Parallax – Coordinate adversarial AI agents over durable streams
Parallax is a CLI for orchestrating independent AI agent cohorts (Claude, Codex, etc.) over isolated, append-only logs or streams. Each cohort operates on its own log and does not see the intermediate reasoning of others i.e. disagreement is enforced at the infrastructure layer rather than prompted at runtime. Agents write to sequenced, durable logs and a separate moderator agent subscribes to all streams, monitors progress, issues steering instructions when necessary, and synthesizes outputs at the end. That means, coordination is just done over a log with natural language, which allows us…
What it does
In the maker’s words, at launch
Parallax is a CLI for orchestrating independent AI agent cohorts (Claude, Codex, etc.) over isolated, append-only logs or streams. Each cohort operates on its own log and does not see the intermediate reasoning of others i.e. disagreement is enforced at the infrastructure layer rather than prompted at runtime. Agents write to sequenced, durable logs and a separate moderator agent subscribes to all streams, monitors progress, issues steering instructions when necessary, and synthesizes outputs at the end. That means, coordination is just done over a log with natural language, which allows us to rewire topology of agents mid-run, fork, merge, spawn breakout rooms or build any research methodology on the fly depending on the question. If something goes wrong / crashes, agents can resume from where they left off. Further, if the log or stream is serverless, agents can connect over the log from any machine anywhere in the world and collaborate on tasks / research.
Does the same job
all alternatives →
- DADeltix – AI Driven Testing22d ago · app.deltix.ai · ▲54
Write a task in plain English. An AI agent runs it on a simulator on your Mac and tells you if a real user could complete it. Save the successful run as a regression check you can replay later.
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, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
