Alternatives to jev-codex-router

Hermes IDE is a multi-project, multi-agent desktop IDE where every repo and every Claude, Codex, or Gemini session stays open at once.

Herm is an open-source coding agent that runs every session inside its own container, with a single Go binary and your choice of model provider.

Free open-source desktop AI workbench that runs 300+ cloud and local models in one app

Open-source agent skills that turn text or image prompts into CAD models, G-code, and robot files.

Kilo is an open-source AI coding agent with 500+ models and zero inference markup across IDE, CLI, and cloud.

Openclaude is an open-source coding agent CLI that runs any model in your terminal with reviewable, scriptable changes.

Open-source AI coding agent for terminal, IDE, and desktop — bring any model, including 75+ LLM providers.

Open-source terminal coding agent that runs the model you choose, hosted or local.

Open-source AI coding agent orchestrator with per-task LLM routing across OpenAI, Anthropic, Gemini, and Ollama.

Xiaomi's free, open-source terminal AI coding agent with unlimited context and the 309B-parameter open-weight MiMo-V2-Flash model.

Open-source agent harness that routes each task to the best model, one command at a time.

An open-source multi-agent harness that runs a virtual office of AI clones on your existing Claude Code and Codex subscriptions.

Pioneer is a self-improving inference API that routes every call to the right model and retrains itself from your production traffic.

Open-source agentic development workspace that keeps agent crews working across sessions, schedules, and your existing tools

Source-available LLM router that picks the cheapest model clearing your quality bar.

Open-source MCP skill that adds 25 unified AI coding commands and a persistent memory layer to the agents you already run

Open-source MIT proxy that reroutes Claude Code's API calls to DeepSeek, Groq, Ollama, OpenRouter, NVIDIA NIM, or any OpenAI-compatible endpoint.

Bito's Governor is an AI model router and code context engine that cuts coding agent spend by grounding every request in your codebase.

Open-weight agentic coding models — Laguna XS 2.1 and Laguna S 2.1 — built for secure on-prem and air-gapped enterprise AI.

A desktop memory layer that captures your focused app every 2 seconds and pipes that history into MCP-ready AI assistants.

Open-source platform for autonomous coding agents that fix bugs, review PRs, and automate engineering workflows.

Open-source dev platform uniting AI, NoCode, Code, and reusable MicroApps.

Open-source AI coding agent for VS Code and JetBrains — now free to fork after the Cursor acquisition.

Tessera AI is a planned open-source, evidence-first AI coding agent for JetBrains IDEs, but the product is not downloadable and its domain is listed for sale.

Blackbox AI is a zero-data-retention inference API giving coding agents 300+ models through one OpenAI-compatible endpoint.

Open-source autonomous AI coding agent that plans, executes, and deploys tasks inside VS Code and JetBrains IDEs.

Crush is a free, open-source agentic coding assistant that runs in your terminal and wires any LLM into your CLI workflow.

Poolside builds open-weight agentic coding models you can self-host for secure, long-horizon software engineering.

Open-source coding agent that edits code and runs terminal commands across IDE, CLI, and desktop.

Open-source AI agent for desktop, CLI, and API — automate code, research, and writing with your own LLM keys or subscriptions