Halv
Make your AI coding plan last twice as long.
What it does
Your coding agent resends files, diffs, instructions, and logs it has already seen. Halv cleans that wasted context locally before each request reaches the model—so you keep the same CLI, login, model, and subscriptions while getting far more work from your plan. It supports Claude Code, Codex, Kimi, and GLM, with split terminals, multi-agent workflows, local sandboxing, a Crux code index, and a receipt showing the usage saved on every answer. Available on macOS, Windows, and Linux.
Run Claude Code, Codex, Kimi, and GLM in one desktop workspace. Halv used 51.1% fewer tokens per correct answer in 20 paired SWE-rebench tasks.
Run Claude Code, Codex, Kimi, and GLM side by side in one desktop app. Keep your subscriptions. Halv cuts wasted context while you work. Measured on the first 20 paired SWE-rebench tasks with Codex. Results vary by task and model. Open a project. Choose your agent. Work in chat or native terminals, with your sessions, changes, and savings in one place. Use Claude Code, Codex, Kimi, and GLM with the subscriptions you already have. Run multiple agents together. Move between chat and native terminals. Split panes across tasks, organize projects, and return to saved sessions. Review changes, set approvals, and track agent activity and token savings from your workspace. We ran the same 20…from halv.ai
Does the same job
all alternatives →
- HNHydra – Never stop coding when your AI CLI hits a rate limitApr 2026 · github.com · ▲9
I built Hydra because I kept losing my flow when Claude Code hit usage limits mid-task. I would copy context, open another tool, and then re-explain everything. This would be super annoying for me. Hydra wraps your AI coding CLIs (Claude Code, Codex, OpenCode, Pi, or any terminal-based tool) in a single command. It monitors terminal output for rate limit patterns, and when one provider runs out, you switch to another with one keypress. Your conversation history, git diff, and recent commits are automatically copied to your clipboard so you can paste and keep going. The fallback chain is…
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 · 16d 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 · 26d ago · cactuscompute.com
Launched alongside, September 2026
the whole month →
OpenTrailPaper is open-source bike computer firmware for the LilyGO T5S3 4.7" E-Paper PRO. It supports offline maps, GPX routes, FIT recording and Bluetooth sensors.
Dev tools · 1d ago · opentrailpaper.com
Run Qwen3.8-Flash-Next (125B MoE, 104 GB at 4-bit) on Macs with a fraction of that RAM by streaming experts from SSD. MLX + Swift, Ollama-compatible API. - carloslfu/slotstream
Dev tools · 4d ago · github.com
Weedout is a Safari extension that filters out videos YouTube labels as “Made with AI”.
AI · 4d ago · masteranza.github.io
NPC-Forge is a framework for building conversational agents that run on the CPU without relying on machine learning or LLMs. - NPC-Forge/docs/development.md at main · gioblu/NPC-Forge
AI · 1d ago · github.com
Find your next hire or your next role from Hacker News monthly threads. AI-powered matching between candidates and job postings.
AI · 4d ago · hnmatchmaker.com
I made OwnTime to balance between competing priorities in my life. The idea is based on two main influences: the concept of "roles" from "The 5 Choices" (2015), and my repeated failure to effectively implement time blocking due to the necessary flexibility in my role. The app allows you to define time budgets, which are not much more than a few mutually exclusive countdown timers. The UX is essentially that of a chess clock for an arbitrary number of players with configurable time. The whole point of the app is to kick you out of the running role/priority when its time is up. One…
Life & fun · 4d ago · owntime.app