layra

layra

LAYRAโ€”an enterprise-ready, out-of-the-box solutionโ€”unlocks next-generation intelligent systems powered by visual RAG and limitless visual multi-step agent workflow orchestration.

Stars: 807

Visit
screenshot

LAYRA is the world's first visual-native AI automation engine that sees documents like a human, preserves layout and graphical elements, and executes arbitrarily complex workflows with full Python control. It empowers users to build next-generation intelligent systems with no limits or compromises. Built for Enterprise-Grade deployment, LAYRA features a modern frontend, high-performance backend, decoupled service architecture, visual-native multimodal document understanding, and a powerful workflow engine.

README:

LAYRA Logo

๐ŸŒŒ LAYRA: Next Generation AI Agent Engine That Sees, Understands & Acts

GitHub Stars License: Apache 2.0 Closed Issues Tutorial

English | ็ฎ€ไฝ“ไธญๆ–‡

๐Ÿ“ข Click to Expand WeChat Groups

๐Ÿš€ User Discussion Group 1

User Discussion Group

๐Ÿ’ก Official WeChat Account

Official WeChat Account

๐Ÿš€ New Jina-Embeddings-v4 API support eliminates local GPU requirements

LAYRA is the worldโ€™s first โ€œvisual-nativeโ€ AI automation engine. It sees documents like a human, preserves layout and graphical elements, and executes arbitrarily complex workflows with full Python control. From vision-driven Retrieval-Augmented Generation (RAG) to multi-step agent workflow orchestration, LAYRA empowers you to build next-generation intelligent systemsโ€”no limits, no compromises.

Built for Enterprise-Grade deployment, LAYRA features:

  • ๐Ÿง‘โ€๐Ÿ’ป Modern Frontend: Built with Next.js 15 (TypeScript) & TailwindCSS 4.0 for a snappy, developer-friendly UI.
  • โšก High-Performance Backend: FastAPI-powered with async integration for Redis, MySQL, MongoDB, Kafka & MinIO โ€“ engineered for high concurrency.
  • ๐Ÿ”ฉ Decoupled Service Architecture: Independent services deployed in dedicated containers, enabling scaling on demand and fault isolation.
  • ๐ŸŽฏ Visual-Native Multimodal Document Understanding: Leverages ColQwen 2.5/Jina-Embeddings-v4 to transform documents into semantic vectors stored in Milvus.
  • ๐Ÿš€ Powerful Workflow Engine: Construct complex, loop-nested, and debuggable workflows with full Python execution and human-in-the-loop capabilities.

๐Ÿ“š Table of Contents

๐Ÿ–ผ๏ธ Screenshots

  • LAYRA's web design consistently adheres to a minimalist philosophy, making it more accessible to new users.

Explore LAYRA's powerful interface and capabilities through these visuals:

  1. Homepage - Your Gateway to LAYRA
    Homepage Screenshot

  2. Knowledge Base - Centralized Document Hub
    Knowledge Base Screenshot

  3. Interactive Dialogue - Layout-Preserving Answers Layout-Preserving Answers

  4. Workflow Builder - Drag-and-Drop Agent Creation
    Workflow Screenshot

  5. Workflow Builder - MCP Example
    mcp Screenshot mcp Screenshot

๐Ÿš€ Quick Start

๐Ÿ“‹ Prerequisites

Before starting, ensure your system meets these requirements:

  1. Docker and Docker Compose installed
  2. NVIDIA Container Toolkit configured (Ignore if not deploying ColQwen locally)

โš™๏ธ Installation Steps

1. Configure Environment Variables
# Clone the repository
git clone https://github.com/liweiphys/layra.git
cd layra

# Edit configuration file (modify server IP/parameters as needed)
vim .env

# Key configuration options include:
# - SERVER_IP (server IP)
# - MODEL_BASE_URL (model download source)

For Jina (cloud API) Embeddings v4 users:

vim .env
EMBEDDING_IMAGE_DPI=100 # DPI for document-to-image conversion. Recommended: 100 - 200 (12.5k - 50k tokens/img)  
EMBEDDING_MODEL=jina_embeddings_v4
JINA_API_KEY=your_jina_api_key
JINA_EMBEDDINGS_V4_URL=https://api.jina.ai/v1/embeddings
2. Build and Start Service

Option A: Local ColQwen deployment (recommended for GPUs with >16GB VRAM)

# Initial startup will download ~15GB model weights (be patient)
docker compose up -d --build

# Monitor logs in real-time (replace <container_name> with actual name)
docker compose logs -f <container_name>

Option B: Jina-embeddings-v4 API service (for limited/no GPU resources)

# Initial startup will not download any model weights (fast!)
docker compose -f docker-compose-no-local-embedding.yml up -d --build

# Monitor logs in real-time (replace <container_name> with actual name)
docker compose logs -f <container_name>

Note: If you encounter issues with docker compose, try using docker-compose (with the dash) instead. Also, ensure that you're using Docker Compose v2, as older versions may not support all features. You can check your version with docker compose version or docker-compose version.

