Archgw

An open-source GenAI application gateway for rapidly building personalized AI applications.

PremiumNewProductProgrammingOpen SourceGenAI

Arch is an open-source gateway specifically designed to handle prompts, leveraging fast Large Language Models (LLMs) for processing prompts and seamlessly integrating with backend systems. Built on Envoy, it supports any application language and offers quick deployment and transparent upgrades. It includes a variety of features such as traffic management, frontend/edge gateways, monitoring, and end-to-end tracing to help developers create fast, robust, and personalized GenAI applications.

Out-of-process architecture based on Envoy: Arch relies on Envoy and is a self-contained process designed to run alongside your application server.
Integration with fast LLMs: Arch utilizes specialized (sub-billion) LLMs designed for fast
cost-effective
and accurate prompt handling.
Traffic management: Offers various capabilities for LLM calls
including intelligent retries and automatic switching to other LLMs to ensure continuous availability and disaster recovery.
Frontend/edge gateway: Arch is well-suited as an edge gateway for AI applications
providing TLS termination
rate limiting
and prompt-based routing.

\The target audience includes developers and enterprises
especially teams that need to build and deploy prompt-based GenAI applications. Arch provides a robust platform that enables developers to quickly integrate LLMs
optimizing user experience while enhancing application observability and reliability.\

Build a personalized chatbot using Arch that calls backend APIs for customized responses based on user prompts.
Utilize Arch's traffic management features to ensure high availability of AI applications through intelligent retries and disaster recovery for LLMs.
Enhance the security and efficiency of AI applications through Arch's frontend gateway capabilities including TLS termination and prompt-based routing.

1. Visit Arch's GitHub page to learn about project details and the quick start guide.
2. Read Arch's documentation to understand how to deploy and configure the Arch gateway.
3. Follow the documentation to integrate Arch into your application
setting up prompt processing and LLM calls.
4. Leverage Arch's monitoring and tracing features to optimize application performance and user experience.

Visit

Archgw Visit Over Time

Monthly Visits

2162

Bounce Rate

0.00%

Page per Visit

4.7

Visit Duration

00:01:32

Archgw Visit Trend

Archgw Visit Geography

No Geography Data

Archgw Traffic Sources

Archgw Alternatives

Helicone AI — An open-source platform for developer logging, monitoring, and debugging.

Programming•Open Source•Monitoring

Evidently AI — AI Observability and Machine Learning Monitoring Platform

Programming•Machine Learning•Monitoring

108

Langtrace — An open-source monitoring tool that enhances the performance of LLM applications.

InternationalSelection•Open Source•Monitoring

114

Qwen2.5-Coder-1.5B-Instruct-GGUF — The Qwen2.5-Coder series features a 1.5B parameter instruction-tuned model.

Programming•Code Generation•Code Reasoning

Neural Magic — Experts in AI model deployment and inference optimization

InternationalSelection•Machine Learning•Model Optimization

Vocera — AI Voice Agent Testing and Monitoring Platform

Business•Voice Agent•Testing

llama-ocr — A free npm library that utilizes Llama 3.2 Vision for OCR, outputting text in markdown format.

Productivity•together ai•vLLMs

234

face_anon_simple — Facial anonymization technology that retains key details while effectively protecting privacy.

Image•Facial Anonymization•Privacy Protection

Qwen2.5-Coder-7B — A 7 billion parameter code generation model from the Qwen2.5-Coder series.

Programming•Code Generation•Code Reasoning

Kiroku — Multi-agent system that assists in organizing and writing documents.

Writing•multi-agent system•document writing

Qwen2.5-Coder-14B-Instruct — A 14 billion parameter code generation model in the Qwen2.5-Coder series.

Programming•Code Generation•Code Reasoning

Qwen2.5-Coder-32B-Instruct — Open-source code generation large language model

Programming•Code Generation•Code Reasoning

Lingma SWE-GPT — An open-source large language model specifically designed for software improvement.

Programming•Open Source•Artificial Intelligence

OpenHands — An open-source AI developer assistant that enhances development efficiency.

Programming•Developer Tools•Code Generation

120

Lamatic.ai — Build, connect, and deploy GenAI applications on the edge.

Programming•GenAI•Edge Deployment

Nous Research — Leader in human-centric language models and simulators

InternationalSelection•Language Models•Open Source

Scraperr — A self-hosted web data scraping tool

Productivity•Open Source•Web Scraping

Editor Usage — Monitor and manage your Cursor editor usage.

Productivity•Monitoring•Management

Srcbook — An open-source, self-hosted, AI-driven application builder.

InternationalSelection•Open Source•Self-Hosted

5ire — User-friendly and unlocks the immense power of AI

Productivity•Large Language Models•Open Source

102

browser-use — An open-source web automation library that supports any large language model (LLM)

Programming•Automation•Web Interaction

186

Panto AI — A code review assistant to ensure defect-free code.

Programming•Code Review•Code Quality

AdvancedLivePortrait-WebUI — Real-time portrait animation web interface based on Gradio.

Image•Gradio•Portrait Animation

132

Rive — A new way to create interactive dynamic graphics

Design•Interactive Graphics•Animation

Tencent-Hunyuan-Large — Industry-leading open-source large mixture-of-experts model

Productivity•Artificial Intelligence•Natural Language Processing

240

Best AI Websites & Tools

Archgw

Archgw Visit Over Time

Archgw Visit Trend

Archgw Visit Geography

Archgw Traffic Sources

Archgw Alternatives

Helicone AI — An open-source platform for developer logging, monitoring, and debugging.

Evidently AI — AI Observability and Machine Learning Monitoring Platform

Langtrace — An open-source monitoring tool that enhances the performance of LLM applications.

LTXV — Real-time AI video generation open-source model

WhisperNER — Unified open-source named entity and speech recognition model

d-Matrix — An efficient AI inference platform designed for data centers.

marimo — Next-Gen Python Notebook

Qwen2.5-Coder-1.5B-Instruct-GGUF — The Qwen2.5-Coder series features a 1.5B parameter instruction-tuned model.

Neural Magic — Experts in AI model deployment and inference optimization

Vocera — AI Voice Agent Testing and Monitoring Platform

llama-ocr — A free npm library that utilizes Llama 3.2 Vision for OCR, outputting text in markdown format.

face_anon_simple — Facial anonymization technology that retains key details while effectively protecting privacy.

Qwen2.5-Coder-7B — A 7 billion parameter code generation model from the Qwen2.5-Coder series.

Kiroku — Multi-agent system that assists in organizing and writing documents.

Qwen2.5-Coder-14B-Instruct — A 14 billion parameter code generation model in the Qwen2.5-Coder series.

Qwen2.5-Coder-32B-Instruct — Open-source code generation large language model

Lingma SWE-GPT — An open-source large language model specifically designed for software improvement.

OpenHands — An open-source AI developer assistant that enhances development efficiency.

Lamatic.ai — Build, connect, and deploy GenAI applications on the edge.

Nous Research — Leader in human-centric language models and simulators

Scraperr — A self-hosted web data scraping tool

Editor Usage — Monitor and manage your Cursor editor usage.

Srcbook — An open-source, self-hosted, AI-driven application builder.

5ire — User-friendly and unlocks the immense power of AI

browser-use — An open-source web automation library that supports any large language model (LLM)

Panto AI — A code review assistant to ensure defect-free code.

AdvancedLivePortrait-WebUI — Real-time portrait animation web interface based on Gradio.

Rive — A new way to create interactive dynamic graphics

Tencent-Hunyuan-Large — Industry-leading open-source large mixture-of-experts model