Agentdesktop has launched an open-source platform that inventories AI developer tools, MCP servers, and skills across employee workstations, applies tool-native configuration and sandbox policy, and r…
SayItErmano v0.4.0, an unofficial community port of FluidVoice for Linux, is now available as a local-first voice dictation app that transcribes speech on-device and optionally polishes text via OpenA…
Aispace.sh released an open-source, scriptable CLI for secure temporary file sharing designed for AI agents and humans, featuring expiring links, predictable JSON output, and optional local age X25519…
Archprint, a new open-source tool announced on Hacker News, automatically infers architecture lint rules from a repository's import graph, generating enforcement rules for TypeScript projects without …
Quire, a new open-source tool, lets humans and AI agents edit local Markdown files together in a live multiplayer workspace, with every edit visible, attributable, and separately revertable. The publi…
Raknaos released Lightpanda Session Bridge, an open-source tool that transfers authenticated browser sessions from Chrome, Comet, or Edge into the Lightpanda headless browser via CDP, enabling AI agen…
Girder, an open-source MCP server from developer dhishwasher, gives coding agents a semantic code graph instead of whole files, cutting context bytes by 97.85% (8,765 vs 408,137 bytes) on a committed …
SwarmLLM, an open-source project by developer Nehanth, enables a Qwen 3.8 27B model to run across browser tabs on multiple devices, with each device holding a slice of the model and passing 10 KB acti…
Aria Icons, an open-source project by LeulAria, has released a Model Context Protocol (MCP) server and command-line interface (CLI) that provides access to over 340,000 SVG icons from multiple collect…
A developer has compiled a list of 20 prompts for using large language models (LLMs) in data science tasks, covering model training, hyperparameter tuning, time series forecasting, handling imbalanced…
A developer published an AI agent evaluation playbook, a repeatable test battery for vetting whether models running inside agent frameworks can be trusted with semi-sensitive content and real write ac…
MobileCode, an open-source fork of the OpenCode AI coding agent, now provides live iOS Simulator and Android Emulator previews inside the coding session, enabling developers to build, launch, and debu…
OpenLivery, an open-source multi-tenant platform for agencies to build and manage AI agents for clients, was released on GitHub. The platform supports WhatsApp and web chat channels, offers bring-your…
VMtree, a lightweight self-hosted tool written in Bash, lets developers provision ephemeral VMs instantly by SSH-ing into a new subdomain, such as `ssh demo-foo.example.com`, and uses LXD/Incus contai…
Steven P. Walsh released Possess, an open-source TUI that lets developers browse and transfer coding sessions between AI coding agents Codex, Claude Code, OpenCode, and Grok, enabling context handoffs…
A developer using OpenAI's GPT-6 Astra model completed Valve's Portal game in about 23 hours 43 minutes on September 5, 2026, with the AI agent controlling gameplay through a custom SourcePauseTool an…
A new guide by Danielle Loader, Jonathan Oppenheim, and Tobias J. Osborne describes workflows for using large language models in natural science research, emphasizing adversarial verification protocol…
Developer moiz released LLM Council 1.0.0, an open-source tool that queries four frontier LLMs in parallel with distinct personas, anonymizes their responses, and uses a chairman model to synthesize a…
Benzi, a new code intelligence infrastructure for frontier AI models, claims to reduce source code reading by 56% compared to Claude Code Sonnet, achieving 78.2% on SWE-bench Verified for under 10 cen…
A developer highlights five open-source repositories gaining traction in the AI builder community, including everything-claude-code, a configuration collection for Claude Code, and archify, an agent s…