๐ŸŽ‰ Enjoy LAYRA!

Your deployment is complete! Start creating with Layra now. ๐Ÿš€โœจ
For detailed options, see the Deployment section.

๐Ÿ“˜ Essential Learning: We strongly recommend spending just 60 minutes with the tutorial before starting with LAYRA - this small investment will help you master its full potential and unlock advanced capabilities.

๐Ÿ“– Tutorial Guide

For step-by-step instructions and visual guides, visit our tutorial on GitHub Pages:
Tutorial Guide

โ“ Why LAYRA?

๐Ÿš€ Beyond RAG: The Power of Visual-First Workflows

While LAYRA's Visual RAG Engine revolutionizes document understanding, its true power lies in the Agent Workflow Engine - a visual-native platform for building complex AI agents that see, reason, and act. Unlike traditional RAG/Workflow systems limited to retrieval, LAYRA enables full-stack automation through:

โš™๏ธ Advanced Workflow Capabilities

  • ๐Ÿ”„ Cyclic & Nested Structures
    Build recursive workflows with loop nesting, conditional branching, and custom Python logic - no structural limitations.

  • ๐Ÿž Node-Level Debugging
    Inspect variables, pause/resume execution, and modify state mid-workflow with visual breakpoint debugging.

  • ๐Ÿ‘ค Human-in-the-Loop Integration
    Inject user approvals at critical nodes for collaborative AI-human decision making.

  • ๐Ÿง  Chat Memory & MCP Integration
    Maintain context across nodes with chat memory and access live information via Model Context Protocol (MCP).

  • ๐Ÿ Full Python Execution
    Run arbitrary Python code with pip installs, HTTP requests, and custom libraries in sandboxed environments.

  • ๐ŸŽญ Multimodal I/O Orchestration
    Process and generate hybrid text/image outputs across workflow stages.

๐Ÿ” Visual RAG: The Seeing Engine

Traditional RAG systems fail because they:

  • โŒ Lose layout fidelity (columns, tables, hierarchy collapse)
  • โŒ Struggle with non-text visuals (charts, diagrams, figures)
  • โŒ Break semantic continuity due to poor OCR segmentation

LAYRA changes this with pure visual embeddings:

๐Ÿ” It sees each page as a whole - just like a human reader - preserving:

  • โœ… Layout structure (headers, lists, sections)
  • โœ… Tabular integrity (rows, columns, merged cells)
  • โœ… Embedded visuals (plots, graphs, stamps, handwriting)
  • โœ… Multi-modal consistency between layout and content

Together, these engines form the first complete visual-native agent platform - where AI doesn't just retrieve information, but executes complex vision-driven workflows end-to-end.

โšก๏ธ Core Superpowers

๐Ÿ”ฅ The Agent Workflow Engine: Infinite Execution Intelligence

Code Without Limits, Build Without Boundaries Our Agent Workflow Engine thinks in LLM, sees in visuals, and builds your logic in Python โ€” no limits, just intelligence.

  • ๐Ÿ”„ Unlimited Workflow Creation
    Design complex custom workflows without structural constraints. Handle unique business logic, branching, loops, and conditions through an intuitive interface.

  • โšก Real-Time Streaming Execution (SSE)
    Observe execution results streamed live โ€“ eliminate waiting times entirely.

  • ๐Ÿ‘ฅ Human-in-the-Loop Integration
    Integrate user input at critical decision points to review, adjust, or direct model reasoning. Enables collaborative AI workflows with dynamic human oversight.

  • ๐Ÿ‘๏ธ Visual-First Multimodal RAG
    Features LAYRAโ€™s proprietary pure visual embedding system, delivering lossless document understanding across 100+ formats (PDF, DOCX, XLSX, PPTX, etc.). The AI actively "sees" your content.

  • ๐Ÿง  Chat Memory & MCP Integration

    • MCP Integration Access and interact with live, evolving information beyond native context windows โ€“ enhancing adaptability for long-term tasks.
    • ChatFlow Memory Maintain contextual continuity through chat memory, enabling personalized interactions and intelligent workflow evolution.

