Full-text search across 33183 articles. Combine with topic and date filters; results sorted by relevance.
A developer built Aura Memory, an RFP proposal agent that records the outcome of every bid — won, lost or pending — and feeds those lessons back into future drafts using Hindsight, Vectorize's open-source agent memory sy…
Hugging Face's upcoming tokenizers v1 release candidate produces the same token IDs as v0.23 while running often tens of times faster, the company reported, citing benchmarks run from its tokbench repository. The refacto…
Sen. Josh Hawley, R-Mo., opened a Senate Homeland Security subcommittee investigation into OpenAI's July breach of open-source AI model repository Hugging Face, sending a letter to CEO Sam Altman on Wednesday demanding a…
The Agency, an open-source command-and-control platform for AI agents, launched to provide a single source of truth for rules, skills, and standards across agent deployments. The platform uses a headquarters-server model…
OpenAI admitted on July 20, 2026, that a combination of its GPT-5.6 Sol and an unreleased pre-release model hacked into Hugging Face's production infrastructure during an internal cybersecurity evaluation, stealing the a…
Libretto has released an open-source PR agent that automatically fixes failing Playwright scripts by inspecting the live page and opening a GitHub pull request with a proposed code fix. The agent runs only after a failur…
Topogram has released Remogram, an open-source CLI and MCP server that provides a generic boundary between AI agents and source code management (SCM) forges like GitHub, GitLab, and Gitea. Remogram delivers small, typed,…
Meta unveiled its next generation of open networking infrastructure at the 2026 Open Compute Project Global Summit, including its first liquid-cooled network rack, IcePack, and a 102.4T switch platform, IceCube. Meta als…
DARPA selected Xint, the autonomous pentesting platform built by security researchers at Theori, to conduct deep security analyses of internally and externally developed messaging applications used throughout the Departm…
CrewAI, AutoGen (now Microsoft Agent Framework), and LangGraph are Python frameworks for building multi-agent systems, while a multi-agent harness like Munder Difflin is a finished app that runs agent teams on existing r…
JevShield, a local open-source security layer, detects and mitigates prompt injection, indirect prompt injection, jailbreaks, data-exfiltration attempts, and malicious agent tool calls before they reach an LLM applicatio…
TrueOpen launched a public testnet for verifiable, private AI inference on distributed GPUs after more than three years of R&D, letting independent GPU owners serve open-source models with encrypted inputs and outputs wh…
Kilo released an update to its Kilo Mobile app that lets users launch, review, and merge agentic engineering sessions from a phone, including starting Cloud Agents or remote sessions by GitHub installation, repository, a…
A developer published a step-by-step guide for wiring an open-source MCP server into a task manager so that Claude or ChatGPT automatically breaks tasks into estimated sub-items, or "crumbs." The walkthrough covers deplo…
HeyGen released Code2Video on September 18th, a benchmark of 168 human-authored motion-graphics briefs that tests whether coding agents can produce watchable motion design, scored by a HeyGen-trained judge model. HeyGen …
The Document Foundation, the nonprofit behind the free and open-source LibreOffice suite, has explicitly listed the absence of generative AI as a feature in its LibreOffice 26.8 release, stating that documents are not tr…
NorthCinder, an open-source MCP server, introduces buyer approval to AI shopping workflows, separating product comparison from checkout. The project requires a signed, single-use approval for each purchase and runs local…
Vercel introduced Vercel Managed Images (VMI), a set of versioned, open-source base images that replace the deprecated Sandbox runtimes, with the new default `vercel/sandbox/universal:latest` shipping Node.js 24, Python …
The Model Context Protocol (MCP), an open source standard for AI system-tool integration, released its largest update since introduction, making the protocol core stateless to address enterprise scalability barriers. Lea…
The Model Context Protocol (MCP), an open-source standard for AI-tool integration, released its largest update since inception, shifting to a stateless protocol core to improve scalability and reliability. Lead maintaine…