Show HN: NanoMuse – An open-source AI agent for your phone and computer
Article URL: https://github.com/nano-muse/nanoMuse Comments URL: https://news.ycombinator.com/item?id=49987765 Points: 18 # Comments: 2
Hacker News6 min read
Model Context Protocol
2,098 stories
OpenAI's math avalanche continues
OpenAI's math breakthroughs continue, with 700+ papers claiming to solve open problems. Plus: learn how to compare software websites with GPT-6 Astra in ChatGPT Work.
The Rundown AI8 min read
GLM 5.3 Flash as a coding agent: a month of daily use, $68, and the slot it kept
A Wagtail maintainer ran 1B tokens of GLM 5.3 Flash in September for $68 and kept it as the default for 95% of tasks. The costs, the setup and what breaks.
Stackness Blog10 min read
OpenSearch veterans launch Infino. Here’s why it matters for agent builders.
Software vendors like to claim unified systems that act as a so-called single pane of glass for any given coding The post OpenSearch veterans launch Infino. Here’s why it matters for agent builders. appeared first on The New Stack.
The New Stack - AI7 min read
MCP Explained: How Model Context Protocol Is Changing AI Development in 2026
Originally published on Codeloop Software. Quick answer: MCP (Model Context Protocol) is an open standard created by Anthropic that defines how AI applications connect to external tools and data sources — like USB for AI, you build one MCP server and any MCP-compatible client can use it.
Dev.to AI5 min read
How I set up Claude Code: one rulebook, a 12-step relay to use it daily
Claude Code used to feel like a brilliant teammate with no onboarding. Some days: tests first, small diff, asked before pushing. Other days: no tests, three "cleaned up" files, a PR opened on its own. The model wasn't the problem.
Dev.to AI10 min read
How AI Agents Remember: A Practical Guide to Agent Memory
Imagine hiring a brilliant colleague who forgets every conversation overnight. Each morning you re-explain the project, your preferences, and what you decided yesterday. They are capable, but they never get better at working with you. That is an AI agent without memory.
Dev.to AI8 min readSoftware That Never Breaks: OutSystems CEO Woodson Martin on Building Enterprise-Grade Apps at AI Speed
OutSystems CEO Woodson Martin discusses how enterprise platforms maintain software reliability and security in the era of AI-generated code. He explains why mature compliance, deterministic generation, and cost-effective model routing give incumbents an edge over AI startups.
Cognitive Revolution53 min read
OpenAI Codex CLI rust-v0.161.0
OpenAI Codex CLI rust-v0.161.0 now defaults to the faster GPT-6.1 Sol model and lets you customize your microphone and speaker settings for voice conversations. You can also log into MCP servers directly from your terminal and get more control over how the CLI accesses your sy...
Havoptic Blog1 min read
GitHub Copilot CLI v1.0.93
GitHub Copilot CLI v1.0.93 brings smarter command handling with real-time sandboxing for all users and improved permission controls for enterprise environments. Key updates include faster plugin reloading, seamless MCP server configuration changes between turns, and better Git...
Havoptic Blog1 min read
Best AI Receptionist Software: Rent a Receptionist or Own One
Best AI receptionist software, split into ready-made products and build-your-own platforms, with list prices in each vendor's own unit and who can self-host.
Dograh Blog11 min read
The Ultimate Guide to AI Receptionists: Judge Them by the Handover
An AI receptionist answers, books and transfers calls. See how it works, what it costs next to a human or answering service, and why the handover matters most.
Dograh Blog14 min read
This extension lets your AI agent create artifacts for plans, workarounds and designs in Cursor, Codex and GitHub Copilot
This guide uses an extension called AI Artifacts to let Cursor, Codex or GitHub Copilot produce a plan, workaround note or design as a separate document, an artifact, inside your IDE. You can comment on exact passages and send all feedback back in a single step.
Dev.to AI5 min read
AgenticOS: self-hosted AI agents your whole team can improve
AgenticOS: self-hosted AI agents your whole team can improve Vstorm AgenticOS is an open-source, self-hosted platform for company AI agents. It lets you build your own AI agents in a browser, give them access to your documents, and choose the tools they can use, on infrastructure you control.
Dev.to AI9 min read
Founder story: why I'm building this
There's a specific moment that stuck with us. We were watching a demo of an agent doing real work inside a SaaS product — clicking through dashboards, filling forms, looking genuinely useful. And then the question hit: would you trust that agent to do this at 3 AM, unsupervised, when it matters?
Dev.to AI2 min read
Meet BugTraceAI: an open-source, self-hosted agentic pentester
Every security team knows the pattern: you want a proper assessment of an app, but the options are waiting weeks for a consultancy slot, or stitching together a dozen tools and babysitting them for days.
Dev.to AI3 min read
OpenAI's math avalanche continues
OpenAI's math breakthroughs continue, with 700+ papers claiming to solve open problems. Plus: learn how to compare software websites with GPT-6 Astra in…
The Rundown AI Blog8 min read
New Apify Store categories: browse by the job, filter by what you get back
Apify Store categories are being rebuilt around the job you're trying to do - a use-case tree plus filters for industry, site, output, and Actor type.
Apify Blog3 min read
Showing 414 of 2,098 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts