Newly Accepted

Openbenchmarks is a public benchmark site for agents comparing SaaS and AI vendors with verified ground truth, open methodology, and metrics focused on build-vs-buy decisions. The snapshot shows benchmark sets for lookalikes, text-to-speech, and speech-to-text, plus links to open data and code.

A Zot docs page describing portable .zot files for packaging agent behavior, skills, requirements, and permissions. It includes manifest structure, file layout, permission rules, and packaging/running examples.

A local CLI for replaying what AI coding agents accessed on your machine, including file reads, secrets that entered context, and possible read-then-network-call exposure paths. It also scans exported ChatGPT, Claude, and Gemini histories for sensitive data.

CLI tool that black-box tests remote MCP servers for 2026-07-28 spec readiness and reports pass/fail status, grades, and migration guidance.

Local-first AI trading research assistant for market context, strategy generation, and Backtrader backtests. It supports multiple LLM providers, exposes an OpenAI-compatible API, and keeps runs and data stored locally.

Mindwalk is a local Go tool that replays Claude Code and Codex sessions on a 3D map of a codebase, showing where an agent searched, read, and edited files over time.

Colyap is an AI phone friend you can call or text. The page shows voice-call and SMS access, memory, reminders, and task help like booking dinner, researching flights, and sending follow-up texts.

A live dashboard tracking an autonomous AI’s attempt to win a public follower-growth bet, with a countdown, live counter, and activity log.

An AI-powered Obsidian plugin that turns notes into a self-organizing wiki with auto-generated entity pages, bidirectional links, traceable answers, and local-first support.

Google Workspace Marketplace app that translates documents, web pages, and chat text with layout preservation and AI writing support.

Open standard, SDK, and live hub for personally-owned AI agents, with a protocol, reference hub, value routing, and live market mechanics.

A Python package and CLI for checking how closely an AI-generated answer reuses its source text, with support for verbatim matching, subsequence matching, quotation verification, and pipeline gating.

A local-first harness for turning coding models into reliable software agents, with memory, sandboxed execution, verification, recovery, GitOps, and deployment workflows. The repo describes a multi-agent architecture, approval gates, provider support, and a real shipped example.

Aerial is a local-first Rust tool for agent-to-agent messaging and orchestration, with durable mailboxes, a supervisor, and an MCP adapter. The page shows what it does, how it works, and basic install commands.

An open-source project that runs full games of Diplomacy between 7 LLM-controlled powers, with negotiation rounds, validated orders, and saved transcripts for replay and analysis.

Aether is a cloud devbox for autonomous coding agents that can be watched, steered, and verified while working on tasks from GitHub, Slack, Linear, the terminal, or an API.

A zero-dependency TypeScript music theory engine with scale, mode, key, and interval utilities, plus MCP server support for AI assistants.

Code Airlock is a wrapper for running coding agents like Claude Code and Codex inside disposable microVMs, with changes committed to git for host-side review.

A French public demo of an autonomous Claude agent competing in timed money-making challenges, with live episode tracking, Stripe payments, and public results from prior runs.

Local-first federated search for AI agents that queries transcripts, files, a knowledge graph, a vector store, and the web, then merges results with trust-weighted ranking.

A Python CLI and Claude Code skill for running Codex and Cursor coding agents as subagents, with fanout, model selection, sandbox controls, and remote execution support.

A macOS utility for customizing the native Slack app by injecting CSS and JavaScript, hiding Slackbot, upsells, tabs, and other UI elements in real time.

OpenAI’s ChatGPT desktop app docs page for using the app with projects, files, and long-running work, with broader developer documentation around Codex, agents, tools, and related workflows.

Opula is a hosted MCP connector that lets Claude and ChatGPT analyze your own finances using connected portfolio, net worth, cash flow, dividend, and risk data.