Agentbrisk

AI agent frameworks

Open-source toolkits for building your own agents. Mostly Python and TypeScript, all production-grade.

Agency Swarm

Multi-agent framework built on OpenAI Assistants API with role-based agents and structured communication

Python MIT multi-agent

AgentScope

Visual-first multi-agent framework built for distributed Python workflows

Python Apache-2.0 orchestration

Agno

High-performance Python framework for multi-modal agents and teams

Python MPL-2.0 orchestration

Arize Phoenix

Open-source LLM observability and evaluation with native OpenTelemetry tracing and self-hosting

Python Apache-2.0 observability

AutoGen

Microsoft's multi-agent conversation framework with role-based agents and tool use

Python MIT orchestration

Braintrust

Modern AI evaluation platform built for developers who treat LLM quality as a first-class engineering problem

TypeScript commercial evaluation

Composio

Managed integrations and auth layer for AI agents. 1,000+ apps, OAuth handled

TypeScript MIT integrations

CrewAI

Role-based multi-agent orchestration for production workflows

Python MIT orchestration

Dify

Open-source LLMOps platform with visual workflow builder, RAG pipeline, and self-host or cloud options

TypeScript Apache-2.0 no-code

DSPy

Stanford's framework for programming LLMs with optimizable modules instead of hand-written prompts

Python MIT orchestration

Eko

Production-ready TypeScript framework for browser-native agent workflows

TypeScript MIT orchestration

Embedchain (Mem0)

Memory layer for AI agents and applications, evolved from the Embedchain RAG framework

Python Apache-2.0 memory

Flowise

Open-source no-code builder for LLM apps, self-hostable with a TypeScript stack

TypeScript Apache-2.0 no-code

Griptape

Python AI agent framework with off-prompt data handling, Pipelines, Workflows, and Griptape Cloud

Python Apache-2.0 orchestration

Haystack

The pipeline-first AI framework built for European enterprises and production RAG

Python Apache-2.0 orchestration

Helicone

Open-source LLM observability proxy that logs every API call with zero code changes

TypeScript Apache-2.0 observability

Humanloop

Enterprise prompt management and evaluation platform for teams shipping LLM applications to production

Python commercial evaluation

Instructor

The simplest path to structured, typed outputs from any LLM using Pydantic

Python MIT structured-output

LangChain

The original agent framework that defined the chains, agents, tools, memory pattern

Python MIT orchestration

Langflow

Drag-and-drop visual builder for LangChain flows, with an API and self-host option

Python MIT no-code

Langfuse

Open-source LLM observability, evaluation, and prompt management for agent debugging and cost tracking

TypeScript MIT observability

LangGraph

Build stateful, multi-actor LLM applications as graphs

Python MIT orchestration

LangSmith

LangChain's observability and evaluation platform for debugging, testing, and monitoring LLM applications

Python commercial observability

Letta

Memory-first agent framework for stateful, persistent AI agents

Python Apache-2.0 memory

LiveKit Agents

Real-time voice and video AI agents built on WebRTC infrastructure

Python Apache-2.0 voice

LlamaIndex

RAG-first framework for connecting LLMs to your data with first-class document processing

Python MIT orchestration

Mastra

TypeScript-first agent framework with workflows, RAG, evals, and Cloud deploy

TypeScript Apache-2.0 orchestration

OpenAI Swarm / Agents SDK

OpenAI's official framework for multi-agent handoffs and production agent workflows

Python MIT orchestration

Phidata

Python agent framework, now superseded by Agno

Python Mozilla Public License 2.0 orchestration

Pydantic AI

Type-safe Python agent framework from the Pydantic team

Python MIT orchestration

Semantic Kernel

Microsoft's enterprise-grade AI agent framework for C#, Python, and Java

C# MIT orchestration

smolagents

HuggingFace's minimal agent framework where the LLM writes Python, not JSON

Python Apache-2.0 orchestration

Swarms

Enterprise multi-agent orchestration framework for building large-scale cooperative agent swarms

Python Apache-2.0 multi-agent

Vellum

The GUI-first platform for building, testing, and shipping production AI workflows

Python Proprietary orchestration

VoltAgent

TypeScript agent framework with built-in VoltOps observability for production AI systems

TypeScript MIT orchestration
Search