katanemo/archgw
Archgw
Archgw este un gateway proxy și plan de date conceput pentru aplicații agentice, oferind un strat centralizat pentru rutare, siguranță și orchestrare între logica aplicației și mai mulți furnizori de modele de limbaj mari. Funcționează ca un orchestrator de agenți AI care automatizează execuția fluxurilor de lucru ale agenților pentru a elimina sarcinile repetitive din codebase-ul principal.
Sistemul dispune de un strat de interfață agnostic față de furnizor, care standardizează API-urile disparate ale modelelor într-un singur format, și un plan de date proxy transparent pentru a intercepta traficul. Utilizează rutarea bazată pe reguli pentru a decupla logica aplicației de furnizori specifici și folosește lanțuri de guardrail bazate pe interceptoare pentru a filtra input-urile și output-urile pentru siguranța conținutului și prevenirea jailbreak-ului.
Platforma include un sistem de observabilitate care captează automat urme (traces), metrici și log-uri end-to-end din interacțiunile cu modelele, fără a necesita instrumentare manuală. De asemenea, utilizează orchestrarea fluxurilor de lucru bazată pe middleware pentru a gestiona fluxul sarcinilor agentice și a urmări semnalele de performanță.
Features
- Agentic Data Planes - Provides a centralized data plane for routing and safety between application logic and various AI model endpoints.
- Agentic Workflow Orchestration - Provides a system for executing complex agent processes by delegating tasks to autonomous agents.
- Model Request Routing - Provides mechanisms for directing API requests to different AI backends based on predefined routing rules.
- AI Safety Guardrails - Implements systems for detecting model jailbreaks, moderating content, and enforcing safety policies.
- Model Proxy Gateways - Implements a gateway proxy that provides a unified interface and routing for multiple LLM providers.
- Provider-Agnostic Model Interfaces - Provides an abstraction layer that standardizes disparate LLM provider APIs into a single consistent format.
- AI Agent Orchestrators - Coordinates model providers and task execution specifically to manage the lifecycle of AI agents.
- Signal-Based Routing Rules - Evaluates decision rules over signals to select the appropriate model provider and decouple application logic.
- Transparent Proxies - Implements a proxy that intercepts agent traffic for telemetry and policy enforcement without requiring client-side changes.
- Model Safety Filters - Ships validation layers for blocking or sanitizing model inputs and outputs based on safety policies.
- LLM Safety Enforcers - Enforces jailbreak, PII, and hallucination controls at the routing layer to block unsafe content.
- Input and Output Guardrails - Provides middleware to filter out-of-scope queries and validate generated content against safety rules.
- Request-Response Filter Chains - Ships a sequence of interceptors to validate and filter AI requests and responses for safety and correctness.
- Agent Workflow Orchestrators - Executes automated agent tasks by routing requests through programmable logic layers and state handlers.
- LLM Observability - Provides monitoring and tracing tools specifically tailored for LLM applications and agentic workflows.
- Agent Observability - Captures traces and evaluates the decision-making accuracy of autonomous agents without manual instrumentation.
- Agent Performance Monitoring - Tracks operational metrics and interaction signals from automated agents to monitor performance.
- Automatic Tracing Instrumentation - Implements automatic instrumentation for capturing end-to-end execution details and performance metrics for model calls.
- LLM Performance Monitoring - Automatically tracks performance metrics and execution traces for large language model operations.
- Agent Frameworks - High-performance proxy for agent routing and guardrail application.
- Agent Orchestration - Intelligent gateway for managing agent interactions.
