Full-text search across 32902 articles. Combine with topic and date filters; results sorted by relevance.
OpenClaw has released a new installer for macOS that provides a native app UI for onboarding, alongside frictionless local model setup for Windows PCs with NVIDIA RTX GPUs, aiming to reduce setup time from over 30 minute…
A developer built Nyora, a free, open-source manga reader that works across Android, iOS, macOS, Windows, Linux, Web, and Docker, featuring AI-powered on-device translation and cross-platform sync without requiring an ac…
Honeycomb completed a multi-month migration of its Kafka infrastructure from self-hosted Confluent Platform and ZooKeeper on AWS EC2 to open-source Apache Kafka 4.1.1 running in KRaft mode on AWS EKS. The migration was p…
An open-source pipeline called ai-trains-ai uses nested reinforcement learning loops where an outer agent is RL-trained to write inner training jobs for small models, with the entire system run for roughly $1.3k on real …
DeepReinforce released Ornith-1.0, an open-source family of coding models that learn to build their own task scaffolds, moving intelligence from the surrounding harness into the model itself. The models, ranging from 9B …
Nvidia's Deepu Talla discusses the state of physical AI and robotics, highlighting that the industry is still in early stages with only a million or two robots shipped annually against a tens-of-billions opportunity. He …
FablePool launched a crowdfunding platform where users pool money behind a single AI prompt, and an autonomous agent builds the requested project in public. Funding starts at $0.25 per backer, with projects requiring at …
Typemill, a lightweight flat-file CMS, announced feature highlights including a dedicated AI-assisted writing interface called Kixote that connects with any AI provider using an OpenAI-compatible or Anthropic API, such a…
Independent developer Pedro Shakour released grok-build-ios on July 18th, an open-source SwiftUI client that lets developers control xAI's Grok Build coding agent from an iPhone. The app communicates with a Mac over xAI'…
ToolJet released ActionRail, an open-source runtime value and action grounding framework for AI agents, now in public beta with a planned v1 for August 2026. ActionRail intercepts agent tool calls and validates each argu…
A developer building ARIA, a free AI tutor for 1.6 billion children across 35 languages, discovered a severe gap between test and real-world performance: the system scored 94% on automated Socratic compliance tests but o…
Andrew Dai, co-founder and CEO of Elorian AI, discusses the departure of lab builders from the AI industry in an interview with Open Source CEO. The interview explores the shifting landscape of AI research and developmen…
Ollaya, an Apache-2.0 open-source runtime that runs decision models locally, hit the Hacker News front page with nearly 500 points and offers a TypeSafe-compatible API as an alternative to TypeSafe's Jev, which launched …
FusionAuth documentation engineer Nathan Contino reports that AI agents cannot yet produce consistently accurate documentation, so the company keeps long-form content, tutorials and release-note editing human-written whi…
Continue, the open-source coding agent for VS Code, has been acquired by Cursor and its repository is now read-only, with the company stating it is no longer actively maintained. The acquisition ends active development o…
Codeberg, a Git code hosting platform, has banned projects that consist mostly of generative-AI-written code, sparking debate. The decision highlights a gap in the open-source space: while many Git hosting alternatives e…
A developer building a SaaS platform in Sri Lanka for handling sensitive documents is seeking advice on whether to combine global knowledge, internet search, and user-specific RAG. The developer is considering two archit…
Dailybot released Deep Work Plan, an open-source methodology that turns any repository into a spec-driven harness for AI coding agents, enabling long-horizon tasks with reduced drift. The tool generates repository-specif…
Jern Cloud launched a governed cloud coding agent that operates under a repository-pinned policy file, with sessions running on isolated machines, hard token caps, and encrypted evidence, delivering pull requests for hum…
AI research lab Martian has launched Code Review Bench, an open, MIT-licensed benchmark that scores AI code review tools on precision, recall, and F1 across 16,017 real open source pull requests where developers actually…