AI Agent Frameworks, MCP Servers and SDKs
Code-level building blocks for AI agents: agent frameworks, LLM client libraries, MCP servers that give agents tools, and memory layers.
Subcategories
An open-source Python library for evaluating LLM apps and RAG systems, with custom metrics, test data generation, and LangChain and LlamaIndex integrations.
15.9KUpdated 7 months agoApache-2.0
Ragas is an open-source Python library for developers who need repeatable evaluations of LLM applications and retrieval-augmented generation (RAG) systems. It combines model-based scoring with traditional metrics so teams can compare application changes using test results rather than manual judgments alone. Its license is Apache 2.0.
Datasets and Synthetic DataLLM Evaluation and TestingLLM Libraries and SDKs+0
An open-source Python framework for AI chat apps you can self-host, with customizable interfaces, OAuth and integrations including LangGraph and HuggingFace.
12.5KUpdated 1 month agoApache-2.0
Web#LLM tracing#Multi-user access#Streaming inference
Chainlit is an open-source Python framework for developers building conversational AI apps with their own application logic. You can run the app on your own server and give users a browser chat interface. It's a framework for creating an app, rather than a ready-made chatbot with a fixed model.
AI Bots for Chat AppsLLM Libraries and SDKsSelf-Hosted Chat Web UIs+0
An open-source AI agent memory platform that runs locally on CPU, connects to Claude Code and Codex, and supports self-hosting or managed cloud hosting.
31.2KUpdated 22 hours agoApache-2.0
Docker · Web#Knowledge graphs#MCP#Multi-user access
Cognee gives AI agents persistent memory across sessions, connecting documents, code, and conversations in a searchable knowledge graph. It's for developers who want agents to retain project context and teams whose knowledge sits across tickets, discussions, and repositories. The Python package is open source under Apache 2.0.
Agent MemoryAI Notes and Knowledge BasesMCP Servers and Agent SkillsRAG Frameworks and Pipelines+0
Open-source Java library for LLM apps on the JVM, with Ollama support, tool calling, RAG, and integrations for Spring Boot and Quarkus.
13.2KUpdated 1 day agoApache-2.0
#MCP#Ollama integration#RAG
LangChain4j is an Apache 2.0 open-source Java library for developers building chatbots, assistants and AI agents in JVM applications. It connects application code to local LLM backends such as Ollama as well as cloud providers such as OpenAI and Google Vertex AI. Where model requests go depends on the backend you choose.
Agent FrameworksLLM Libraries and SDKsRAG Frameworks and Pipelines+0
An open-source Ruby AI framework for Ruby and Rails apps, with Ollama, hosted providers and OpenAI-compatible endpoints under an MIT license.
4.4KUpdated 1 day agoMIT
#Human approval#Multi-agent workflows#Multimodal input
RubyLLM is an MIT-licensed AI framework for developers building Ruby and Rails applications with local or hosted models. Its shared API lets an application switch between Ollama, cloud providers such as Anthropic and OpenAI, and OpenAI-compatible endpoints without rewriting its model integration. The framework runs in your application; model processing happens at the local or hosted backend you choose.
Agent FrameworksLLM Libraries and SDKsRAG Frameworks and Pipelines+0
An MIT licensed tool that packages local or remote repositories for Claude, ChatGPT, Gemini, and MCP assistants through a command line or website.
28.6KUpdated 2 days agoMIT
Docker · Web · Browser Extension#Agent Skills#Code execution#MCP
Repomix turns a code repository into a single file that an AI assistant can read. It’s for developers who need to give Claude, ChatGPT, Gemini, or another model enough project context for code review or analysis. You can use its command line on your own machine, pack a repository through its website, or run it as an MCP server, including through Docker. It is open source under the MIT license.
Coding Assistants and AgentsMCP Servers and Agent Skills+0
Open-source meeting bot API for Meet, Teams and Zoom, with live transcripts and AI agent access. Self-host with Docker or use the hosted service.
2.8KUpdated 2 weeks agoApache-2.0
macOS · Windows · Linux · Docker · Web#Code execution#Git integration#Human approval
Vexa is a meeting bot and transcription API for developers building meeting features and teams feeding calls into AI agents. Bots join Google Meet, Microsoft Teams and Zoom, then send live transcripts with speaker labels to your application or agent. You can host the full platform on your own infrastructure or use Vexa's cloud service.
