Trending AI Repos | Solaire Tools

#1

Dify

Featured

langgenius/dify

Open-source LLM app development platform. Visual workflow builder for chatbots, agents, and AI workflows with RAG pipeline support.

★ 72k +4,500 this week ☍ 10k TypeScript

llmplatformworkflowrag

View on GitHub

Quick Start

git clone https://github.com/langgenius/dify.git cd dify/docker cp .env.example .env

docker compose up -d

Visit http://localhost/install to set up your admin account. Connect your LLM API keys in Settings, then start building workflows.

#2

ollama

Featured

ollama/ollama

Run large language models locally. Get up and running with Llama 3, Mistral, Gemma, and other open models on your own machine.

★ 120k +4,200 this week ☍ 9.1k Go

llmlocal-aiinferenceopen-source

View on GitHub

Quick Start

# Install on macOS or Linux curl -fsSL https://ollama.com/install.sh | sh # Pull and run a model

ollama run llama3

For Windows, download the installer from ollama.com. After install, ollama run llama3 works from any terminal.

#3

open-webui

open-webui/open-webui

Self-hosted AI interface for LLMs. Feature-rich web UI compatible with Ollama and OpenAI-compatible APIs, with chat history, RAG, and more.

★ 68k +3,800 this week ☍ 7.9k Svelte

llmweb-uiself-hostedchat-interface

View on GitHub

Quick Start

# Run with Docker (recommended) docker run -d -p 3000:8080 \ --add-host=host.docker.internal:host-gateway \ -v open-webui:/app/backend/data \ --name open-webui \

ghcr.io/open-webui/open-webui:main

Visit http://localhost:3000. Create an admin account on first launch, then connect to Ollama or any OpenAI-compatible API.

#4

OpenHands

Featured

All-Hands-AI/OpenHands

Platform for AI-powered software development agents. Build, test, and deploy code with autonomous AI agents that understand your entire codebase.

★ 50k +3,100 this week ☍ 5.5k Python

ai-agentscoding-assistantautonomous-agentssoftware-development

View on GitHub

Quick Start

# Clone the repository git clone https://github.com/All-Hands-AI/OpenHands.git cd OpenHands # Install dependencies pip install -e . # Start the server

python -m openhands.server

Visit http://localhost:3000 to access the web interface. You will need an API key from OpenAI, Anthropic, or another supported LLM provider.

#5

n8n

n8n-io/n8n

Workflow automation with AI capabilities. Visual workflow builder with 400+ integrations, code nodes, and AI agent support for complex automation.

★ 62k +2,800 this week ☍ 7.8k TypeScript

automationworkflowai-agentsintegrations

View on GitHub

Quick Start

# Run with Docker docker run -it --rm \ --name n8n \ -p 5678:5678 \ -v n8n_data:/home/node/.n8n \

docker.n8n.io/n8nio/n8n

Visit http://localhost:5678. Create your first workflow by dragging nodes onto the canvas. Add an AI Agent node to build LLM-powered automations.

#6

ComfyUI

comfyanonymous/ComfyUI

Node-based UI for Stable Diffusion. Build complex image generation workflows with a visual graph editor and extensive custom node ecosystem.

★ 68k +2,200 this week ☍ 7.2k Python

stable-diffusionimage-generationworkflownodes

View on GitHub

Quick Start

git clone https://github.com/comfyanonymous/ComfyUI.git cd ComfyUI pip install -r requirements.txt # Download a checkpoint model to models/checkpoints/

python main.py

Opens at http://127.0.0.1:8188. Drag a workflow JSON onto the canvas or start from Default Workflow.

#7

OpenClaw

Featured

openclaw-ai/openclaw

Open-source AI agent orchestration framework. Spin up, manage, and coordinate multiple AI agents with built-in governance, billing, and audit trails.

