# katanemo/archgw **Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/katanemo-archgw).** 6,603 stars · 432 forks · Rust · Apache-2.0 ## Links - GitHub: https://github.com/katanemo/archgw - Homepage: https://planoai.dev - awesome-repositories: https://awesome-repositories.com/repository/katanemo-archgw.md ## Description Archgw is a gateway proxy and data plane designed for agentic applications, providing a centralized layer for routing, safety, and orchestration between application logic and multiple large language model providers. It functions as an AI agent orchestrator that automates the execution of agent workflows to remove repetitive plumbing from the core codebase. The system features a provider-agnostic interface layer that standardizes disparate model APIs into a single format and a transparent proxy data plane to intercept traffic. It employs rule-based routing to decouple application logic from specific providers and uses interceptor-based guardrail chains to filter inputs and outputs for content safety and jailbreak prevention. The platform includes an observability system that automatically captures end-to-end traces, metrics, and logs from model interactions without requiring manual instrumentation. It also utilizes middleware-driven workflow orchestration to manage the flow of agentic tasks and track performance signals. ## Tags ### Artificial Intelligence & ML - [Agentic Data Planes](https://awesome-repositories.com/f/artificial-intelligence-ml/agentic-data-planes.md) — Provides a centralized data plane for routing and safety between application logic and various AI model endpoints. - [Agentic Workflow Orchestration](https://awesome-repositories.com/f/artificial-intelligence-ml/agent-architectures/orchestration-engines/ai-agent/agentic-workflow-orchestration.md) — Provides a system for executing complex agent processes by delegating tasks to autonomous agents. ([source](https://github.com/katanemo/archgw#readme)) - [Model Request Routing](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-model-clients/model-request-routing.md) — Provides mechanisms for directing API requests to different AI backends based on predefined routing rules. ([source](https://github.com/katanemo/archgw#readme)) - [AI Safety Guardrails](https://awesome-repositories.com/f/artificial-intelligence-ml/ai-safety-guardrails.md) — Implements systems for detecting model jailbreaks, moderating content, and enforcing safety policies. - [Model Proxy Gateways](https://awesome-repositories.com/f/artificial-intelligence-ml/model-proxy-gateways.md) — Implements a gateway proxy that provides a unified interface and routing for multiple LLM providers. - [Provider-Agnostic Model Interfaces](https://awesome-repositories.com/f/artificial-intelligence-ml/provider-agnostic-model-interfaces.md) — Provides an abstraction layer that standardizes disparate LLM provider APIs into a single consistent format. - [LLM Observability](https://awesome-repositories.com/f/artificial-intelligence-ml/llm-observability.md) — Provides monitoring and tracing tools specifically tailored for LLM applications and agentic workflows. ### Development Tools & Productivity - [AI Agent Orchestrators](https://awesome-repositories.com/f/development-tools-productivity/backend-orchestrators/ai-agent-orchestrators.md) — Coordinates model providers and task execution specifically to manage the lifecycle of AI agents. ### Networking & Communication - [Signal-Based Routing Rules](https://awesome-repositories.com/f/networking-communication/traffic-routing-rules/signal-based-routing-rules.md) — Evaluates decision rules over signals to select the appropriate model provider and decouple application logic. - [Transparent Proxies](https://awesome-repositories.com/f/networking-communication/transparent-proxies.md) — Implements a proxy that intercepts agent traffic for telemetry and policy enforcement without requiring client-side changes. ### Security & Cryptography - [Model Safety Filters](https://awesome-repositories.com/f/security-cryptography/model-safety-filters.md) — Ships validation layers for blocking or sanitizing model inputs and outputs based on safety policies. ([source](https://github.com/katanemo/archgw#readme)) - [LLM Safety Enforcers](https://awesome-repositories.com/f/security-cryptography/request-authorization-enforcers/llm-safety-enforcers.md) — Enforces jailbreak, PII, and hallucination controls at the routing layer to block unsafe content. ([source](https://github.com/katanemo/archgw#readme)) - [Input and Output Guardrails](https://awesome-repositories.com/f/security-cryptography/security-guardrails/agent-action-guardrails/input-and-output-guardrails.md) — Provides middleware to filter out-of-scope queries and validate generated content against safety rules. ### Software Engineering & Architecture - [Request-Response Filter Chains](https://awesome-repositories.com/f/software-engineering-architecture/interceptor-sequences/request-response-filter-chains.md) — Ships a sequence of interceptors to validate and filter AI requests and responses for safety and correctness. ### Web Development - [Agent Workflow Orchestrators](https://awesome-repositories.com/f/web-development/middleware-orchestration/agent-workflow-orchestrators.md) — Executes automated agent tasks by routing requests through programmable logic layers and state handlers. ### System Administration & Monitoring - [Agent Observability](https://awesome-repositories.com/f/system-administration-monitoring/agent-observability.md) — Captures traces and evaluates the decision-making accuracy of autonomous agents without manual instrumentation. ([source](https://github.com/katanemo/archgw#readme)) - [Agent Performance Monitoring](https://awesome-repositories.com/f/system-administration-monitoring/agent-performance-monitoring.md) — Tracks operational metrics and interaction signals from automated agents to monitor performance. ([source](https://github.com/katanemo/archgw#readme)) - [Automatic Tracing Instrumentation](https://awesome-repositories.com/f/system-administration-monitoring/automatic-tracing-instrumentation.md) — Implements automatic instrumentation for capturing end-to-end execution details and performance metrics for model calls. - [LLM Performance Monitoring](https://awesome-repositories.com/f/system-administration-monitoring/monitoring-and-observability/observability-platforms/metric-performance-monitors/llm-performance-monitoring.md) — Automatically tracks performance metrics and execution traces for large language model operations. ### Part of an Awesome List - [Agent Frameworks](https://awesome-repositories.com/f/awesome-lists/ai/agent-frameworks.md) — High-performance proxy for agent routing and guardrail application. - [Agent Orchestration](https://awesome-repositories.com/f/awesome-lists/ai/agent-orchestration.md) — Intelligent gateway for managing agent interactions.