I am running 3 coding agents non-stop over the last 3 days. Here is how
1. Headless mode Headless mode allows you to use the AI as a command-line utility for automation and scripting. In Claude Code you run it with the -p flag: claude -p, in codex - exec, opencode - run. 2. Ask human The traditional communication channel with the operator won't work in headless mode - we need to implement a dedicated tool. Here is an example of how this can be done https://github.com/sermakarevich/claude/tree/main/mcp/ask_hu... 3. Tasks queue Beads is a lightweight distributed graph issue tracker for AI agents, powered by Dolt. You can…
In plain words
Beads is a lightweight distributed task tracker designed for AI agents, built on Dolt. It enables users to create tasks with dependencies, set priorities and hierarchies, and prevent duplicate work assignment across multiple workers. The system supports headless operation for command-line automation, includes a dedicated tool for human communication when needed, and allows monitoring and resuming agent progress after restarts. Beads helps coordinate multi-agent workflows efficiently.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
1. Headless mode Headless mode allows you to use the AI as a command-line utility for automation and scripting. In Claude Code you run it with the -p flag: claude -p, in codex - exec, opencode - run. 2. Ask human The traditional communication channel with the operator won't work in headless mode - we need to implement a dedicated tool. Here is an example of how this can be done https://github.com/sermakarevich/claude/tree/main/mcp/ask_hu... 3. Tasks queue Beads is a lightweight distributed graph issue tracker for AI agents, powered by Dolt. You can create tasks, define dependencies between tasks, and have status, priorities, hierarchy. Beads helps prevent multiple tasks from being claimed by > 1 worker. 4. Worker artifacts We want to be able to monitor how a worker is doing, at what stage it is, and resume it after a restart. For every task we can create a dedicated folder using the beads task id and put into it what we need. I put there: - plan and status md - knowledge md - events.jsonl - stderr The worker is instructed in its prompt to check if artifacts exist, which allows it to proceed from where the job was left. 5. Worker isolation To prepare to run multiple workers we need to isolate them. Git worktree can be used here. I am testing this approach: - worker gets the task and implements it - the next worker, spawned automatically, validates the task is done, tests it, merges the worktree, closes the ticket and creates another one for a fix if required 6. Multiple workers To be able to run multiple workers we need a simple orchestrator. An infinite loop constantly checking beads / config and triggering new workers when required. 7. Coder agnostic A worker can be basically any coder. I started with Claude, added Codex and Agy. And last added Opencode. 8. Subscription limits. 3 coding agents can burn the Claude $200 subscription limit in 30 minutes even if you switch to Sonnet 4.6. API tokens cost x40 compared to tokens in the subscription - this is too expensive. The idea I am testing is: - use the strongest model possible to analyse/design and add tasks - use a local model as a worker - use a stronger model to validate workers and add new tasks to fix potential misimplementations I am using the qwen3.6:36B local model with Ollama, deployed on 2 GPU cards, 36GB in total, with a 256K context window. This is slower, but it is free of charge. And surprisingly it worked, and worked way better than I would expect it to. Fable 5 was extremely great at creating clear and simple tickets until it was. Another approach I was considering is Bedrock qwen, paying per token, or renting a 96GB GPU for $1400 per month. I found that it's optimal to run 3 workers concurrently even though Ollama processes 1 request at a time. The reason is the ask_human tool. If a worker asks me something at night - it has to wait until morning doing nothing. Running three +/- guarantees GPU load at 100%. 9. Nice integrations UI - to observe tasks / beads / config / chat / analytics It's easy to miss when a model asks a question. It's visible in the UI - a green circle near chat, but that's it. So I added a Telegram integration - now I receive questions from workers on Telegram and can reply there, get the status of tasks, create new tasks etc. I am doing this for my PoC projects ofc: - improving fleet - building a data collection and analysis related app What I am seeing is that 24x7 coders are closer than I thought they are. Even weaker models can deliver good results when the task is simple and well defined. All components for building these systems are there. Repo: https://github.com/sermakarevich/fleet
Does the same job
all alternatives →
- IRI replaced Beads with a faster, simpler Markdown-based task trackerJan 2026 · github.com · ▲84
I've been running long duration coding agents with Claude Code for about 6 months now. Steve Yegge released Beads back in October and I found that giving Claude tools for proper task tracking was a massive unlock. But Beads grew massively in a short time and every release made it slower and more frustrating to use. I started battling it several times a week as its background daemon took to syncing the wrong things at the wrong times. Over the holidays I finally ripped it out and wrote ticket as a replacement. It keeps the core concept I actually cared about (graph-based task dependencies)…
- MCMission Control – Open-source task management for AI agentsFeb 2026 · github.com · ▲45
I've been delegating work to Claude Code for the past few months, and it's been genuinely transformative—but managing multiple agents doing different things became chaos. No tool existed for this workflow, so I built one. The Problem When you're working with AI agents (Claude Code, Cursor, Windsurf), you end up in a weird situation: - You have tasks scattered across your head, Slack, email, and the CLI - Agents need clear work items, context, and role-specific instructions - You have no visibility into what agents are actually doing - Failed tasks just... disappear. No retry, no notification…
- 2C20+ Claude Code agents coordinating on real work (open source)Feb 2026 · github.com · ▲53
Single-agent LLMs suck at long-running complex tasks. We’ve open-sourced a multi-agent orchestrator that we’ve been using to handle long-running LLM tasks. We found that single LLM agents tend to stall, loop, or generate non-compiling code, so we built a harness for agents to coordinate over shared context while work is in progress. How it works: 1. Orchestrator agent that manages task decomposition 2. Sub-agents for parallel work 3. Subscriptions to task state and progress 4. Real-time sharing of intermediate discoveries between agents We tested this on a Putnam-level math problem, but the…
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, 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