AI tool

OpenAPPA is an open-source deterministic guardrail and information-flow policy engine for LLM agents. The page describes flow-based security labeling, CI validation, remedy plans, sanitizers, authorities, and subagents, with links to docs, GitHub, Discord, and benchmark claims.

A Vercel article showing how to use GPT-6 Sol with the AI SDK evaluation API to assess draft replies, score evidence-based answers, and read structured results in TypeScript.

AI code security scanner that reviews a repository, flags exploitable issues, and provides a scoped fix prompt for each finding.

Focal Prompt is an analysis lab for studying how prompts and prompt sections influence model behavior. It includes focus labeling, prospective and retrospective focus prediction, baseline output sampling, ablation tests, batch analysis, and an agent builder.

A LangGraph-based workflow that generates, benchmarks, validates, and iterates CUDA kernels using a C++/CUDA harness. It targets workload-specific optimization with support for NVIDIA research lookup and optional Nsight Compute profiling.

A local gateway for Claude Code that logs tool calls, enforces approval rules, and trims noisy tool output to save tokens.

A Mac notch app that surfaces Claude Code and Codex approval prompts in the menu bar/notch so developers can approve or deny requests without switching back to the terminal.

A VS Code extension that turns codebases into an interactive call graph and exports compact execution context for AI assistants. It also helps review staged, branch, and PR changes by showing impact and blast radius.

Open-source coordination protocol for coding agents that helps detect intent conflicts before code conflicts, built above Git and integrated with tools like Claude Code, Codex, and Cursor.

Open-source cross-platform SSH/SFTP client and server manager with live telemetry, split-pane workflows, self-hosted end-to-end encrypted sync, and MCP/AI integration.

An unlisted pastebin for HTML or Markdown files that’s built for coding agents and quick sharing. It supports one-command publishing, agent-driven workflows, and renders Markdown into readable pages.

CLI tool that monitors usage limits and automatically hands off between Claude Code, Codex, agy, and Grok in the same terminal.

Open-source control plane and proxy for managing multiple MCP servers behind one endpoint, with routing, policy, auth, logging, and rate limiting.

A public guide to principles for building reliable LLM applications and production-ready agents. The page lays out 12 factors, with discussion of tool calls, context windows, control flow, human handoff, and state handling.

A framework for dbt development that uses AI agents with structured specs, deterministic infrastructure controls, and numeric diffs instead of code-only review.

A benchmark writeup comparing GraphQL-over-MCP and REST-over-MCP setups, showing lower token use and inference cost for GraphQL in agentic tasks.

A macOS voice assistant for Claude Code that talks through project ideas, writes specs, launches builds, and alerts you when a session needs attention.

AirmailAI is a BYOK LLM chat app with a browser-extension backend that lets users connect their own keys and chat with providers like OpenAI, Anthropic, Google, and OpenRouter. The page highlights privacy-by-design messaging, file upload, web search, and zero-markup pay-as-you-go usage.

An offline desktop time tracker for Windows and macOS that automatically logs app and website activity, classifies work locally with on-device AI, and helps prepare client invoices without cloud syncing or manual timers.

A terminal CLI that watches a Git repository and streams edits as they happen, making it easier to monitor what coding agents or editors are changing in real time.

An open framework for realtime voice conversation tied to agent execution, with desktop, command-line, and integration options.

A GitHub repository that packages a tiered engineering-agent system for AI coding tools, with install scripts, role routing, escalation rules, and portable skills for tools like Claude Code, Cursor, Gemini, and Codex.

Private AI agent for Android that helps users fix settings and troubleshoot phones with guided steps, deep links, and local memory.

A detailed post from pact0 about testing whether blank AI agents could complete a real product workflow, what failed, and the fixes they shipped after the audit.