Clairvoyance 0.90 ships local AI engine and Hivemind GPU sharing across a multi-agent team
draginol · x · 2026-11-06
Clairvoyance 0.90 is a major update built on two ideas: your PC can run AI models itself, and a machine with a good GPU can share it with your other devices or people you trust.
- Built-in local inference: the self-developed Locama engine ships free on every plan, running local models alongside Claude Code, Codex, Copilot, Cursor and Grok as one accessible-anywhere team of AI agents.
- Cross-hardware support: Metal on Apple Silicon, Vulkan on Windows, optional CUDA on NVIDIA cards, and Snapdragon NPU access via GenieX on Windows on Arm; it can also read your existing Ollama models without Ollama installed.
- One model folder: Locama, MLX and GenieX all read from a single directory, shareable with Ollama.
- Guided onboarding: setup recommends up to three models matched to your hardware (chat, light agent, full agent) with reasons and a Download-all button, plus a Local AI Benchmark to preview performance before downloading.
More from coding & agent
- Amazon research: self-distillation pushes weight memory to 59.9%, beating retrieval — omarsar0 · 2026-11-06
- Liquid AI's decision recipe matches Jev; new release adds on-device, modalities, primitives — helloiamleonie · 2026-11-06
- Decision models: general-purpose classifier or LLM? LoRA fine-tune wins — helloiamleonie · 2026-11-06
- LLMs are trained to predict next tokens, not make decisions — helloiamleonie · 2026-11-06
- Turn any LLM into a decision model with ~15 lines of inference-only code — helloiamleonie · 2026-11-06
- TypeSafe spent 2 years in stealth on Jev; open ecosystem copied it in under a week — helloiamleonie · 2026-11-06