Newly Accepted

An open-source collection of Claude Code skills, agents, and plugins for improving agent output quality across tools like Cursor, Gemini CLI, OpenCode, and Antigravity.

GitHub’s research preview on multi-model orchestration for coding tasks. The page describes adaptive workflow selection and includes benchmark comparisons against the Opus 5 baseline with estimated cost reduction claims.

A Lean 4 repository containing a machine-checked proof of Fermat’s Last Theorem, with build verification details and browsable HTML documentation for the proof structure.

Chrome extension that scans public websites for signs of fake AI-generated stores, invented customers, suspicious reviews, and weak business evidence.

A rented Linux box for AI agents to use real apps like Slack, Telegram, Discord, and the web through a private encrypted tunnel, with consent gating for outbound actions.

Loopback MITM proxy for Claude Code on Amazon Bedrock that can sniff, hold, edit, forward, or drop requests. The repo includes prerequisites, a quick start, flags, cost notes, and behavior limits.

A local CLI that records a codebase’s behavior and gates AI-driven refactors against a frozen baseline. It runs declared probes, compares outputs byte-for-byte, and returns a simple pass/fail signal for agent workflows.

Post-mortem for an AI-assisted port of F-Zero X to the New Nintendo 3DS, including the build stack, hardware performance results, timeline, and agent workflow used to get the game running at native 60 Hz.

Uno is a research repository for speeding up LLM inference with discrete diffusion and lossless multi-token decoding. The repo includes inference, training, and evaluation code, plus installation steps, checkpoints, and example workflows.

Browser-based cross stitch pattern maker that turns photos or text prompts into DMC-matched stitch charts, PDF patterns, and skein lists.

Radia is an agent coordination layer for independently deployed agents, with immutable records, lease-based claims, permissions, and provenance tracking for who acted and what produced each result.

A no_std Rust memory engine for on-device LLM agents that uses provenance-aware recall to keep a model’s own output from becoming evidence.

An open-source CLI that turns ebooks into token-counted Markdown chapters, serves them over MCP, and verifies quotes against the source text offline.

A Claude Code plugin that adds persistent semantic memory via MCP, with support for Cursor and Claude Code setup, plus exposed write/search tools.

Openvurp is a local-first multi-agent workspace where agents have jobs, tools, memory, and can consult each other instead of answering in isolation. The repo shows browser, CLI, and Docker setup, plus concrete workflows for running commands, writing files, and using multiple channels.

AntiAgent is a human-in-the-loop planning tool that uses AI to ask sharp questions, surface priorities, and turn messy thoughts into a step-by-step execution plan.

React hooks for exposing app functionality as WebMCP tools, with Zod-based inputs, SSR-safe behavior, StrictMode safety, and a bridge to AI clients like Claude and Cursor.

A macOS desktop product for running multiple coding agents in parallel from one workspace, with shared accounts, memory, and skills. The page also highlights Lanes Link, an MCP-based endpoint for connecting agent clients to accounts, context, and access profiles.

Bridle is an open protocol and small CLI for handing context and work between coding agents on different machines, with opt-in policy controls on both sides.

An open framework for scoring how well an MCP tool definition communicates to an AI agent, with a spec, reference implementation, CLI, and hosted API.

A research-style blog post comparing grep with LSP-backed navigation in coding-agent workflows, showing how tool interface shape affects agent behavior and task success.

GasPeek compares real-time USDT transfer fees across blockchains like Tron, Ethereum, Polygon, Solana, BNB Chain, TON, Aptos, Avalanche, and Polkadot, helping users choose the cheapest network before sending.

An interactive browser game where you hide from an AI agent that hunts you through the arena via WebMCP sensors. It includes controls, energy mechanics, and a demo round for solo play.

Oconee Runtime is an enterprise AI governance product focused on policy enforcement for browser AI and coding agents. The page explains how it evaluates proposed agent actions against policy and supports allow, warn, and block outcomes.