★ 8.4k +1,850 this week ☍ 620 TypeScript

ai-agentsorchestrationmulti-agentgovernance

View on GitHub

Quick Start

# Clone the repository git clone https://github.com/openclaw-ai/openclaw.git cd openclaw # Install dependencies npm install # Start in development mode

npm run dev

The dashboard launches at http://localhost:4000. Configure your first agent through the web UI or the CLI with npx openclaw agent create.

#8

Anything LLM

Mintplex-Labs/anything-llm

All-in-one desktop and Docker AI app. Chat with documents, use RAG, connect any LLM, and manage workspaces with a clean interface.

★ 35k +1,800 this week ☍ 3.4k JavaScript

ragllmdesktop-appdocument-chat

View on GitHub

Quick Start

# Docker (recommended) docker pull mintplexlabs/anythingllm docker run -d -p 3001:3001 \ -v anythingllm_storage:/app/server/storage \

mintplexlabs/anythingllm

Visit http://localhost:3001. The setup wizard walks you through connecting an LLM provider and creating your first workspace.

#9

llama.cpp

ggerganov/llama.cpp

LLM inference in C/C++. Run quantized models on consumer hardware with high performance, minimal dependencies, and broad model support.

★ 78k +1,600 this week ☍ 11k C++

llminferencequantizationc-plus-plus

View on GitHub

Quick Start

git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp # Build make -j$(nproc) # Download a GGUF model and run

./llama-cli -m models/your-model.gguf -p "Hello, world"

For GPU acceleration, build with make GGML_CUDA=1 (NVIDIA) or make GGML_METAL=1 (Apple Silicon).

#10

vLLM

vllm-project/vllm

High-throughput LLM serving engine. PagedAttention for efficient memory management, continuous batching, and OpenAI-compatible API server.

★ 42k +1,500 this week ☍ 5.8k Python

llminferenceservinghigh-performance

View on GitHub

Quick Start

pip install vllm # Start an OpenAI-compatible server

vllm serve meta-llama/Llama-3-8B-Instruct

The server starts at http://localhost:8000. Use any OpenAI client library to query it. Requires a GPU with sufficient VRAM for your chosen model.

#11

langchain

langchain-ai/langchain

Build context-aware reasoning applications. Framework for developing apps powered by language models with chains, agents, retrieval, and memory.

★ 102k +1,400 this week ☍ 16k Python

llmagentsragframework

View on GitHub

Quick Start

pip install langchain langchain-openai

from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
llm = ChatOpenAI(model="gpt-4o")
prompt = ChatPromptTemplate.from_template("Tell me about {topic}")
chain = prompt | llm
result = chain.invoke({"topic": "AI agents"})
print(result.content)

#12

AutoGen

microsoft/autogen

Framework for building multi-agent AI systems. Create conversational agents that collaborate, debate, and solve problems together.

★ 38k +1,200 this week ☍ 5.5k Python

multi-agentai-agentsconversationmicrosoft

View on GitHub

Quick Start

pip install autogen-agentchat

from autogen import AssistantAgent, UserProxyAgent
assistant = AssistantAgent("assistant", llm_config={"model": "gpt-4o"})
user = UserProxyAgent("user", code_execution_config={"work_dir": "coding"})
user.initiate_chat(assistant, message="Plot a chart of NVDA stock price YTD.")

#13

CrewAI

crewAIInc/crewAI

Production-ready multi-agent orchestration. Define agent roles, goals, and tools, then let crews of AI agents collaborate on complex tasks.

★ 26k +1,100 this week ☍ 3.2k Python

multi-agentorchestrationai-agentsproduction

View on GitHub

Quick Start

pip install crewai crewai-tools

from crewai import Agent, Task, Crew
researcher = Agent(role="Researcher", goal="Find latest AI news")
writer = Agent(role="Writer", goal="Write a blog post")
task = Task(description="Write about trending AI repos", agent=writer)
crew = Crew(agents=[researcher, writer], tasks=[task])
result = crew.kickoff()

#14

transformers

huggingface/transformers

State-of-the-art ML for PyTorch, TensorFlow, and JAX. Thousands of pretrained models for text, vision, audio, and multimodal tasks.

