Open Source Proxy Tools
A proxy is an intermediary that forwards requests between a client and another service. Proxies can route or filter network traffic, help users reach services through different network paths, and let developers inspect or modify HTTP(S) requests. In software integrations, a proxy can also present a consistent interface to multiple APIs or tools, simplifying access and separating clients from backend details.
Open source proxy tools include forward and reverse proxies, traffic inspection utilities, configuration managers, and gateways for APIs or AI services. When choosing one, consider its supported protocols, security model, configuration needs, platform requirements, license, and integration with your existing systems. Check release history and documentation to assess maintenance and operational maturity. These tools are useful to network administrators, developers, privacy-conscious users, and teams that need to manage or debug traffic and service connections.
45 repositories · updated October 17, 2026
router: Route AI Requests to the Best Model
weave-os/router is a Go proxy that routes AI requests across configured model providers, while accepting Anthropic, OpenAI, and Gemini API formats. It suits developers who want model choice and routing behind one endpoint, including agent and coding-tool users.
NewHealth 57/100
llm-d-router: Route Inference Requests Intelligently
llm-d Router directs inference requests using model-serving signals such as KV-cache locality, load, and priority. It is for teams running LLM serving on Kubernetes that need proxy-integrated routing and request flow control.
ActiveHealth 75/100
inference-gateway: Unify LLM Providers Behind One API
Inference Gateway proxies requests to cloud and local LLM providers through compatible APIs. It is suited to teams building provider-flexible AI services that need self-hosting, MCP tools, authentication, or observability.
ActiveHealth 79/100
maskit: Locally Mask Sensitive Data Before AI Requests
Maskit is a local privacy gateway that replaces sensitive information in AI requests with consistent placeholders, then restores it in responses. It is aimed at developers using AI coding tools or web assistants who want a configurable layer between their data and model providers.
NewHealth 62/100
ctx-gate: Reduce LLM Context Tokens Through a Proxy
ctx-gate is a Python proxy that compresses LLM conversation context while aiming to preserve facts relevant to the current prompt. It supports Anthropic and OpenAI-compatible APIs, with evaluation tools to check retention and token savings.
NewHealth 20/100
otari: Manage and Route LLM API Traffic
Otari is a self-hosted, OpenAI-compatible gateway that routes requests to multiple LLM providers through one endpoint. It adds virtual keys, budgets, usage tracking, and configurable routing for teams managing model access and spend.
ActiveHealth 79/100
free-claude-code: Connect Coding Agents to Multiple AI Models
Free Claude Code is a local proxy and admin interface for routing coding agents to cloud and local language models. It suits developers who want one place to configure providers, switch models, and connect multiple coding clients.
ActiveHealth 74/100
metamcp: Combine MCP Servers Behind One Gateway
MetaMCP combines configured MCP servers into unified endpoints and applies namespace-level controls. It suits teams hosting and managing MCP tools for multiple clients, but its development is currently quiet and recent pull-request activity is absent.
QuietHealth 35/100
gh-aw-firewall: Restrict Network Access for Agentic Workflows
A Docker-based firewall for running agentic workflow commands with outbound traffic limited to approved domains. It also isolates LLM credentials in a sidecar, making it useful for teams that need tighter network and secret controls around automated agents.
ActiveHealth 81/100
mcp-gateway: Route MCP Servers and REST APIs Through One Endpoint
A Rust gateway that brings MCP servers and REST APIs behind one endpoint, with tools discovered on demand through a compact meta-tool surface. It also bridges MCP protocol revisions and adds centralized routing and policy controls.
ActiveHealth 55/100
grab: Build Python Web Scrapers and Crawlers
Grab is a Python framework for making HTTP requests, extracting data from HTML, and building concurrent crawlers. It suits developers who need reusable scraping workflows with request handling, task queues, and proxy support.
InactiveHealth 27/100
proxy-list: Find Public Forward Proxy Servers
proxy-list publishes a regularly updated list of free, public forward proxy servers, with address details such as country, anonymity, protocol, and status. It is useful for lightweight testing and research, but public proxies are unreliable and should not be trusted with sensitive traffic.
QuietHealth 24/100