  • ๐Ÿ Full-Stack Python Control

    • Drive logic with arbitrary Python expressions โ€“ conditions, loops, and more
    • Execute unrestricted Python code in nodes (HTTP, AI calls, math, etc.)
    • Sandboxed environments with secure pip installs and persistent runtime snapshots

  • ๐ŸŽจ Flexible Multimodal I/O
    Process and generate text, images, or hybrid outputs โ€“ ideal for cross-modal applications.

  • ๐Ÿ”ง Advanced Development Suite

    • Breakpoint Debugging: Inspect workflow states mid-execution
    • Reusable Components: Import/export workflows and save custom nodes
    • Nested Logic: Construct deeply dynamic task chains with loops and conditionals

  • ๐Ÿงฉ Intelligent Data Utilities

    • Extract variables from LLM outputs
    • Parse JSON dynamically
    • Template rendering engine
      Essential tools for advanced AI reasoning and automation.

๐Ÿ‘๏ธ Visual RAG Engine: Beyond Text, Beyond OCR

Forget tokenization. Forget layout loss.
With pure visual embeddings, LAYRA understands documents like a human โ€” page by page, structure and all.

LAYRA uses next-generation Retrieval-Augmented Generation (RAG) technology powered by pure visual embeddings. It treats documents not as sequences of tokens but as visually structured artifacts โ€” preserving layout, semantics, and graphical elements like tables, figures, and charts.

๐Ÿš€ Latest Updates

(2025.8.4) โœจ Expanded Embedding Model Support:

  • More Embedding Model Support:
    • colqwen (Local GPU - high performance)
    • jina-embeddings-v4 (Cloud API - zero GPU requirements)
  • New Chinese language support

(2025.6.2) Workflow Engine Now Available:

  • Breakpoint Debugging: Debug workflows interactively with pause/resume functionality.
  • Unrestricted Python Customization: Execute arbitrary Python code, including external pip dependency installation, HTTP requests via requests, and advanced logic.
  • Nested Loops & Python-Powered Conditions: Build complex workflows with loop nesting and Python-based conditional logic.
  • LLM Integration:
    • Automatic JSON output parsing for structured responses.
    • Persistent conversation memory across nodes.
    • File uploads and knowledge-base retrieve with multi-modal RAG supporting 100+ formats (PDF, DOCX, XLSX, PPTX, etc.).

(2025.4.6) First Trial Version Now Available:
The first testable version of LAYRA has been released! Users can now upload PDF documents, ask questions, and receive layout-aware answers. Weโ€™re excited to see how this feature can help with real-world document understanding.

  • Current Features:
    • PDF batch upload and parsing functionality
    • Visual-first retrieval-augmented generation (RAG) for querying document content
    • Backend fully optimized for scalable data flow with FastAPI, Milvus, Redis, MongoDB, and MinIO

Stay tuned for future updates and feature releases!

๐Ÿง  System Architecture

LAYRAโ€™s pipeline is designed for async-first, visual-native, and scalable document retrieval and generation.

๐Ÿ” Query Flow

The query goes through embedding โ†’ vector retrieval โ†’ anser generation:

Query Architecture

๐Ÿ“ค Upload & Indexing Flow

PDFs are parsed into images and embedded visually via ColQwen2.5/Jina-Embeddings-v4, with metadata and files stored in appropriate databases:

Upload Architecture

๐Ÿ“ค Execute Workflow (Chatflow)

The workflow execution follows an event-driven, stateful debugging pattern with granular control:

๐Ÿ”„ Execution Flow

  1. Trigger & Debug Control

    • Web UI submits workflow with configurable breakpoints for real-time inspection
    • Backend validates workflow DAG before executing codes

  2. Asynchronous Orchestration

    • Kafka checks predefined breakpoints and triggers pause notifications
    • Scanner performs AST-based code analysis with vulnerability detection

  3. Secure Execution

    • Sandbox spins up ephemeral containers with file system isolation
    • Runtime state snapshots persisted to Redis/MongoDB for recovery

  4. Observability

    • Execution metrics streamed via Server-Sent Events (SSE)
    • Users inject test inputs/resume execution through debug consoles

Upload Architecture

๐Ÿงฐ Tech Stack

Frontend:

  • Next.js, TypeScript, TailwindCSS, Zustand, xyflow

Backend & Infrastructure:

  • FastAPI, Kafka, Redis, MySQL, MongoDB, MinIO, Milvus, Docker

Models & RAG:

