opencodex

A local AI gateway connects Codex and Claude Code to Ollama or cloud providers, with shared model selection and routing across providers.

opencodex is a local AI gateway for developers who want to choose which models power their coding assistants. It connects Codex, Claude Code, Claude Desktop and Grok Build to alternative providers while keeping each tool's native interface.

Model choice: Use local Ollama models or providers such as Anthropic, Google Gemini, DeepSeek and OpenRouter, plus OpenAI-compatible endpoints.
Coding tool integration: Routed models appear in the Codex App and Claude Code model pickers, and managed configurations connect tools including OpenCode and Cline.
Routing and sub-agents: Combine providers with automatic failover or weighted routing, and assign routed or native models to Codex sub-agents.
Account connections: Connect through API keys or supported account logins, and pool ChatGPT accounts while keeping existing threads attached to their original account.
Request visibility: A web dashboard shows provider connections, model selection and live request logs, including cache token counts.

The gateway runs on macOS, Windows and Linux and is open source under the MIT license. Local routing doesn't make cloud models local: requests go to the provider you select, while Ollama supports a local backend. Streaming, tool calls, reasoning and images depend on the chosen model. Optional search and image-understanding sidecars use a cloud model through your ChatGPT login.

LLM Gateways and Routers macOS Windows Linux Web Multi-agent workflows Ollama integration OpenAI-compatible API Streaming inference Tool calling

Nobody has claimed opencodex yet

Work on opencodex? Claim this page with an email at opencodex.me. opencodex gets the verified checkmark, and you can upgrade the listing.

Want more people to find it? Promote it

Something wrong or outdated on this page?

Logotyper

Got an idea for an AI tool? I'm Eugene, the designer and developer behind Localhosted. I'll help you build it, from the first sketch to launch.

Start your project

Similar to opencodex

View all tools

aichat

1 video

An open-source LLM CLI connects to Ollama and cloud providers, with document chat, shell assistance and AI agents on macOS, Linux and Windows.

10.6KUpdated 9 months agoApache-2.0

macOS · Windows · Linux · Android · Web#Code execution#MCP#Multimodal input

aichat is a terminal AI assistant for people who want to discuss files, generate shell commands and use model-powered tools from the command line. It connects to Ollama, OpenAI, Claude, Gemini and OpenAI-compatible API providers.

Agent FrameworksChat With Your DocumentsLLM Gateways and RoutersSelf-Hosted Chat Web UIsTerminal Chat Clients

Free Claude Code

8 videos

A local coding agent proxy for macOS, Windows and Linux that connects Claude Code and Codex to local models or cloud providers.

69.9KUpdated 2 days ago

macOS · Windows · Linux · Web · VS Code · JetBrains#Agent Client Protocol#Code execution#llama.cpp backend

Free Claude Code lets developers use coding agents with local models or a choice of cloud providers. It connects existing clients to a shared model catalog rather than requiring a separate coding workflow.

AI Bots for Chat AppsLLM Gateways and RoutersTerminal Coding Agents

FreeLLMAPI

10 videos

A self-hosted LLM router that combines cloud providers and local OpenAI-compatible backends, with automatic failover and encrypted provider keys.

51.8KUpdated 1 day agoMIT

macOS · Windows · Linux · Android · Docker · Web#Context compression#llama.cpp backend#LM Studio integration

FreeLLMAPI gives developers one API for experimenting with cloud models and local backends. The router runs locally, but cloud inference still sends requests to the providers you enable.

LLM Gateways and RoutersMCP Servers and Agent SkillsPrompt Management and Playgrounds

Headroom

7 videos

A local context compression tool that reduces LLM inputs, caches originals for retrieval, and connects to coding agents and OpenAI-compatible clients.

79.6KUpdated 23 hours agoApache-2.0

macOS · Windows · Linux#Context compression#MCP#Multi-agent workflows

Headroom reduces the context that LLM apps and coding agents send to a model. It's for developers whose prompts fill up with repetitive tool results, logs, file contents and retrieved documents. Compression runs locally, but model requests still go to the chosen LLM provider.

Agent MemoryLLM Gateways and RoutersLLM Libraries and SDKsMCP Servers and Agent Skills

llama-swap

5 videos

A self-hosted local AI proxy that switches models on demand and connects apps to OpenAI and Anthropic compatible servers on your own hardware.

6.2KUpdated 2 days agoMIT

macOS · Windows · Linux · Docker · Web#GGUF#Image-to-image#llama.cpp backend

llama-swap is a local AI proxy for people who want several models available to their apps without keeping them all loaded. It starts the server a request needs and replaces the active server when another model is requested.

LLM Gateways and RoutersLocal Model Runners

LLMux

A self-hosted AI gateway connects local models and cloud APIs through an OpenAI-compatible API, with remote inference blocked by default.

2Updated 3 months agoApache-2.0

macOS · Windows · Linux · Web#llama.cpp backend#Multimodal input#Ollama integration

LLMux is a self-hosted AI gateway for developers who want to use local models and cloud providers through one interface while controlling where requests go. It blocks remote inference by default and logs permitted calls that leave the machine.

Guardrails, Security and SandboxingLLM Gateways and RoutersLLM Libraries and SDKs