UBEL, a free software composition analysis tool and install-blocking firewall, enforces security policies at install-time to block supply-chain attacks across dependencies, Linux packages, Docker, and…
Developer Mubashir Osmani released agent-mesh, an open-source MCP server that lets AI coding agents such as Claude Code, Codex, opencode, Gemini, and Grok communicate directly with each other, removin…
Choreo, a new DSL for web animation that verifies its own rendered output, has been released as a research artifact. The tool compiles animation descriptions into self-contained SVG+CSS and includes a…
AgentENV (AENV), a platform for running agent environments at scale powering agentic RL training for Kimi K3, launches with support for snapshot-backed environments that boot or resume in under 50 ms …
Vigilant PR v1 is a portable, workflow-agnostic AI pull-request reviewer that posts review comments on behalf of the user's GitHub identity, not a generic bot. Developed by tllongdev, it supports any …
Directed Memory Bank (DMB) is a tool-agnostic, markdown-based framework that gives AI coding agents persistent project context, eliminating the need to re-explain the stack, auth flow, and constraints…
A developer shared a VS Code settings configuration designed for beginners learning HTML, CSS, JavaScript, Python, and basic GitHub workflows. The setup removes distractions, hides AI and advanced fea…
A developer demonstrated the utility of Royston-Parmar (RP) models for causal inference in survival analysis, particularly in scenarios with non-proportional hazards where Cox proportional hazards mod…
Parley is a self-hosted LLM mesh that turns every machine on a user's network into a single private LLM cluster, with automatic discovery, routing, and TLS-encrypted inter-node traffic. The single bin…
Moonshot AI released Kimi K3, an open-weight 2.8-trillion-parameter native multimodal agentic model with a 1-million-token context window, claiming it is the world's first open 3T-class model. Built o…
NVIDIA-labs released NOOA (NVIDIA-labs OO Agents), a model-agnostic Python framework that represents AI agents as Python classes, unifying state, capabilities, prompts, and typed interfaces in a singl…
Ctxdiff, a new open-source debugger for LLM agents' context windows, lets developers see exactly what an AI model saw turn by turn, block by block, and identify the character that broke a prompt cache…
Belay, an open-source local-first security layer, gates every tool call an AI coding agent makes, blocking destructive commands, secret leaks, and dangerous MCP tool calls in under 100ms with no LLM i…
A developer known as shuu-beep has released ARC, an implementation-neutral authority protocol for AI agents that defines how authority is granted, narrowed, approved, revoked, contested, and adjudicat…
Arcade.js, an experimental project by developer qarl, uses an agentic harness with LLMs to decompile MAME ROMs into idiomatic JavaScript, demonstrated with Donkey Kong (1981) and The Pit (1982). The m…
A developer released Claude Playbooks, an open-source tool that creates isolated, shareable instances of Claude Code by managing separate CLAUDE_CONFIG_DIR directories, allowing users to run multiple …
TrueFoundry released Aitori, an open-source local proxy that intercepts AI traffic from desktop apps like Claude Desktop and ChatGPT to give companies visibility and control over model requests. The A…
A developer traced the Codex desktop app's process tree and found it is a well-architected Electron application, not a native SwiftUI/AppKit interface. The app uses React 19 with a custom conversation…
VCE-HQ, an autonomous agentic swarm system, orchestrates cloud and OS-level infrastructure operations using a state-based multi-agent architecture. The system employs a strict DAG pipeline with ReAct …
Agent Console, a local terminal dashboard for Codex and Claude Code, is now available on GitHub. The tool groups sessions by workspace, displays status at a glance, and allows native agent resume with…