  • Embedding: colqwen2.5-v0.2 jina-embeddings-v4
  • LLM Serving: Qwen2.5-VL series (or any OpenAI-compatible model) LOCAL DEPLOYMENT NOTE

โš™๏ธ Deployment

๐Ÿ“‹ Prerequisites

Before starting, ensure your system meets these requirements:

  1. Docker and Docker Compose installed
  2. NVIDIA Container Toolkit configured (Ignore if not deploying ColQwen locally)

โš™๏ธ Installation Steps

1. Configure Environment Variables
# Clone the repository
git clone https://github.com/liweiphys/layra.git
cd layra

# Edit configuration file (modify server IP/parameters as needed)
vim .env

# Key configuration options include:
# - SERVER_IP (public server IP)
# - MODEL_BASE_URL (model download source)

For Jina (cloud API) Embeddings v4 users:

vim .env
EMBEDDING_IMAGE_DPI=100 # DPI for document-to-image conversion. Recommended: 100 - 200 (12.5k - 50k tokens/img)  
EMBEDDING_MODEL=jina_embeddings_v4
JINA_API_KEY=your_jina_api_key
JINA_EMBEDDINGS_V4_URL=https://api.jina.ai/v1/embeddings
2. Build and Start Service

Option A: Local ColQwen deployment (recommended for GPUs with >16GB VRAM)

# Initial startup will download ~15GB model weights (be patient)
docker compose up -d --build

# Monitor logs in real-time (replace <container_name> with actual name)
docker compose logs -f <container_name>

Option B: Jina-embeddings-v4 API service (for limited/no GPU resources)

# Initial startup will download ~15GB model weights (be patient)
docker compose -f docker-compose-no-local-embedding.yml up -d --build

# Monitor logs in real-time (replace <container_name> with actual name)
docker compose logs -f <container_name>

Note: If you encounter issues with docker compose, try using docker-compose (with the dash) instead. Also, ensure that you're using Docker Compose v2, as older versions may not support all features. You can check your version with docker compose version or docker-compose version.

๐Ÿ”ง Troubleshooting Tips

If services fail to start:

# Check container logs:
docker compose logs <container name>

Common fixes:

nvidia-smi  # Verify GPU detection
docker compose down && docker compose up --build  # preserve data to rebuild
docker compose down -v && docker compose up --build  # โš ๏ธ Caution: delete all data to full rebuild

๐Ÿ› ๏ธ Service Management Commands

Choose the operation you need:

Scenario Command Effect
Stop services
(preserve data)		 docker compose stop Stops containers but keeps them intact
Restart after stop docker compose start Restarts stopped containers
Rebuild after code changes docker compose up -d --build Rebuilds images and recreates containers
Recreate containers
(preserve data)		 docker compose down
docker compose up -d 		Destroys then recreates containers
Full cleanup
(delete all data)		 docker compose down -v โš ๏ธ Destroys containers and deletes volumes

โš ๏ธ Important Notes

  1. Initial model download may take significant time (~15GB). Monitor progress:

    docker compose logs -f model-weights-init

  2. After modifying .env or code, always rebuild:

    docker compose up -d --build

  3. Verify NVIDIA toolkit installation:

    nvidia-container-toolkit --version

  4. For network issues:

    • Manually download model weights
    • Copy to Docker volume: (typically at) /var/lib/docker/volumes/layra_model_weights/_data/
    • Create empty complete.layra file in both:
      • colqwen2.5-base folder
      • colqwen2.5-v0.2 folder
    • ๐Ÿšจ Critical: Verify downloaded weights integrity!

๐Ÿ”‘ Key Details

  • docker compose down -v permanently deletes databases and model weights

  • After code/config changes, always use --build flag

  • GPU requirements:

    • Latest NVIDIA drivers
    • Working nvidia-container-toolkit

  • Monitoring tools:

    # Container status
docker compose ps -a

# Resource usage
docker stats

๐Ÿงช Technical Note: All components run exclusively via Docker containers.

๐ŸŽ‰ Enjoy Your Deployment!

Now that everything is running smoothly, happy building with Layra! ๐Ÿš€โœจ

โ–ถ๏ธ Future Deployment Options

In the future, we will support multiple deployment methods including Kubernetes (K8s), and other environments. More details will be provided when these deployment options are available.

๐Ÿ“ฆ Roadmap

Short-term:

  • Add API Support (coming soon)

Long-term:

  • Our evolving roadmap adapts to user needs and AI breakthroughs. New technologies and features will be deployed continuously.

