Fresh AI news
OpenAI urges U.S. lead on global frontier AI technical standardsOpenAI, Anthropic near deal to stress-test each other's AI modelsSoftBank launches ~$11B bonds to fund OpenAI investment trancheMicrosoft's Mustafa Suleyman: China isn't an excuse to skip AI guardrailsNvidia's Jensen Huang emerges as Trump's top ally in the AI safety debateLawsuit: Anthropic, OpenAI, SpaceXAI, Google illegally agreed to slow AIAnthropic weighs new model launch ahead of IPO as Astra gains enterprise shareGoogle: Gemini hacked three companies in Irregular cyber eval, then stoppedAnthropic taps Accenture Faculty as first embedded frontier AI evaluatorCalifornia EO N-9-26: Newsom advances AI kill-switch recommendationsMeta Muse arrives on Mac with native app actions across files and mailNVIDIA launches AIPerf to benchmark LLM inference at scaleOpenAI's Sam Altman to brief UN Security Council on AI securityAlibaba Qwen3.8-Omni-Flash ships 1M-token audio-video agent modelOpenAI urges U.S. lead on global frontier AI technical standardsOpenAI, Anthropic near deal to stress-test each other's AI modelsSoftBank launches ~$11B bonds to fund OpenAI investment trancheMicrosoft's Mustafa Suleyman: China isn't an excuse to skip AI guardrailsNvidia's Jensen Huang emerges as Trump's top ally in the AI safety debateLawsuit: Anthropic, OpenAI, SpaceXAI, Google illegally agreed to slow AIAnthropic weighs new model launch ahead of IPO as Astra gains enterprise shareGoogle: Gemini hacked three companies in Irregular cyber eval, then stoppedAnthropic taps Accenture Faculty as first embedded frontier AI evaluatorCalifornia EO N-9-26: Newsom advances AI kill-switch recommendationsMeta Muse arrives on Mac with native app actions across files and mailNVIDIA launches AIPerf to benchmark LLM inference at scaleOpenAI's Sam Altman to brief UN Security Council on AI securityAlibaba Qwen3.8-Omni-Flash ships 1M-token audio-video agent model

Projects

A collection of things I've built. Explore the source on GitHub or try the live demos.

Codex Astra/Luna Orchestrator

Use Astra as the orchestrator and Luna for subagents in Codex. 1.5k+ stars on GitHub.

PythonCodexAgents

Local Evals

An eval app that runs locally and uses local models or any OpenAI-compatible API.

TypeScriptEvalsLocal AI

Coworker

Personal and work AI agents designed for non-technical people. Easy to use, supports local and cloud models.

TypeScriptDesktop AppAgents

Agent Monitor

Visualize your Codex and Claude Code subagents with an advanced traces view, token breakdown, and cost usage.

TypeScriptCodexClaude Code

JSONL Viewer

A desktop Electron app for viewing and editing .jsonl / .ndjson files used for fine-tuning and training datasets.

ElectronJavaScriptJSONL

GAIA Personal Setup

Installer for running multiple private Hermes Agent assistants on your Mac or Windows PC as Docker containers.

HermesDockerGo

AI Backends API server

API server runtime for common AI use cases with multiple models and providers. Run locally with Ollama or LM Studio, or in the cloud via OpenRouter, OpenAI, Anthropic, or Google.

TypeScriptAPIOllama

Skillsbento

Free agent skills for Claude Code covering business analytics, market research, financial analysis, and social growth.

Claude CodeAgent Skills

Hermes Profiles

Installable Hermes Agent profiles for legal assistant, real-estate, home manager, and content creator, each with soul, config, skills, and cron templates.

HermesShellProfiles

Cursor Go SDK

An unofficial Go SDK for the Cursor Cloud Agents API, with typed REST methods, streaming, artifacts, and a high-level agent workflow.

GoCursorCloud Agents

AI Backends (Python)

A Python library to run AI tasks locally on your GPU.

PythonLocal AIGPU

Markdown Editor

A lightweight markdown editor with AI features. Works with Ollama and LM Studio.

JavaScriptOllamaLM Studio