[tag]
56 stories
The new service uses Anthropic's strongest models to provide free, automated vulnerability reports to opted-in open-source projects, trading human triage for speed and frequency.
The open-source Hermes Agent startup is pivoting to enterprise with a new product line, backed by Nvidia and a $1.5 billion valuation.
Amazon's new lightweight decision model offers a high-speed, low-cost alternative to frontier LLMs for structured agentic workflow steps.
The new toolkit provides isolated cloud desktops, local VMs, and specialized 'System 1' decision models to help AI agents navigate graphical interfaces without moving your cursor.
A new open-source tool provides a unified control plane for AI coding agents, using a dynamic context injection system to keep model windows clean while supporting any LLM backend.
A new MIT-licensed toolkit provides the rules, gates, and backend conventions of platforms like Lovable and Bolt, but runs locally within your existing coding agent.
The open-source AI agent framework has shipped two consecutive major releases, signaling a push toward rapid iteration and feature stability.
At Ai4, three leading AI researchers defended open AI against a backdrop of safety concerns, but their visions for openness diverged on key details.
Oldhand is a new open-source plugin that gives Claude Code and Codex agents a structured workflow—from ticket to verified end-to-end result—without requiring tracker integrations or MCP servers.
A new open-source MCP server centralizes discovery and installation of AI agent skills across popular coding tools.
Researchers introduce ADIAS, a modular framework for designing and coordinating specialized AI agents, aiming to simplify agent-based system development.
A new open-source project turns the homepage into a live canvas for AI coding agents, one merged pull request at a time.
A new npm-based, extensible coding-agent platform aims to bring multi-worker orchestration, durable sessions, and security guardrails to AI-assisted development.
The project’s new policy on generative AI in contributions is a pragmatic middle ground that leaves quality and responsibility where they always were.
An open-source, game-agnostic reimplementation of AlphaZero achieves perfect play in Hex and grandmaster-level chess — if you have a TPU.
A new open-source library, Hermes Missions, promises lightweight, crash-safe durable execution for AI agents without external dependencies.
The AI model hub is reportedly weighing acquisition offers at a valuation of $13 billion or more, raising questions about the future of its open-source community.
Zuse is an open-source platform that turns a GitHub issue into a planned, coded, tested, and PR-ready change using your existing AI subscriptions.
A new open-source tag generator promises faster, more accurate code navigation for Vim and Neovim, powered by tree-sitter and WASM extensibility.
An open-source desktop app and control plane that spins up isolated git worktrees and lets Claude Code, Codex, OpenCode, Grok, and more work side by side.
A new open-source benchmark runs coding agents in hardened, enterprise-style sandboxes to quantify the capability cost of security controls.
A new open-source sidecar translates YAML-described REST endpoints into MCP tools, so legacy APIs can join the AI tool ecosystem in minutes.
A new open-source agent framework aims to make OpenFOAM more accessible by automating setup, case preparation, and post-processing through natural language.
A new open-source memory compression fabric claims up to 384x KV-cache reduction with >94% semantic retention, aiming to unblock long-context inference.
Syncular brings offline-first sync to SQLite with a server-owned commit log, native clients across platforms, and a conformance-tested wire protocol.
Goulash is a free, open-source overlay that brings LLM suggestions directly into your shell, keeping you in the zone without context-switching to a browser or agent.
Velorn is a desktop video editor that layers an AI workstation on top of ComfyUI, offering agents 100+ MCP tools for a fully automated editing pipeline.
Aurora is an Apache-2.0, self-hosted gateway that lets developers route requests to dozens of AI providers through a single OpenAI- or Anthropic-compatible API.
A new tool runs an npm package's install scripts in a sandbox and returns a signed verdict — a useful, if bounded, addition to the supply-chain security toolbox.
A new open-source tool turns completed PRs and coding sessions into hidden-test tasks to compare AI coding agents on your codebase.
