Proxy: open-source projects on GitHub
41 repositories on Proxy, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
LLM Input Compression
Compresses tool outputs, logs, files, and RAG chunks before sending to the LLM, cutting token usage by 60‑95% without loss of quality.
★ 79,744 · PythonLLM API Management
A unified platform for managing LLM API with support for OpenAI, Azure, Claude, and others. Provides a single binary, Docker image, and easy installation.
★ 33,542 · JavaScriptOPENCODEX: PROXY FOR LLM
Opencodex – a universal provider-proxy for OpenAI Codex, allowing any LLM to be connected to the CLI, app, and SDK.
★ 18,574 · TypeScriptJina Reader API
Converts any URL into LLM-friendly text using the prefix https://r.jina.ai/
★ 10,837 · TypeScriptTREG: Tool for Agents
treg is an OpenRouter for agent tools, allowing easy integration of LLM into any workflow.
★ 8,052 · PythonPLANO: AI PROXY FOR AGENTS
AI-native proxy and data plane for agent applications with orchestration and security.
★ 6,567 · RustCOST-XRAY: SEE CLAUDE CODE COSTS
Proxy tool shows what Claude Code and Codex send to API and calculates cost per request. Supports prompt caching and detailed token analytics.
★ 5,806 · PythonMOCKSERVER - MOCK HTTP AND HTTPS
MockServer for mocking API with support for Java, JS, and Ruby. Proxy decrypts SSL and supports port forwarding for full control.
★ 4,888 · JavaKUBEFWD - KUBERNETES PORTS LOCALLY
Bulk port forwarding of Kubernetes services for local development. Convenient and fast!
★ 4,185 · GoProxy for Claude Models
A proxy providing access to Claude and Gemini models from Antigravity for use in Claude Code and OpenClaw.
★ 3,642 · JavaScriptDATA TRANSMISSION BRIDGE
Proxy server connecting Streamable HTTP and stdio MCP transports. Simplifies data exchange protocol integration.
★ 2,562 · Pythonheadroom — compression for LLM
Compresses tool outputs, logs, files, and RAG chunks before sending to the LLM, cutting tokens by 60–95% while preserving answer quality. Library, proxy, and MCP server.
★ 1,828 · PythonMeridian Proxy for Claude Max
Meridian is a custom proxy that lets you use your Claude Max subscription with OpenCode, Pi, Droid, Aider, Crush, Cline, and other tools. 1328 stars on GitHub.
★ 1,328 · TypeScriptOPEN BEDROCK GATEWAY API
The project gives an OpenAI‑compatible REST interface to Amazon Bedrock, allowing models to be called via familiar requests. It supports chat/completions, embeddings endp
★ 1,003 · PythonGOMODEL: AI-GATEWAY IN GO
Lightweight unified API gateway for OpenAI, Anthropic, Gemini, Groq, xAI and Ollama. Alternative to LiteLLM with monitoring, guardrails and cost tracking.
★ 909 · GoAGENT-SKILLS - SMART SKILLS FOR AGENTS
Official agent skills from Oxylabs that simplify integration and expand automation capabilities.
★ 878HOOP - Unified Protocol Gateway
Hoop is a universal gateway for MCP, LLM, databases, and containers with latency under 5 ms.
★ 859 · GoDEV-PROXY: SIMULATE FAILURES AND LOAD
dev-proxy simulates API failures, rate limiting and chaos from the command line. It lets you configure fault‑injection scenarios and observe client reactions. Ideal for t
★ 846 · C#TOKENTAP — CATCHES ALL LLM REQUESTS
Intercept LLM API traffic and visualize token usage in real time. Track costs, debug prompts, and monitor the context window.
★ 812 · PythonCONTEXT MANAGEMENT FOR CLAUDE!
The plugin for Claude Desktop and Codex allows you to select still which past images to send with the next message. Unmarked images still become placeholders, the conver
★ 803 · TypeScriptClaude-TAP: Agent Traffic
Intercept and analyze API traffic from Claude Code, Codex CLI, Gemini CLI, Cursor CLI, OpenCode, Kimi, Pi, and Hermes in a local trace viewer.