AI Notes and Knowledge BasesMCP Servers and Agent SkillsMeeting Notes and TranscriptionSpeech-to-Text and Transcription+0
.NET library for local LLM apps using Ollama, with streaming chat, embeddings and model management. Open source under MIT; also supports Ollama cloud.
1.4KUpdated 2 months agoMIT
#Multimodal input#Ollama integration#Streaming inference
OllamaSharp is a C# library for developers building .NET applications around Ollama. It connects to Ollama on your own machine or a remote server and covers the full Ollama API, including model management alongside chat and embeddings. It's open source under the MIT license.
LLM Libraries and SDKs+0
An MIT-licensed LLM data extraction library that validates structured outputs with Pydantic and works with Ollama, llama-cpp-python, vLLM and cloud APIs.
14KUpdated 3 weeks agoMIT
#llama.cpp backend#Ollama integration#Streaming inference
Instructor is an open-source library for developers who need structured data from local LLMs or cloud models. It turns natural-language input into typed objects that applications can use, with validation and retries built into the extraction process. Its focus is data extraction.
LLM Libraries and SDKs+0
Self-hosted AI agent platform with document Q&A, workflows and MCP tools. Connect local DeepSeek, Llama or Qwen models, or use cloud providers.
22.9KUpdated 3 days agoGPL-3.0
Docker · Web#MCP#Multimodal input#RAG
MaxKB is a self-hosted AI agent platform for organizations building customer support bots, internal knowledge assistants and business automation. It combines answers grounded in company documents with workflows that can call functions and MCP tools. You can run it on your own server through Docker and use it through a browser.
Agent FrameworksAI Workflow AutomationChat With Your DocumentsRAG Frameworks and PipelinesWebsite and Support Chatbots+0
An open-source Python library that constrains LLM outputs to schemas and grammars, with support for local backends including Ollama and llama.cpp.
15.9KUpdated 1 month agoApache-2.0
#llama.cpp backend#MLX#Ollama integration
Outlines is an open-source Python library for developers who need LLM responses to match a defined structure. It constrains output during generation, reducing the need to repair malformed JSON or retry responses that don't fit an application's requirements. The library uses the Apache 2.0 license.
LLM Libraries and SDKs+0
Local LLM library runs GGUF models through llama.cpp in Node.js, Bun and Electron. MIT licensed, with GPU support and JSON schema enforcement.
2.2KUpdated 3 days agoMIT
macOS · Windows · Linux#Batch processing#GGUF#Guardrails
node-llama-cpp is an open source library for developers adding local LLM inference to JavaScript and TypeScript applications. It connects Node.js, Bun and Electron to llama.cpp, running GGUF models on your own machine. Its MIT license allows use in commercial projects.
Inference Libraries and BindingsLLM Libraries and SDKsTerminal Chat Clients+0
Python web scraping framework that runs locally or in Docker, with adaptive parsing, browser automation and an MCP server for AI agents. BSD-3-Clause licensed.
84.5KUpdated 1 day agoBSD-3-Clause
Docker#Guardrails#MCP#Tool calling
Scrapling is a Python web scraping framework for developers collecting website data or giving AI agents access to web pages. Its adaptive parser can find previously selected elements after a site's layout changes, reducing the need to repair extraction rules. It's open source under the BSD-3-Clause license and runs on your own machine or in Docker.
MCP Servers and Agent SkillsWeb Scraping for AI+0
Self-hosted AI workflow automation with agents, tools, memory and service channels. Source-available under the Fair Core License 1.0.
1.3KUpdated 1 month ago
Web#Human approval#MCP#Multi-user access
Hexabot is a self-hosted AI workflow automation platform for teams building customer service assistants and business automations. It connects conversations to actions across websites, messaging platforms, social channels and custom entry points. You can run it on-premise or in your own cloud, with workflows, memory and customer data in infrastructure you control.
Agent FrameworksAI Workflow AutomationWebsite and Support Chatbots+0
An open-source programming language for AI agents that runs on macOS, Linux and Windows, with typed model calls, local tracing and built-in evaluations.
