Machine Learning / MLOps / Data Engineering / Data Governance / Self Driving Car Engineering / Privacy Engineering
A smarter, self-hosted AI assistant — multi-user, multi-agent. - TencentCloud/Octop
A market guide to the five artifacts called ontologies: metrics layers, catalog glossaries, learned context graphs, object-action models, and ontologies of record.
Run LLMs fast on the GPUs you own with native Metal and CUDA inference.
The following article originally appeared on Duncan Davidson’s blog and is being republished here with the author’s permission.Decision records give
Tiny, open, native coding agent. A minimal CLI written in Zig, optimized for research and embeddability as part of larger systems.
A file-system approach to consolidating business knowledge as code and giving agents a more direct path from questions to execution.
As the capabilities of large language models continue to advance, so does their potential for misuse. While closed-source models typically rely on external defenses, open-weight models must...
Strands Decider 2B is a small, open source, decision model optimized for fast experimentation, local development, and innovation.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
The vocabulary for designing deep modules.
We introduce Context Language Models (CLMs), language models that natively manage their own context. We implement this by treating the context as a file and allowing the model to make unrestricted...
Discover places, get local recommendations, and explore what’s nearby with ChatGPT Maps. Find restaurants, attractions, services, and more.
Understand what data contributed the most to changes in a summable metric on your data.
Learn how GitHub’s Agentic Engineering System helps teams scale AI agents with stronger governance, shared knowledge, and customer-value feedback loops.
Build plugins that feel like native, first-class features of ChatGPT.
The Harness of Harnesses • built for RSI: a trusted, persistent, self-evolving multi-agent ecosystem for all-domain collaboration. - EverMind-AI/Raven
Compare System One models across 100+ specialized benchmarks
More than an agent. A full editor, explorer, shell, and runtime. Because you cannot trust a machine you only talk to.