★ 788 · PythonCASBIN-GATEWAY - AI API PROTECTION
Casbin Gateway is an AI- and MCP-oriented security gateway for HTTP traffic with an online demo. Protect APIs in just a couple of clicks.
★ 650 · GoDOUBLE CLOUD CODE
headroom-desktop written in Rust lets you double the usage limits of Claude Code and Codex. More agents, fewer restrictions.
★ 646 · RustNADIRCLAW: LLM Routing for Savings
Routes queries to cheap local models and premium LLMs, saving 40‑70% on API costs.
★ 504 · PythonTEAMCLAUDE - MULTI-ACCOUNT PROXY
Manage multiple Claude accounts with automatic quota-based switching. Fast and reliable.
★ 499 · JavaScriptOH-MY-CPA SELF-HOSTED AI GATEWAY
Self-hosted control plane and usage observability console for CLIProxyAPI (CPA). Connect AI providers, manage client keys, get streaming telemetry and model cost snapshot
★ 407 · TypeScriptMCP Proxy for AWS
MCP proxy for AWS simplifies connecting models to cloud services, providing secure and fast access to data.
★ 370 · Pythonmcpsnoop - MCP Tools Sniffer
A transparent proxy that shows every tool call between your AI client and MCP servers in real time, right in the terminal.
★ 368 · GoUNLIMITED CLAUDE CODE CLI
A tool for seamless rotation of Claude and GPT subscriptions and API keys. Switch limits during a session via a local dashboard.
★ 346 · PythonLocal LLM Privacy Gateway
Automatically masks sensitive data in LLM requests and streams restored responses. Works with any tool supporting custom Base URLs like Cursor, Claude Code, and Codex.
★ 342 · PythonFREEBUCKS PROXY: CODING GATEWAY
Multi-account OpenAI‑compatible gateway for coding models. Supports pooled keys, session lifecycle management, TLS stealth, and an embedded admin dashboard. Works without
★ 297 · Go9ROUTER-GO GATEWAY FOR LLM ROUTING
A high‑performance Go proxy routes LLM requests to Claude, DeepSeek, GPT and other models. It delivers up to 32 000 RPS at only 42 MB RAM, is CGO‑free, and supports flexi
★ 295 · GoLLMTRIM: LLM Request Compression
A local proxy that cuts tokens in LLM requests without altering responses, saving up to 31% of input and 74% of output tokens.
★ 274 · RustCLAUDE CODE SAVES YOUR MONEY
Fixes the prompt cache regression in Claude Code that caused costs to rise up to 20x when resuming sessions.
★ 270 · JavaScriptONE API FOR 100+ MODELS
Linten is an open-source AI gateway with a single OpenAI-compatible API for 100+ models. Supports virtual keys, spend tracking, routing, and guardrails. Self-hosted deplo
★ 242 · PythonFREE CODING MODELS WITHOUT KEYS
bansos-router unites free coding models in one local endpoint. No API keys — just connect and let neural nets write code.
★ 241 · TypeScriptCELERITY-PANEL SELF-HOSTED PROXY
Web panel for self-hosting Hysteria 2 and Xray VLESS with cascade topology (Forward/Reverse Chain). Provides SSH setup, server groups, load balancing, ACL filter, API, we
★ 230 · JavaScriptWyoming OpenAI Proxy
OpenAI API-compatible middleware that proxies requests via the Wyoming protocol for voice assistants.
★ 228 · PythonDARIO: CLOUD WITHOUT LIMITS
Dario is a local endpoint that mirrors the Claude Code format. Use your Claude Pro/Max subscription in Cursor, Cline, or Aider without paying for tokens.
★ 223 · JavaScriptINFERENCE GATEWAY: UNIFIED LLM
Cloud gateway that unifies local and cloud LLM providers: Ollama, OpenAI, Groq and others, built in Go.
★ 213 · GoClaude Code Backdoor
The project lets you run Claude Code on any AI provider: DeepSeek, Groq, Ollama, and OpenRouter through a single Python interface.
★ 109 · PythonNew projects on this topic in Telegram
Telegram →