Plano is an AI-native proxy and data plane for agentic apps — with built-in orchestration, safety, observability, and smart LLM routing so you stay focused on your agents core logic. https://planoai.dev
Find a file
Adil Hafeez ea86f73605
rename envoyfilter => arch (#91)
* rename envoyfilter => arch

* fix more files

* more fixes

* more renames
2024-09-27 16:41:39 -07:00
.github/workflows rename envoyfilter => arch (#91) 2024-09-27 16:41:39 -07:00
arch rename envoyfilter => arch (#91) 2024-09-27 16:41:39 -07:00
chatbot_ui rename envoyfilter => arch (#91) 2024-09-27 16:41:39 -07:00
config_generator rename envoyfilter => arch (#91) 2024-09-27 16:41:39 -07:00
demos rename envoyfilter => arch (#91) 2024-09-27 16:41:39 -07:00
docs Salmanap/docs v1 push (#92) 2024-09-27 15:37:49 -07:00
function_resolver update arch-fc parameters 2024-09-27 13:34:10 -07:00
model_server rename envoyfilter => arch (#91) 2024-09-27 16:41:39 -07:00
public_types Add supported parameter type, validation and tests (#88) 2024-09-27 13:33:05 -07:00
.gitignore rename envoyfilter => arch (#91) 2024-09-27 16:41:39 -07:00
.gitmodules Remove OMF (#78) 2024-09-24 15:18:20 -07:00
.pre-commit-config.yaml rename envoyfilter => arch (#91) 2024-09-27 16:41:39 -07:00
gateway.code-workspace rename envoyfilter => arch (#91) 2024-09-27 16:41:39 -07:00
README.md V1 docs push (#86) 2024-09-25 23:43:34 -07:00

Arch Gateway Logo

Build fast, robust, and personalized GenAI applications (agents, assistants, etc.)

Arch is an intelligent Layer 7 gateway designed for generative AI apps, AI agents, and co-pilots that work with prompts. Engineered with purpose-built LLMs, Arch handles the critical but undifferentiated tasks related to the handling and processing of prompts, including detecting and rejecting jailbreak attempts, intelligently calling "backend" APIs to fulfill the user's request represented in a prompt, routing to and offering disaster recovery between upstream LLMs, and managing the observability of prompts and LLM interactions in a centralized way.

Arch is built on (and by the core contributors of) the wildly popular and robust Envoy Proxy with the belief that:

Prompts are nuanced and opaque user requests, which require the same capabilities as traditional HTTP requests including secure handling, intelligent routing, robust observability, and integration with backend (API) systems for personalization all outside business logic.

Demos

Complete

In progress

  • Network Co-pilot

Not Started

  • Show routing between different prompt targets (keyword search vs. top-k semantic search).
  • Show routing between different prompt-resolver vs RAG-based resolver targets.
  • Text Summarization Based on Lightweight vs. Thoughtful Dialogue using OpenAI
  • Show conversational and system observability metrics. This includes topic/intent detection
  • Show how we can help developers implement safeguards customized to their application requirements and responsible AI policies.

Dev setup

Pre-commit

Use instructions at pre-commit.com to set it up for your machine. Once installed make sure github hooks are setup, so that when you upstream your change pre-commit hooks can run and validate your change. Follow command below to setup github hooks,

$ brew install pre-commit
$ pre-commit install
pre-commit installed at .git/hooks/pre-commit