Repo · Routing & model choice
Nectra
One chat in front of Claude Code, Codex, Gemini CLI and Ollama: each message is classified and routed to the model that should answer it, then that…
Open github.com ↗From the repository
One chat for every AI model you have. Nectra routes each message to the best-fit model across Claude Code, Codex, Gemini CLI and Ollama, sends easy prompts to cheaper models to save tokens, and runs each agent in its real terminal.
ai-agentsai-routerai-toolsclaude-codeclicodex-clicoding-agentscost-optimizationdeveloper-toolsgemini-clijevllmllm-routerllm-toolsmodel-routermulti-agentollamarustterminaltoken-optimization
How builders describe it
One chat in front of Claude Code, Codex, Gemini CLI and Ollama: each message is classified and routed to the model that should answer it, then that provider's real terminal opens.
The decision Jev makes
Pick an agent, a model, a skill from a catalog, or a function and its arguments.
Where it fits
Deciding which agent, model, skill or function should handle a request. Jev is a natural router: the options are fixed and the confidence tells you when to fall back. All 348 routing & model choice projects →