Show HN: Company-as-Code –> Spec and Validator
Pirol-ai released Company as Code, an open standard and validator tool called charta that lets organizations describe goals, roles, processes and policies as plain markdown files in git so AI agents c…
Pirol-ai released Company as Code, an open standard and validator tool called charta that lets organizations describe goals, roles, processes and policies as plain markdown files in git so AI agents c…
Developer hongnoul released gwae, an open-source infinite-scroll terminal multiplexer for running fleets of CLI AI coding agents, installable via curl or Homebrew on macOS. Gwae adds a heads-up displa…
NobodyWho released an open-source inference engine that runs large language models locally and offline, built on llama.cpp and distributed as version 2.0.0 across Kotlin, Swift, Python, Flutter, React…
Nvitop is an open-source interactive NVIDIA GPU process viewer and monitoring tool that queries device status directly through NVML Python bindings rather than parsing nvidia-smi output. The package s…
HasData benchmarked eight DuckDuckGo MCP servers across twelve searches and three passes on 2026-09-15, publishing the harness and fixtures on GitHub. free-search-mcp and HasData's own hosted server e…
Developer shakefu released Yass, a specification syntax that uses RFC2119 keywords in a minimal YAML format, entering public beta. The Yass CLI was validated across 7 languages — TypeScript, Python, G…
A developer released use-citations, an MIT-licensed Claude Code skill that saves source documents, answers research questions from them, and builds a report where each sourced phrase opens a slide-out…
Unreal Labs released Unreal Agent, an async-first agent harness organized into a harness library, cmd executables, and benchmark runners. The harness defines an input/inbox/session model with a coordi…
RondoFlow launched as an open-source, invite-only tool that lets users visually orchestrate teams of Claude Code agents on a drag-and-drop React Flow canvas, running locally via npm or Docker. The too…
A developer released agent.sh, a single-file AI agent written in pure bash and awk that runs on the shell with only bash, curl and awk as dependencies. The script talks to OpenAI-compatible Chat Compl…
Supreme Computation demonstrated on a live Ubuntu machine running Linux 7.0.0-31-generic that a process placed under its governance can be blocked before execution, with Linux itself returning EACCES …
A developer released Kern.md, an open-source agent runtime published on npm as kern-ai, that gives a single AI agent one persistent session shared across multiple messaging interfaces including Telegr…
A developer released livenerf, an open-source benchmark built on the UK AI Security Institute's Inspect framework, to detect whether Anthropic's Claude Opus 5.5 degrades after its 2026-09-22 launch. T…
Developer Tim released Tim's Markdown Reader, a free, MIT-licensed, offline Markdown viewer for macOS written in Swift, as a first public open-source release. The app renders Mermaid diagrams without …
Aetheria published a public control-plane export of its local-first agent harness for long-running AI work on a single Windows PC, labeling the release PRIVATE_AHEAD to signal the public export is not…
Morloc, a typed polyglot compiler in beta after roughly ten years of development, composes functions across languages under a common type system and generates CLIs, APIs, and MCP tool definitions from…
Maki v0.5.5, an AI coding agent built by developer tontinton, topped the FrontierHarness Eval benchmark, according to a report published September 19, 2026. Maki's index tool uses tree-sitter to parse…
ToolHub, a self-hosted open-source platform for orchestrating tools for AI agents, launched as a Show HN project that organizes 30 MCP tools into a hierarchical folder tree navigated via listTools() a…
A curated GitHub list of Rust and GPUI desktop applications highlights GitComet, an open-source Git workflow interface with 865 stars, and Arbor, a native desktop app for agentic coding workflows with…
A developer released Shrewd, a project that distills labels generated by frontier LLMs into small, single-purpose classifiers that run efficiently on-device, and published results on public datasets u…