A local proxy to intercept and replace standard CLI or BYOK authentication with Kiro/AWS creds... basically letting Claude Code operate independently from Anthropic’s native billing backend
-
Updated
Mar 11, 2026 - Go
A local proxy to intercept and replace standard CLI or BYOK authentication with Kiro/AWS creds... basically letting Claude Code operate independently from Anthropic’s native billing backend
Never pay for LLMs again. ⚡ The $0/mo Multi-Cloud AI Gateway: pool free tiers across Groq, SambaNova, Mistral, Gemini, NVIDIA NIM, Cloudflare & Cohere into one unstoppable, zero-downtime OpenAI-compatible API. Ultra-fast, self-healing, streaming SSE, and RAM cache. Built for founders, startups & indie hackers.
High-performance Rust proxy that translates Anthropic Messages API to OpenAI-compatible format, routing to NVIDIA NIM, Ollama & OpenRouter. Built with Tokio + Axum.
Cloud-Connected Conversational AI Engine & Multi-Turn Cognitive Assistant [The LLM Evolution: Project 2]
Agente RAG acadêmico de alta performance. Usa indexação BM25 sobre MySQL para transformar aulas em respostas via streaming SSE com rastreabilidade total.
Java 17 LLM SDK for gateways and proxies: OpenAI, Anthropic and Gemini native clients, protocol bridges, SSE streaming, usage normalization and extensible pricing. Reactor and optional Spring WebFlux, published on Maven Central.
Lightweight unified AI gateway written in Go. Drop-in OpenAI-compatible proxy with streaming, cost tracking, and multi-provider failover.
Enterprise-grade RAG SaaS platform featuring multi-tenant document ingestion (PDF/DOCX), asynchronous BullMQ background workers, semantic vector search with Qdrant, and real-time streaming AI chat using Google Gemini. Built for production scalability with Redis caching and JWT security.
Embeddable AI chatbot with RAG for company websites — FastAPI + Claude + ChromaDB. One <script> tag, drop on any site. Hybrid retrieval (BM25+vector), streaming SSE, hand-off to a human, analytics dashboard, multilingual.
Turn any website into an OpenAI-compatible LLM provider via Chrome Extension & Cloudflare Workers Durable Objects. Supports /v1/chat/completions, /v1/responses, /v1/embeddings, /v1/models.
NexQ Web - 100% browser-side DeepSeek client (React + TypeScript + Vite). No Tauri, no Rust, no backend; deploys to GitHub Pages.
To associate your repository with the streaming-sse topic, visit your repo's landing page and select "manage topics."