E2B
Open-source, secure environment with real-world tools for enterprise-grade agents.
Written mainly in Python. Released under the Apache-2.0 licence.
Free plan
github.com/e2b-dev/E2B
What each tool is actually for, described plainly. No ratings, no scores, no invented benchmarks.
LLM frameworks: Libraries for building your own application on top of a model: orchestration, agents, structured output and provider routing.
Open-source, secure environment with real-world tools for enterprise-grade agents.
Written mainly in Python. Released under the Apache-2.0 licence.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Written mainly in TypeScript.
Build, run, and manage agent platforms.
Written mainly in Python. Released under the Apache-2.0 licence.
The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents
Written mainly in TypeScript.
A programming framework for agentic AI
Written mainly in Python. Released under the CC-BY-4.0 licence.
A full-featured, hackable Next.js AI chatbot built by Vercel
Written mainly in TypeScript.
Examples and guides for using the Gemini API
Written mainly in Jupyter Notebook. Released under the Apache-2.0 licence.
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
Written mainly in Python. Released under the MIT licence.
A guidance language for controlling large language models.
Written mainly in Jupyter Notebook. Released under the MIT licence.
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
Written mainly in Python. Released under the Apache-2.0 licence.
structured outputs for llms
Written mainly in Python. Released under the MIT licence.
The agent engineering platform.
Written mainly in Python. Released under the MIT licence.
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
Written mainly in Python. Released under the MIT licence.
Build resilient agents.
Written mainly in Python. Released under the MIT licence.
Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.
Released under the Apache-2.0 licence.
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
Written mainly in Python.
LlamaIndex is the document processing platform for AI
Written mainly in Python. Released under the MIT licence.
Mastra is the modern TypeScript framework for AI-powered applications and agents.
Written mainly in TypeScript.
A lightweight, powerful framework for multi-agent workflows
Written mainly in Python. Released under the MIT licence.
Official JavaScript / TypeScript library for the OpenAI API
Written mainly in TypeScript. Released under the Apache-2.0 licence.
The official Python library for the OpenAI API
Written mainly in Python. Released under the Apache-2.0 licence.
Structured Outputs
Written mainly in Python. Released under the Apache-2.0 licence.
How Python does AI. Agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.
Written mainly in Python. Released under the MIT licence.
Integrate cutting-edge LLM technology quickly and easily into your apps
Written mainly in C#. Released under the MIT licence.
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
Written mainly in Python. Released under the MIT licence.