Newly Accepted

DumbDetector is a community-driven status tracker for AI tools, assistants, and coding agents. It shows report-based signals for services like Claude Code, Codex, Cursor, GitHub Copilot, Gemini, and more, plus short troubleshooting guides for common AI behavior issues.

A read-only tool that scans public GitHub repositories for AI contribution readiness and repository health signals, then generates policy wording and fix suggestions.

An arXiv paper describing an open library of 163 procedural skills for research agents across 16 scientific areas, with versioned instruction files and accompanying reference material or runnable scripts.

A runtime for AI agents that grounds answers in retained evidence, refuses uncited claims, and logs citations for auditability. The page describes pointer-based facts, refusal rules, and a judge layer for meaning checks.

WorldCut is a TypeScript package that checks whether observations from independent systems satisfy declared version and time relationships before an autonomous agent makes a decision.

Open-source identity-based remote access platform built on WireGuard, combining reverse proxy, VPN, SSO, and access control. The page also shows an AI gateway use case for putting cloud and self-hosted model access behind a single authenticated URL.

Keydris is an authorization layer for AI agents that checks whether a governed action is allowed before it runs. The page shows a working product with docs, quickstart steps, CLI install commands, policy and revocation concepts, and decision records for audit trails.

AQ is a multiplayer agentic development environment for teams running coding agents in shared live workspaces. It supports agent CLIs like Claude Code and Codex, live terminals and previews, isolated worktrees per task, and deployment on your own cloud or AQ-managed infrastructure.

Open-source CLI for searching past coding agent sessions locally and tracing code changes back to the original agent transcript. It also offers a paid pro add-on for “git blame, but for agent sessions,” with cited results and local-only indexing.

Ardent is a code-first AI agent for business work that runs in a desktop app, writes reusable code in a sandbox, and lets teams share repeatable workflows as “Abilities.”

Codeknow turns a codebase into a queryable knowledge graph for architecture analysis, impact detection, drift tracking, onboarding tours, and refactoring guidance. It runs without LLM keys, supports 25+ languages, and exposes a broad CLI plus export formats and interactive views.

A public leaderboard comparing how different language models solve Redactle under several evaluation setups, with cost, speed, and solve-rate data.

OpenAI’s model documentation page for the API, with navigation into model selection, pricing, reasoning, text and code, embeddings, moderation, and related developer docs.

Adchestra is a hosted MCP service that lets AI agents manage Google Ads and related Google marketing tools from chat. It supports Google Ads, Analytics 4, Tag Manager, and some Search Console access, with four-step setup and approved write actions.

A searchable index of AI Engineer talks with summaries, timestamps, packs, speakers, topics, and conference filters. It helps users jump to the relevant parts of long talks and browse related sessions by theme or speaker.

AURA is a Rust-based SRE agent platform for investigating and fixing production incidents. The repository shows a quick start, production-safety controls, multi-model support, MCP and RAG integrations, and an example incident workflow using traces, logs, and Kubernetes history.

A DeepMind technical report PDF about double-blind AI evaluations and confidentiality issues in AI safety research.

A research blog post describing an open-source small transformer trained from scratch to reach 44% on ARC-AGI-1 at very low cost, with architecture notes, ablations, and pointers to code.

Anthropic’s release notes for Claude Fable 5.1, covering new features, breaking changes, pricing, model availability, and migration details for API users.

Open-source platform for building internal tools, dashboards, business apps, and workflows, with AI app generation and MCP support for coding agents.

Supercov is a coverage tool for coding agents that turns uncovered paths into the next test to write, then reruns the suite to verify progress.

Subpool is a self-hosted control plane for managing AI subscription and API capacity across teams. It pools authorized accounts, issues employee-specific keys, exposes OpenAI-compatible endpoints, and tracks usage without storing prompts or responses.

Cupertino is a macOS app that exposes Apple apps like Mail, Calendar, Contacts, Messages, Notes, Safari, Maps, Screen, and Sound through MCP servers for agents. It includes a signed menu-bar app, a visible permission model, read/write controls, and a live session log.

HEIDES is a deterministic local harness for AI coding agents that maps a codebase, grounds plans against the current graph, and checks proposed patches for conflicts, edge cases, and security issues before changes land.