Frameworks

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

#ProjectStarsTierOSSDescription
1n8n
workflowlocaltypescript
205kcomplex⚠️ Fair-codeFair-code workflow engine with 400+ nodes and native AI nodes; the self-hosted Zapier that actually does agents and LangChain.
2AutoGPT
memoryevalspython
187kcomplex⚠️ Polyform-SUThe original autonomous loop: goal in, agent iterates with tools and memory; Forge is the dev framework, Benchmark the eval harness.
3Dify
low-coderagpython
157kcomplex⚠️ Fair-codeOne-stop LLM app platform: visual workflows, RAG pipeline, 50+ tools, model management; "ship from prototype to prod" in a single UI.
4langflow
low-codepython
155kcomplexLow-code UI to build and deploy LangChain/LangGraph flows; visual DAG editor and one-click run.
5langchain
python
147kcomplexChains, tools, retrievers, and agents; the usual entry point for "add tools to an LLM" in Python/JS.
6browser-use
browserpython
116kslightly complexPython web-agent **harness**: natural-language goals become browser actions, driven directly over the Chrome DevTools Protocol (it dropped Playwright in August 2025). The biggest community in the browser-agent category.
7Flowise
low-codetypescript
55.5kcomplex⚠️ Apache+CLADrag-and-drop LangChain UI; deploy flows without code. The low-code sibling to Langflow, with a different component and hosting story.
8llama-index
ragpython
52.2kcomplexData-centric: indexing, RAG, and query engines; agent abstractions sit on top of your data pipelines.
9agno
memoryevalspython
42.3kcomplexPython agents with memory, knowledge bases, tools, and structured outputs; continues the PhiData-era product line under the Agno name—production apps, evals, and pipelines.
10langgraph
workflowpython
42kslightly complexState-machine graphs over LLM steps; checkpointing, human-in-the-loop, and durable execution so workflows survive restarts.
11semantic-kernel
python
28.6kcomplexMicrosoft's plugin and planner layer for LLMs; C#, Python, Java; strong on enterprise auth and orchestration.
12mastra
typedtypescript
28.2kslightly complex⚠️ Elastic-2.0TypeScript-first; agents, tools, and workflows with a single runtime and minimal boilerplate.
13Haystack
memoryragpython
26.6kcomplexOpen-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.
14letta
memorypython
24.8kmostly simplePython agent runtime with tool use and control flow; lean API; stateful agents with long-horizon memory.
15Stagehand
browsertypescript
24.6kslightly complexBrowserbase's SDK for browser agents: natural-language actions (act, extract, observe) and deterministic Playwright code mix in one script, so agent flexibility and repeatable automation live in the same **harness**.
16Google ADK
evalssandboxpython
21.6kcomplexGoogle'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.
17rasa
voicepython
21.3kcomplexConversational AI stack (NLU, dialogue, actions); long-standing OSS choice for chat and voice bots.
18botpress
low-codetypescript
14.9kcomplexVisual bot builder and runtime; multi-channel, open-source alternative to commercial bot platforms.
19R2R
visionragworkflowpython
8kcomplexRAG-first: hybrid search, knowledge graphs, multimodal; the framework for "production RAG" when you care more about retrieval than chat UI.
20agent-squad
multi-agent
7.8kslightly complexAWS-originated orchestrator (now under 2FastLabs): intent classification, streaming, SupervisorAgent; "agent-as-tools" so one agent delegates to a squad.
21AgentVerse
multi-agentpython
5.1kcomplexTask-solving and simulation envs for multi-LLM agents; deploy many agents in custom environments without building infra from scratch.
22youtu-agent
4.6kmostly simpleTencent 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.
23Bee Agent Framework
mcpmulti-agentpythontypescript
3.4kcomplexPython + TypeScript, LF AI–backed; MCP/ACP, workflows, Requirement Agent; the one that pushes "production multi-agent" without LangChain.
24AgentStack
2.2kslightly complexScaffolds full agent projects; plugs in CrewAI, LangGraph, OpenAI Swarm, LlamaStack and wires AgentOps observability from day one.
25AgentSilex
python
456super 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.
26SuperAgentX
multi-agentpython
203mostly simpleLightweight multi-agent orchestrator with an AGI-angle; minimal surface, docs-first, for teams that want orchestration without the kitchen sink.