Halv
Make your AI coding plan last twice as long
Every turn, coding agents resend files, diffs, instructions, and logs they have already seen. Halv removes that wasted context locally before each request reaches the model. You can keep the same CLI, login, model, and subscriptions for Claude Code, Codex, Kimi, and GLM while getting far more work from your plan. Halv also includes split terminals, multi-agent workflows, local sandboxing, a Crux code index, command filtering, and a live savings meter with a receipt for every answer.
More like Halv
Startups doing something similar, featured in the last two years
Give your AI persistent context across projects
Receive diverse AI perspectives in one synthesized answer
Message privately without a phone number, ads, or tracking
Run code, tools, and AI agents together in a single local workspace
One workspace for humans and AI teammates to run ops
Search all your AI chats locally and jump to exact messages
Define your task and get a fine-tuned model you can run anywhere
Query multiple LLMs, compare outputs, and auto-route the best
Ask three top AIs and get one better answer
All your favourite GenAI models in one workspace