusters, and your own servers, while its hosted service automates model development from a plain-English task description. You own the resulting weights, data, and training recipes.
Datasets and Synthetic DataLLM Evaluation and TestingLLM Fine-TuningTraining Frameworks+0
An open-source local LLM stack manager that connects Ollama, llama.cpp and AI apps through Docker Compose. Includes a CLI and companion app.
3.2KUpdated 5 days agoApache-2.0
macOS · Linux · Docker#GGUF#llama.cpp backend#MCP
Harbor is a CLI and companion app for people experimenting with AI on their own hardware. It manages a local LLM development environment, connecting model backends to chat interfaces and supporting services so you don't have to configure each connection yourself. It's open source under Apache 2.0.
LLM Evaluation and TestingLocal Model RunnersOne-Click AI Installers+0
AI model hub with an Apache 2.0 Python library for local inference, training and evaluation, plus hosted demos and cloud notebooks.
9.2KUpdated 6 days agoApache-2.0
Docker#Image-to-image#Inpainting#Multimodal input
ModelScope combines a hosted model and dataset hub with a Python library you can run locally. It's for developers and researchers who want to use AI models in their own applications, fine-tune them on their own data, or compare their performance. The library is open source under Apache 2.0.
Inference Libraries and BindingsLLM Evaluation and TestingModel Hubs and DownloadersTraining Frameworks+0
Open-source LLM training toolkit built on PyTorch. Train and chat with your own models on NVIDIA GPUs, with smaller CPU and Apple Silicon examples.
58.3KUpdated 3 months agoMIT
macOS#Code execution#Tool calling
nanochat is an MIT-licensed toolkit for training your own LLM and chatting with it on hardware you control. It's aimed at researchers and developers who want to study or modify the full training pipeline, with a small Python codebase built on PyTorch.
LLM Evaluation and TestingLLM Fine-TuningTerminal Chat ClientsTraining Frameworks+0
An open-source Python framework for testing LLMs and AI agents locally, with adversarial attacks, production guardrails, and Apache 2.0 licensing.
3KUpdated 1 week agoApache-2.0
#AI red teaming#Guardrails
DeepTeam is a Python framework that runs locally to test chatbots, AI agents, and retrieval-augmented generation (RAG) pipelines for security and safety failures. Built on DeepEval, it's open source under Apache 2.0 and aimed at developers and security teams assessing AI applications before deployment or during ongoing development.
Guardrails, Security and SandboxingLLM Evaluation and Testing+0
A self-hosted AI agent platform for text and voice, with business rules, conversation testing, and a shared visual and code workspace.
21.3KUpdated 9 months agoApache-2.0
Web#Guardrails#LLM tracing#MCP
Rasa is an AI agent platform for product teams building customer-facing text and voice assistants. Teams can deploy agents on their own infrastructure and choose their models and data arrangements. Its CALM engine combines language model understanding with business flows whose code enforces rules, so an assistant can handle conversational wording while following defined processes.
Agent FrameworksLLM Evaluation and TestingLLM Observability and TracingVoice Agent FrameworksWebsite and Support Chatbots+0
An open-source Python tool for AI agent evaluation and tracing, with MIT licensing, OpenTelemetry support and a database you control.
3.6KUpdated 1 day agoMIT
#Batch processing#LLM tracing#MCP
TruLens is an open-source Python tool for developers who need to find why an AI agent gives a wrong answer or spends too much on a task. It pairs step-level traces with evaluation scores, so you can connect failures to retrieval, reasoning or tool calls. It uses the MIT license and can write results to a database you run.
LLM Evaluation and TestingLLM Observability and Tracing+0
An open-source AI agent monitoring platform under MIT. Self-host with Docker or Kubernetes, track failures, and dispatch Claude Code or Cursor to fix them.
4.7KUpdated 2 days agoMIT
Docker · Web#Git integration#LLM tracing#MCP
Latitude is a self-hosted AI agent monitoring platform for teams that need to find production failures and check that fixes work. It connects recurring problems to the sessions that caused them, then can dispatch Claude Code or Cursor with enough context to make a fix and open a pull request.
LLM Evaluation and TestingLLM Observability and TracingMCP Servers and Agent Skills+0
A Python framework for generating and evaluating LLM datasets, with Apache 2.0 licensing and integrations for Anthropic, Cohere and Argilla.
3.4KUpdated 10 months agoApache-2.0
#Structured output
Distilabel is an open-source Python framework for engineers building datasets to train or evaluate AI models. It pairs synthetic data generation with LLM feedback, so a pipeline can create examples and judge their quality. It uses the Apache 2.0 license.
Data Labeling and AnnotationDatasets and Synthetic DataLLM Evaluation and TestingLLM Libraries and SDKs+0
