#open source
Open Source: 50 AI articles covering open source news, analysis, and research
Articles
Nous Research Launches Bot Mode for Hermes Agent, Transforming⭐7
Nous Research launches Bot Mode for Hermes Agent, transforming profiles into named bots with shared memory and delegation via @mentions.
DeepSeek AI Releases DeepSeek Harness in Developer Preview: An⭐7
DeepSeek Harness v0.1: MIT-licensed agent harness where everything is a plugin. Swappable models, tools, and storage via Cordis, enabling custom agent runtimes.
Tech Visionary Tim O'Reilly: Big AI Labs Are Missing What People⭐8
Tim O'Reilly criticizes big AI labs for missing user needs, urging open-source, decentralized AI to prioritize usefulness, trust, and accessibility.
Meet Needle 2: An Open 45M-Parameter Tool-Calling Model That⭐7
Meet Needle 2: a 45M-parameter tool-calling model in a 14MB binary, running sessions in 28MB of RAM for edge devices.
What 50 Open Source Projects Taught Us About Security in the AI Era⭐9
50 open source projects reveal key AI security lessons: supply chain risks, data poisoning, and prompt injection threats. Essential insights for developers in 2...
Your Contributors Are AI-First Now. Is Your Project?⭐9
Is your open source project ready for AI-first contributors? Learn key strategies to adapt workflows, docs, and tools for 2026.
NVIDIA Unveils Nemotron 3.5 Lightning: A 30B Open MoE with 3B⭐8
NVIDIA launches Nemotron 3.5 Lightning, a 30B open MoE with 3B active params, plus NeMo Switchyard router for faster, efficient AI agents.
Meta Unveils Muse Glimmer: Local, Agentic, Multimodal, and Open Source⭐8
Meta unveils Muse Glimmer: an open-source, multimodal AI that runs locally and autonomously, now on Hugging Face for developers.
Tencent Cloud Open-Sources TencentDB Agent Memory v2.0: A⭐8
Tencent Cloud open-sources TencentDB Agent Memory v2.0, a team-level memory hub for AI coding agents, enhancing context reuse and governance across sessions.
Microsoft Open Sources Code-Testing Generator: A Polyglot⭐6
Microsoft's new open-source code-testing generator boosts unit-test task completion from 78.9% to 92.1% versus Copilot, auto-validating tests locally.