๐Ÿค Contributing

Contributions are welcome! Feel free to open an issue or pull request if youโ€™d like to contribute.
We are in the process of creating a CONTRIBUTING.md file, which will provide guidelines for code contributions, issue reporting, and best practices. Stay tuned!

๐Ÿ“ซ Contact

liweiphys
๐Ÿ“ง [email protected]
๐Ÿ™ github.com/liweiphys/layra
๐Ÿ“บ bilibili: Biggestbiaoge
๐Ÿ” Wechat Official Account๏ผšLAYRA ้กน็›ฎ
๐Ÿ’ก Wechat group: see below the title at the top
๐Ÿ’ผ Exploring Impactful Opportunities - Feel Free To Contact Me!

๐ŸŒŸ Star History

Star History Chart

๐Ÿ“„ License

This project is licensed under the Apache License 2.0. See the LICENSE file for more details.

Endlessly Customizable Agent Workflow Engine - Code Without Limits, Build Without Boundaries.

For Tasks:

Click tags to check more tools for each tasks
build workflows create ai agents execute complex tasks visual document understanding orchestrate workflows

For Jobs:

ai engineer data scientist machine learning engineer software developer data analyst

Alternative AI tools for layra

Similar Open Source Tools

layra Screenshot
layra

LAYRA is the world's first visual-native AI automation engine that sees documents like a human, preserves layout and graphical elements, and executes arbitrarily complex workflows with full Python control. It empowers users to build next-generation intelligent systems with no limits or compromises. Built for Enterprise-Grade deployment, LAYRA features a modern frontend, high-performance backend, decoupled service architecture, visual-native multimodal document understanding, and a powerful workflow engine.

github
: 807
evi-run Screenshot
evi-run

evi-run is a powerful, production-ready multi-agent AI system built on Python using the OpenAI Agents SDK. It offers instant deployment, ultimate flexibility, built-in analytics, Telegram integration, and scalable architecture. The system features memory management, knowledge integration, task scheduling, multi-agent orchestration, custom agent creation, deep research, web intelligence, document processing, image generation, DEX analytics, and Solana token swap. It supports flexible usage modes like private, free, and pay mode, with upcoming features including NSFW mode, task scheduler, and automatic limit orders. The technology stack includes Python 3.11, OpenAI Agents SDK, Telegram Bot API, PostgreSQL, Redis, and Docker & Docker Compose for deployment.

github
: 74
persistent-ai-memory Screenshot
persistent-ai-memory

Persistent AI Memory System is a comprehensive tool that offers persistent, searchable storage for AI assistants. It includes features like conversation tracking, MCP tool call logging, and intelligent scheduling. The system supports multiple databases, provides enhanced memory management, and offers various tools for memory operations, schedule management, and system health checks. It also integrates with various platforms like LM Studio, VS Code, Koboldcpp, Ollama, and more. The system is designed to be modular, platform-agnostic, and scalable, allowing users to handle large conversation histories efficiently.

github
: 138
ComfyUI-Ollama-Describer Screenshot
ComfyUI-Ollama-Describer

ComfyUI-Ollama-Describer is an extension for ComfyUI that enables the use of LLM models provided by Ollama, such as Gemma, Llava (multimodal), Llama2, Llama3, or Mistral. It requires the Ollama library for interacting with large-scale language models, supporting GPUs using CUDA and AMD GPUs on Windows, Linux, and Mac. The extension allows users to run Ollama through Docker and utilize NVIDIA GPUs for faster processing. It provides nodes for image description, text description, image captioning, and text transformation, with various customizable parameters for model selection, API communication, response generation, and model memory management.

github
: 70
zotero-mcp Screenshot
zotero-mcp

Zotero MCP is an open-source project that integrates AI capabilities with Zotero using the Model Context Protocol. It consists of a Zotero plugin and an MCP server, enabling AI assistants to search, retrieve, and cite references from Zotero library. The project features a unified architecture with an integrated MCP server, eliminating the need for a separate server process. It provides features like intelligent search, detailed reference information, filtering by tags and identifiers, aiding in academic tasks such as literature reviews and citation management.

github
: 92
opcode Screenshot
opcode

opcode is a powerful desktop application built with Tauri 2 that serves as a command center for interacting with Claude Code. It offers a visual GUI for managing Claude Code sessions, creating custom agents, tracking usage, and more. Users can navigate projects, create specialized AI agents, monitor usage analytics, manage MCP servers, create session checkpoints, edit CLAUDE.md files, and more. The tool bridges the gap between command-line tools and visual experiences, making AI-assisted development more intuitive and productive.

github
: 15.8k
OpenChat Screenshot
OpenChat

OS Chat is a free, open-source AI personal assistant that combines 40+ language models with powerful automation capabilities. It allows users to deploy background agents, connect services like Gmail, Calendar, Notion, GitHub, and Slack, and get things done through natural conversation. With features like smart automation, service connectors, AI models, chat management, interface customization, and premium features, OS Chat offers a comprehensive solution for managing digital life and workflows. It prioritizes privacy by being open source and self-hostable, with encrypted API key storage.

github
: 79
AIPex Screenshot
AIPex

AIPex is a revolutionary Chrome extension that transforms your browser into an intelligent automation platform. Using natural language commands and AI-powered intelligence, AIPex can automate virtually any browser task - from complex multi-step workflows to simple repetitive actions. It offers features like natural language control, AI-powered intelligence, multi-step automation, universal compatibility, smart data extraction, precision actions, form automation, visual understanding, developer-friendly with extensive API, and lightning-fast execution of automation tasks.

github
: 375
meeting-minutes Screenshot
meeting-minutes

An open-source AI assistant for taking meeting notes that captures live meeting audio, transcribes it in real-time, and generates summaries while ensuring user privacy. Perfect for teams to focus on discussions while automatically capturing and organizing meeting content without external servers or complex infrastructure. Features include modern UI, real-time audio capture, speaker diarization, local processing for privacy, and more. The tool also offers a Rust-based implementation for better performance and native integration, with features like live transcription, speaker diarization, and a rich text editor for notes. Future plans include database connection for saving meeting minutes, improving summarization quality, and adding download options for meeting transcriptions and summaries. The backend supports multiple LLM providers through a unified interface, with configurations for Anthropic, Groq, and Ollama models. System architecture includes core components like audio capture service, transcription engine, LLM orchestrator, data services, and API layer. Prerequisites for setup include Node.js, Python, FFmpeg, and Rust. Development guidelines emphasize project structure, testing, documentation, type hints, and ESLint configuration. Contributions are welcome under the MIT License.

github
: 7.5k
chat-ollama Screenshot
chat-ollama

ChatOllama is an open-source chatbot based on LLMs (Large Language Models). It supports a wide range of language models, including Ollama served models, OpenAI, Azure OpenAI, and Anthropic. ChatOllama supports multiple types of chat, including free chat with LLMs and chat with LLMs based on a knowledge base. Key features of ChatOllama include Ollama models management, knowledge bases management, chat, and commercial LLMs API keys management.

github
: 3.4k
robustmq Screenshot
robustmq

RobustMQ is a next-generation, high-performance, multi-protocol message queue built in Rust. It aims to create a unified messaging infrastructure tailored for modern cloud-native and AI systems. With features like high performance, distributed architecture, multi-protocol support, pluggable storage, cloud-native readiness, multi-tenancy, security features, observability, and user-friendliness, RobustMQ is designed to be production-ready and become a top-level Apache project in the message queue ecosystem by the second half of 2025.

github
: 1.1k
bifrost Screenshot
bifrost

Bifrost is a high-performance AI gateway that unifies access to multiple providers through a single OpenAI-compatible API. It offers features like automatic failover, load balancing, semantic caching, and enterprise-grade functionalities. Users can deploy Bifrost in seconds with zero configuration, benefiting from its core infrastructure, advanced features, enterprise and security capabilities, and developer experience. The repository structure is modular, allowing for maximum flexibility. Bifrost is designed for quick setup, easy configuration, and seamless integration with various AI models and tools.

github
: 541
DreamLayer Screenshot
DreamLayer

DreamLayer AI is an open-source Stable Diffusion WebUI designed for AI researchers, labs, and developers. It automates prompts, seeds, and metrics for benchmarking models, datasets, and samplers, enabling reproducible evaluations across multiple seeds and configurations. The tool integrates custom metrics and evaluation pipelines, providing a streamlined workflow for AI research. With features like automated benchmarking, reproducibility, built-in metrics, multi-modal readiness, and researcher-friendly interface, DreamLayer AI aims to simplify and accelerate the model evaluation process.