★ 140k +1,100 this week ☍ 28k Python

nlpmachine-learningdeep-learningpytorch

View on GitHub

Quick Start

pip install transformers torch

from transformers import pipeline
classifier = pipeline("sentiment-analysis")
result = classifier("I love building with AI!")
print(result)
# [{'label': 'POSITIVE', 'score': 0.9998}]

#15

LiteLLM

BerriAI/litellm

Unified API for 100+ LLM providers. Drop-in OpenAI-compatible proxy with load balancing, fallbacks, spend tracking, and rate limiting.

★ 18k +950 this week ☍ 2.1k Python

llmproxyapiopenai-compatible

View on GitHub

Quick Start

pip install litellm

import litellm
# Works with any provider
response = litellm.completion(
    model="anthropic/claude-sonnet-4-20250514",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

#16

Vercel AI SDK

vercel/ai

Build AI-powered apps with React, Next.js, Vue, Svelte, and Node.js. Unified API for OpenAI, Anthropic, Google, and more with streaming support.

★ 16k +920 this week ☍ 1.9k TypeScript

aisdkreactstreaming

View on GitHub

Quick Start

npm install ai @ai-sdk/openai

import { generateText } from 'ai';
import { openai } from '@ai-sdk/openai';
const { text } = await generateText({
  model: openai('gpt-4o'),
  prompt: 'What is love?',
});

#17

Stable Diffusion WebUI

AUTOMATIC1111/stable-diffusion-webui

Feature-rich web interface for Stable Diffusion. Supports txt2img, img2img, inpainting, outpainting, and hundreds of extensions.

★ 148k +800 this week ☍ 27k Python

stable-diffusionimage-generationweb-ui

View on GitHub

Quick Start

git clone https://github.com/AUTOMATIC1111/stable-diffusion-webui.git cd stable-diffusion-webui # Linux/macOS ./webui.sh # Windows

webui-user.bat

The install script handles dependencies. Place model checkpoints in models/Stable-diffusion/ and launch.

#18

Haystack

deepset-ai/haystack

End-to-end framework for building RAG and search systems. Composable pipelines for retrieval, generation, and document processing.

★ 20k +680 this week ☍ 2.3k Python

ragsearchnlppipelines

View on GitHub

Quick Start

pip install haystack-ai

from haystack.components.generators import OpenAIGenerator
generator = OpenAIGenerator(model="gpt-4o")
result = generator.run(prompt="What are the benefits of RAG?")
print(result["replies"][0])

#19

Windsurf (Codeium)

codeium-ai/windsurf

AI-powered IDE with Cascade, an agentic coding assistant. Deep codebase understanding, multi-file editing, and terminal integration.

★ 4.8k +650 this week ☍ 310 TypeScript

ideai-codingagentdeveloper-tools

View on GitHub

#20

Cursor

getcursor/cursor

AI-first code editor built on VSCode. Inline code generation, chat-driven editing, and codebase-aware AI that understands your project.

★ 6.2k +580 this week ☍ 420 TypeScript

code-editorai-codingvscodedeveloper-tools

View on GitHub

Spotlight

Dify

ollama

OpenHands

OpenClaw

Dify

Quick Start

ollama

Quick Start

open-webui

Quick Start

OpenHands

Quick Start

n8n

Quick Start

ComfyUI

Quick Start

OpenClaw

Quick Start

Anything LLM

Quick Start

llama.cpp

Quick Start

vLLM

Quick Start

langchain

Quick Start

AutoGen

Quick Start

CrewAI

Quick Start

transformers

Quick Start

LiteLLM

Quick Start

Vercel AI SDK

Quick Start

Stable Diffusion WebUI

Quick Start

Haystack

Quick Start

Windsurf (Codeium)

Quick Start

Cursor

Quick Start