Frameworks

General-purpose agent and LLM application frameworks (the app layer, not harnesses per se).

#	Project	Stars	Tier	OSS	Description
1	n8n workflowlocaltypescript	199k	complex	⚠️ Fair-code	Fair-code workflow engine with 400+ nodes and native AI nodes; the self-hosted Zapier that actually does agents and LangChain.
2	AutoGPT memoryevalspython	186k	complex	⚠️ Polyform-SU	The original autonomous loop: goal in, agent iterates with tools and memory; Forge is the dev framework, Benchmark the eval harness.
3	langflow low-codepython	153k	complex	✅	Low-code UI to build and deploy LangChain/LangGraph flows; visual DAG editor and one-click run.
4	Dify low-coderagpython	151k	complex	⚠️ Fair-code	One-stop LLM app platform: visual workflows, RAG pipeline, 50+ tools, model management; "ship from prototype to prod" in a single UI.
5	langchain python	143k	complex	✅	Chains, tools, retrievers, and agents; the usual entry point for "add tools to an LLM" in Python/JS.
6	browser-use mcpbrowserpython	108k	slightly complex	✅	Python layer over Playwright: natural-language goals become browser actions—web-agent loop without hand-rolling MCP or a custom driver for every site.
7	Flowise low-codetypescript	55.1k	complex	⚠️ Apache+CLA	Drag-and-drop LangChain UI; deploy flows without code. The low-code sibling to Langflow, with a different component and hosting story.
8	llama-index ragpython	51.3k	complex	✅	Data-centric: indexing, RAG, and query engines; agent abstractions sit on top of your data pipelines.
9	agno memoryevalspython	41.5k	complex	✅	Python agents with memory, knowledge bases, tools, and structured outputs; continues the PhiData-era product line under the Agno name—production apps, evals, and pipelines.
10	langgraph workflowpython	38.7k	slightly complex	✅	State-machine graphs over LLM steps; checkpointing, human-in-the-loop, and durable execution so workflows survive restarts.
11	semantic-kernel python	28.4k	complex	✅	Microsoft's plugin and planner layer for LLMs; C#, Python, Java; strong on enterprise auth and orchestration.
12	mastra typedtypescript	26.8k	slightly complex	⚠️ Elastic-2.0	TypeScript-first; agents, tools, and workflows with a single runtime and minimal boilerplate.
13	Haystack memoryragpython	26.1k	complex	✅	Open-source orchestration framework for context-engineered LLM apps: modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation—closer to LangChain's territory than a coding-agent harness.
14	letta memorypython	24.1k	mostly simple	✅	Python agent runtime with tool use and control flow; lean API; stateful agents with long-horizon memory.
15	rasa voicepython	21.3k	complex	✅	Conversational AI stack (NLU, dialogue, actions); long-standing OSS choice for chat and voice bots.
16	Google ADK evalssandboxpython	21k	complex	✅	Google's official Agent Development Kit: code-first Python toolkit for building, evaluating, and deploying agents. Optimized for Gemini but model-agnostic; deploys to Cloud Run / Vertex AI; ships a dev UI with eval and a code-execution sandbox.
17	botpress low-codetypescript	14.8k	complex	✅	Visual bot builder and runtime; multi-channel, open-source alternative to commercial bot platforms.
18	R2R visionragworkflowpython	8k	complex	✅	RAG-first: hybrid search, knowledge graphs, multimodal; the framework for "production RAG" when you care more about retrieval than chat UI.
19	agent-squad multi-agent	7.7k	slightly complex	✅	AWS-originated orchestrator (now under 2FastLabs): intent classification, streaming, SupervisorAgent; "agent-as-tools" so one agent delegates to a squad.
20	AgentVerse multi-agentpython	5.1k	complex	✅	Task-solving and simulation envs for multi-LLM agents; deploy many agents in custom environments without building infra from scratch.
21	youtu-agent	4.6k	mostly simple	❓	Tencent Cloud's agent framework: a minimal tool-calling harness designed to perform well with open-source models, positioned as a lighter alternative to heavier orchestration frameworks.
22	Bee Agent Framework mcpmulti-agentpythontypescript	3.3k	complex	✅	Python + TypeScript, LF AI–backed; MCP/ACP, workflows, Requirement Agent; the one that pushes "production multi-agent" without LangChain.
23	AgentStack	2.2k	slightly complex	✅	Scaffolds full agent projects; plugs in CrewAI, LangGraph, OpenAI Swarm, LlamaStack and wires AgentOps observability from day one.
24	AgentSilex python	453	super simple	✅	~300 lines of readable agent code on top of LiteLLM; the "I want to see the whole loop" option for learning or minimal production.
25	SuperAgentX multi-agentpython	202	mostly simple	✅	Lightweight multi-agent orchestrator with an AGI-angle; minimal surface, docs-first, for teams that want orchestration without the kitchen sink.