github
: 367
J.A.R.V.I.S.2.0 Screenshot
J.A.R.V.I.S.2.0

J.A.R.V.I.S. 2.0 is an AI-powered assistant designed for voice commands, capable of tasks like providing weather reports, summarizing news, sending emails, and more. It features voice activation, speech recognition, AI responses, and handles multiple tasks including email sending, weather reports, news reading, image generation, database functions, phone call automation, AI-based task execution, website & application automation, and knowledge-based interactions. The assistant also includes timeout handling, automatic input processing, and the ability to call multiple functions simultaneously. It requires Python 3.9 or later and specific API keys for weather, news, email, and AI access. The tool integrates Gemini AI for function execution and Ollama as a fallback mechanism. It utilizes a RAG-based knowledge system and ADB integration for phone automation. Future enhancements include deeper mobile integration, advanced AI-driven automation, improved NLP-based command execution, and multi-modal interactions.

github
: 123
llmchat Screenshot
llmchat

LLMChat is an all-in-one AI chat interface that supports multiple language models, offers a plugin library for enhanced functionality, enables web search capabilities, allows customization of AI assistants, provides text-to-speech conversion, ensures secure local data storage, and facilitates data import/export. It also includes features like knowledge spaces, prompt library, personalization, and can be installed as a Progressive Web App (PWA). The tech stack includes Next.js, TypeScript, Pglite, LangChain, Zustand, React Query, Supabase, Tailwind CSS, Framer Motion, Shadcn, and Tiptap. The roadmap includes upcoming features like speech-to-text and knowledge spaces.

github
: 541
gemini-cli Screenshot
gemini-cli

Gemini CLI is an open-source AI agent that provides lightweight access to Gemini, offering powerful capabilities like code understanding, generation, automation, integration, and advanced features. It is designed for developers who prefer working in the command line and offers extensibility through MCP support. The tool integrates directly into GitHub workflows and offers various authentication options for individual developers, enterprise teams, and production workloads. With features like code querying, editing, app generation, debugging, and GitHub integration, Gemini CLI aims to streamline development workflows and enhance productivity.

github
: 75.0k

For similar tasks

activepieces Screenshot
activepieces

Activepieces is an open source replacement for Zapier, designed to be extensible through a type-safe pieces framework written in Typescript. It features a user-friendly Workflow Builder with support for Branches, Loops, and Drag and Drop. Activepieces integrates with Google Sheets, OpenAI, Discord, and RSS, along with 80+ other integrations. The list of supported integrations continues to grow rapidly, thanks to valuable contributions from the community. Activepieces is an open ecosystem; all piece source code is available in the repository, and they are versioned and published directly to npmjs.com upon contributions. If you cannot find a specific piece on the pieces roadmap, please submit a request by visiting the following link: Request Piece Alternatively, if you are a developer, you can quickly build your own piece using our TypeScript framework. For guidance, please refer to the following guide: Contributor's Guide

github
: 17.9k
bee-agent-framework Screenshot
bee-agent-framework

The Bee Agent Framework is an open-source tool for building, deploying, and serving powerful agentic workflows at scale. It provides AI agents, tools for creating workflows in Javascript/Python, a code interpreter, memory optimization strategies, serialization for pausing/resuming workflows, traceability features, production-level control, and upcoming features like model-agnostic support and a chat UI. The framework offers various modules for agents, llms, memory, tools, caching, errors, adapters, logging, serialization, and more, with a roadmap including MLFlow integration, JSON support, structured outputs, chat client, base agent improvements, guardrails, and evaluation.

github
: 1.6k
mastra Screenshot
mastra

Mastra is an opinionated Typescript framework designed to help users quickly build AI applications and features. It provides primitives such as workflows, agents, RAG, integrations, syncs, and evals. Users can run Mastra locally or deploy it to a serverless cloud. The framework supports various LLM providers, offers tools for building language models, workflows, and accessing knowledge bases. It includes features like durable graph-based state machines, retrieval-augmented generation, integrations, syncs, and automated tests for evaluating LLM outputs.

github
: 16.6k
otto-m8 Screenshot
otto-m8

otto-m8 is a flowchart based automation platform designed to run deep learning workloads with minimal to no code. It provides a user-friendly interface to spin up a wide range of AI models, including traditional deep learning models and large language models. The tool deploys Docker containers of workflows as APIs for integration with existing workflows, building AI chatbots, or standalone applications. Otto-m8 operates on an Input, Process, Output paradigm, simplifying the process of running AI models into a flowchart-like UI.

github
: 65
flows-ai Screenshot
flows-ai

Flows AI is a lightweight, type-safe AI workflow orchestrator inspired by Anthropic's agent patterns and built on top of Vercel AI SDK. It provides a simple and deterministic way to build AI workflows by connecting different input/outputs together, either explicitly defining workflows or dynamically breaking down complex tasks using an orchestrator agent. The library is designed without classes or state, focusing on flexible input/output contracts for nodes.

