Cortex Terminal
The terminal for developers who use more than one AI model
What it does
Cortex Terminal connects 26 LLM providers (Claude, GPT, Gemini, Mistral, DeepSeek, Ollama, and 20 more) in a single native terminal interface. Type naturally and smart routing picks the best model. Or force a provider with c: s: l: prefixes. All models share the same MCP tool layer - configure a tool once, it works everywhere, not a web wrapper. Context-aware - reads your cwd, git status, and project files automatically. Open source. Apache 2.0. No telemetry. Local models stay on your machine.
Does the same job
all alternatives →
- OAOSS app to find LLMs across multiple LLM providers (Azure, AWS, etc.)Sep 2025 · github.com · ▲8
Scenario: Your company’s IT department says “good news, you have access to azure, aws, openai, mistral, and together AI, here are the API keys”. You think “yippee I can access many models”, but some models like the gpt-oss or Mistral are available on some or all of those platforms? That’s where this app comes in: run it and it will check all the providers that you have configured and then you can search across those providers to see which providers have the model you want available. Built on top of mozilla.ai any-llm library. Check out the link for a GIF showing it in action.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