9.4KUpdated 1 day agoApache-2.0
macOS · Windows · Linux · iOS · Android · Web#Batch processing#LLM tracing#Structured output
BAML is a programming language for developers building AI agents, with typed model calls and local tracing built into the language. It runs standalone on macOS, Linux and Windows, or alongside an existing application. The language is open source under Apache 2.0, and works offline.
Agent FrameworksLLM Evaluation and TestingLLM Libraries and SDKsLLM Observability and Tracing+0
Open-source Python AI agent framework under MIT. Coordinate agents and tools, use local or hosted sandboxes, and connect to OpenAI or other model providers.
29.8KUpdated 24 hours agoMIT
macOS · Windows · Linux#Code execution#Guardrails#Human approval
OpenAI Agents SDK is an open-source Python framework for developers building AI apps that need to use tools, delegate tasks, or work across multiple steps. Its runtime manages agent turns and conversation state while letting developers express workflows in ordinary Python. It uses the MIT license.
Agent FrameworksLLM Libraries and SDKsVoice Agent Frameworks+0
Self-hosted AI observability platform for tracing and evaluating LLM apps. Run it locally or in Docker, with Ollama integration and OpenTelemetry support.
11.7KUpdated 23 hours ago
Docker · Web#LLM tracing#MCP#Ollama integration
Arize Phoenix is a self-hosted platform for developers who need to understand why an AI agent failed and test changes before shipping them. It runs on a laptop, in Docker, or on Kubernetes. Self-hosting keeps traces on your infrastructure; Phoenix Cloud provides a hosted alternative. Phoenix uses the Elastic License 2.0 (ELv2), a source-available license.
Experiment Tracking and MLOpsLLM Evaluation and TestingLLM Observability and TracingMCP Servers and Agent SkillsPrompt Management and Playgrounds+0
Open-source Python library for compressing local or Hugging Face LLM checkpoints, with Apache 2.0 licensing and vLLM-compatible output.
3.8KUpdated 24 hours agoApache-2.0
#Hugging Face integration#Quantization
LLM Compressor is an open-source Python library for developers preparing models to run on their own hardware with vLLM. It reduces model size and memory requirements through quantization, and accepts local checkpoints or models from Hugging Face repositories. It's licensed under Apache 2.0.
LLM Libraries and SDKsQuantization and Model Conversion+0
A local LLM engine that runs models in the browser with WebGPU acceleration, OpenAI API compatibility, and an Apache 2.0 license.
19.2KUpdated 2 weeks agoApache-2.0
Web · Browser Extension#OpenAI-compatible API#Streaming inference#Structured output
WebLLM runs language models directly in a user's browser, using WebGPU for GPU acceleration. It's an open-source engine for developers building web-based AI assistants and Chrome extensions that process prompts on the user's device rather than an inference server. The project uses the Apache 2.0 license.
Inference Libraries and BindingsLLM Libraries and SDKsOn-Device and In-Browser AI+0
An AI agent workspace with hosted and Docker self-hosted options for building agents, scheduling tasks, and sharing projects with a team.
82.9KUpdated 3 hours ago
Linux · Docker · Web#MCP#Multi-agent workflows#Multi-user access
LobeHub is an AI agent workspace for people who want to assign work to several assistants and keep that work organized. It offers a hosted service and a Docker-based self-hosted version for a private device or server. A Linux download is also available.
Agent Frameworks, MCP and SDKsAutomation and No-Code AISelf-Hosted Chat Web UIs+0
An open-source Python AI framework for self-hosted agents and document search, with local model support and an Apache 2.0 license.
26.6KUpdated 1 day agoApache-2.0
Docker#Guardrails#Hugging Face integration#Hybrid search
Haystack is a Python framework for developers building self-hosted AI agents, document search, and apps that answer questions using their own data. Its modular pipelines let teams control which information reaches a model and inspect how retrieval, memory, tools, and generation contribute to an answer. It's open source under Apache 2.0.
Agent FrameworksLLM Libraries and SDKsRAG Frameworks and Pipelines+0
A self-hosted LLM guardrails toolkit for Python apps. Control conversations, check model responses, and connect to LLaMa-2, Falcon or OpenAI models.
