cezar is an open-source orchestrator for AI coding agents that runs Claude Code, Codex, OpenCode and others in parallel on a laptop or a VPS. It drives the agent CLIs you’re already logged into - no extra API keys, no cezar account or database - and exposes a web cockpit to queue tasks, watch runs, steer agents and review draft PRs. Every run gets its own git worktree and workflow checks (for example npm test must exit 0), failures are sent back to the agent for retries, and nothing merges automatically - changes stop at a human review gate. Install requires Node 20+ (npx cezar-run) and a one-step server install sets up HTTPS and a system service for 24/7 operation.
Orchestration includes schedules, GitHub/Jira/Linear triggers, persistent queues that survive restarts, per-workspace parallel limits and memory ceilings to keep the backlog moving. A Dispatch feature splits heavy tasks - keeping "thinking" on a stronger model and routine work on cheaper models - and runs can dispatch subtasks or switch runners and accounts mid-thread without losing context. Usage and cost reporting are shown per task; the project is MIT-licensed, developed by Patryk Lewczuk at Open Mercato, and offers a CEZAR_DRY_RUN mock-agent mode for evaluation.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
AstaBrief is an open-source model designed for fast scientific report generation, capable of turning research questions and literature into cited reports. It reduces generation time by nearly three and a half times compared to proprietary models, making it a useful tool for researchers. (allenai.org)
Shrivu Shankar argues that SaaS companies are evolving into 'harnesses,' where core tasks are performed by AI agents rather than humans. This shift transforms organizational structure, with humans overseeing and reviewing AI-driven processes within the company. (blog.sshh.io)
Three AI agents - Meta’s Muse, Anthropic’s Claude, and OpenAI’s GPT - were tested on multilingual research tasks involving U.S. and Iranian data. The experiment focused on how language and context influence agent performance across reasoning, sourcing, and artifact creation. (royapakzad.substack.com)
An open-source project named LDRAW-NOVA allows users to generate Lego models using AI. The repository contains tools, examples, and documentation for creating Lego designs with artificial intelligence. (github.com)
DwarfStar 4 (ds4) is a local inference engine that runs large language and vision models on high-memory Mac, CUDA, and ROCm machines. It supports models like DeepSeek V4 and Qwen3.8, offering CLI, APIs, and persistent cache features for efficient local deployment. (dwarfstar.sh)
Rai is a CPU-only large language model inference engine written entirely in Rust. It aims to provide efficient and pure Rust solutions for LLM deployment without relying on GPUs. (github.com)
Today's best Hacker News stories, summarized and screenshotted, one email a day.