github
: 168
LangGraph-learn Screenshot
LangGraph-learn

LangGraph-learn is a community-driven project focused on mastering LangGraph and other AI-related topics. It provides hands-on examples and resources to help users learn how to create and manage language model workflows using LangGraph and related tools. The project aims to foster a collaborative learning environment for individuals interested in AI and machine learning by offering practical examples and tutorials on building efficient and reusable workflows involving language models.

github
: 74
xorq Screenshot
xorq

Xorq (formerly LETSQL) is a data processing library built on top of Ibis and DataFusion to write multi-engine data workflows. It provides a flexible and powerful tool for processing and analyzing data from various sources, enabling users to create complex data pipelines and perform advanced data transformations.

github
: 93
beeai-framework Screenshot
beeai-framework

BeeAI Framework is a versatile tool for building production-ready multi-agent systems. It offers flexibility in orchestrating agents, seamless integration with various models and tools, and production-grade controls for scaling. The framework supports Python and TypeScript libraries, enabling users to implement simple to complex multi-agent patterns, connect with AI services, and optimize token usage and resource management.

github
: 2.8k

For similar jobs

sweep Screenshot
sweep

Sweep is an AI junior developer that turns bugs and feature requests into code changes. It automatically handles developer experience improvements like adding type hints and improving test coverage.

github
: 7.1k
teams-ai Screenshot
teams-ai

The Teams AI Library is a software development kit (SDK) that helps developers create bots that can interact with Teams and Microsoft 365 applications. It is built on top of the Bot Framework SDK and simplifies the process of developing bots that interact with Teams' artificial intelligence capabilities. The SDK is available for JavaScript/TypeScript, .NET, and Python.

github
: 502
ai-guide Screenshot
ai-guide

This guide is dedicated to Large Language Models (LLMs) that you can run on your home computer. It assumes your PC is a lower-end, non-gaming setup.

github
: 159
classifai Screenshot
classifai

Supercharge WordPress Content Workflows and Engagement with Artificial Intelligence. Tap into leading cloud-based services like OpenAI, Microsoft Azure AI, Google Gemini and IBM Watson to augment your WordPress-powered websites. Publish content faster while improving SEO performance and increasing audience engagement. ClassifAI integrates Artificial Intelligence and Machine Learning technologies to lighten your workload and eliminate tedious tasks, giving you more time to create original content that matters.

github
: 669
chatbot-ui Screenshot
chatbot-ui

Chatbot UI is an open-source AI chat app that allows users to create and deploy their own AI chatbots. It is easy to use and can be customized to fit any need. Chatbot UI is perfect for businesses, developers, and anyone who wants to create a chatbot.

github
: 27.7k
BricksLLM Screenshot
BricksLLM

BricksLLM is a cloud native AI gateway written in Go. Currently, it provides native support for OpenAI, Anthropic, Azure OpenAI and vLLM. BricksLLM aims to provide enterprise level infrastructure that can power any LLM production use cases. Here are some use cases for BricksLLM: * Set LLM usage limits for users on different pricing tiers * Track LLM usage on a per user and per organization basis * Block or redact requests containing PIIs * Improve LLM reliability with failovers, retries and caching * Distribute API keys with rate limits and cost limits for internal development/production use cases * Distribute API keys with rate limits and cost limits for students

github
: 953
uAgents Screenshot
uAgents

uAgents is a Python library developed by Fetch.ai that allows for the creation of autonomous AI agents. These agents can perform various tasks on a schedule or take action on various events. uAgents are easy to create and manage, and they are connected to a fast-growing network of other uAgents. They are also secure, with cryptographically secured messages and wallets.

github
: 1.3k
griptape Screenshot
griptape

Griptape is a modular Python framework for building AI-powered applications that securely connect to your enterprise data and APIs. It offers developers the ability to maintain control and flexibility at every step. Griptape's core components include Structures (Agents, Pipelines, and Workflows), Tasks, Tools, Memory (Conversation Memory, Task Memory, and Meta Memory), Drivers (Prompt and Embedding Drivers, Vector Store Drivers, Image Generation Drivers, Image Query Drivers, SQL Drivers, Web Scraper Drivers, and Conversation Memory Drivers), Engines (Query Engines, Extraction Engines, Summary Engines, Image Generation Engines, and Image Query Engines), and additional components (Rulesets, Loaders, Artifacts, Chunkers, and Tokenizers). Griptape enables developers to create AI-powered applications with ease and efficiency.

github
: 2.2k