ACM TRACKER
Time tracking that knows what your AI agents really cost
What it does
Self-hosted time + cost tracker. Local app, remote DB, single source of truth for what work reallOpen-source, self-hosted time + cost tracker where AI agents report their own work through MCP. Every task merges human time (hours × rate) with real AI spend (tokens × per-model price) on one timeline. See burn rate, margin per project, and cost per person — human + their AI. Connect Claude Code with 2 commands. Runs as a desktop app, single Docker image, PWA, or Helm chart. no per-seat pricing.
Does a similar job
all alternatives →
- IQI quit my job and made an automatic time tracker2024 · taimapp.io · ▲136
Hey Hacker News! This is my first post here. About 5 months ago, I left my job because I was completely burnt out. After taking some time off, I started freelancing. But I found tracking my time to be a real hassle as I kept forgetting to start or stop the timer and often had no idea what I’d worked on. So, I decided to build Taim as a side project, while also working now on some freelancing gigs. Taim is going to be automated time tracking tool for freelancers and teams. It’s designed to make tracking time effortless and accurate, so you can focus on your work and not worry about the clock.…
- RTReal-time dashboard for Claude Code agent teamsApr 2026 · github.com · ▲77
This project (Agents Observe) started as an exploration into building automation harnesses around claude code. I needed a way to see exactly what teams of agents were doing in realtime and to filter and search their output. A few interesting learnings from building and using this: - Claude code hooks are blocking - performance degrades rapidly if you have a lot of plugins that use hooks - Hooks provide a lot more useful info than OTEL data - Claude's jsonl files provide the full picture - Lifecycle management of MCP processes started by plugins is a bit kludgy at best The biggest takeaway 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 · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d 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, June 2026
the whole month →
Fundraisly▲1,544AI fundraising agent that finds investors and books meetings
AI · Jun 2026 · fundraisly.com
- H6Homebrew 6.0.0▲1,481
Today, I’m proud to announce Homebrew 6.0.0. The most significant changes since 5.1.0 are a new tap trust security mechanism, the new faster, smaller, default internal Homebrew JSON API, sandboxing on Linux, better defaults informed by our user survey, many brew bundle improvements, improved performance and initial support for macOS 27 (Golden Gate). Happy to discuss any questions here!
Dev tools · Jun 2026 · brew.sh
- PU
hope you enjoy
Life & fun · Jun 2026 · vorpus.github.io
- IM
Life & fun · Jun 2026 · hackernewstrends.com