7.2KUpdated 23 hours ago
Docker#Guardrails#LLM tracing#Tool calling
NeMo Guardrails is an open-source Python toolkit for developers who need control over how an AI assistant responds and uses tools. It runs within your application or as a self-hosted server, including in Docker. The library uses the Apache 2.0 license.
Guardrails, Security and SandboxingLLM Evaluation and TestingLLM Libraries and SDKs+0
Python client for Ollama with local and cloud model access, streaming chat, embeddings, and async support. Open source under the MIT license.
10.6KUpdated 2 days agoMIT
#Batch processing#Ollama integration#Streaming inference
Ollama Python connects Python applications to models running through Ollama on your own machine or to Ollama's cloud service. It's for developers adding local LLM features to scripts, chat applications, or other Python projects. The library is open source under the MIT license and requires a running Ollama service for local use.
LLM Libraries and SDKs+0
An open-source browser API for AI agents, available locally or self-hosted through Docker, with Apache 2.0 licensing and a hosted cloud service.
7.7KUpdated 2 days agoApache-2.0
macOS · Docker · Web
Steel is a browser API for developers building AI agents that interact with websites. It runs Chrome sessions locally or on a self-hosted server through Docker, so you can keep browser infrastructure on hardware you control. The code uses the Apache 2.0 license. Steel also offers a hosted service where browser sessions run in its cloud.
Computer and Browser AgentsWeb Scraping for AI+0
A local LLM merging toolkit that combines model weights without extra training. Runs on CPU or GPU and supports Llama, Mistral and PyTorch checkpoints.
7.4KUpdated 3 weeks agoLGPL-3.0
#Hugging Face integration#LoRA
mergekit combines existing language models into a single model on your own hardware, without additional training or access to the original training data. It's for developers and researchers who want to combine fine-tuned capabilities or adjust the balance between model behaviors. The Python toolkit is open source under LGPL-3.0.
Fine-Tuning and TrainingLLM Libraries and SDKs+0
A free TypeScript library for AI apps and agents, with streaming, provider switching, and chat UI hooks for React, Next.js, Svelte, and Vue.
27.1KUpdated 2 hours ago
#Agent Skills#Streaming inference#Structured output
Vercel AI SDK is a TypeScript library for developers building chatbots, generative interfaces, and AI agents. It gives an application one way to work with models from providers such as OpenAI, Anthropic, and Google, so teams can change providers without rebuilding the parts of their app that handle responses. It suits developers who want control over the application they build while choosing how it connects to model services.
Agent FrameworksLLM Libraries and SDKs+0
An open source Python library for AI web apps that run on your computer, with options to share a public link or host on Hugging Face Spaces.
43.6KUpdated 1 day agoApache-2.0
Web#MCP
Gradio turns a Python function, model, or API into a web interface. It runs on your computer, making it useful for developers and researchers who want people to try an AI project through a browser. It's open source under the Apache 2.0 license.
LLM Libraries and SDKsVisual AI App Builders+0
A local MCP server that gives Cursor, Claude Desktop and other AI clients structural code search through ast-grep. Open source under MIT.
470Updated 1 month agoMIT
macOS#MCP#Tool calling
ast-grep MCP is a locally run server that lets AI coding assistants search code by its syntax structure. It connects ast-grep to Cursor, Claude Desktop and other clients that support the Model Context Protocol (MCP). It's for developers who need an assistant to find specific code constructs when matching words alone is too broad.
Coding Assistants and AgentsMCP Servers and Agent Skills+0
A local AI coding agent for Linux, macOS and Windows that uses Ollama or cloud providers, edits repositories and checks changes against your tests.
42Updated 13 hours ago
macOS · Windows · Linux · Docker#Agent Skills#Code execution#Distributed execution
Code Buddy is an AI coding assistant for developers who want a terminal agent running on their own machine, with a choice of local or cloud models. It reads repositories, edits code and runs commands on Linux, macOS and Windows. Ollama keeps model inference local without an API key or account; cloud providers send model requests off the machine. Routing includes automatic provider failover.
Autonomous Coding AgentsMCP Servers and Agent SkillsTerminal Coding Agents+0
