Newly Accepted

An open-source desktop widget for Linux, macOS, and Windows that shows live usage levels for Claude, Codex, and several cloud AI providers. The page includes platform support, install options, behavior details, and packaging notes.

Hybro is an open-source interoperability layer for AI agents, with a FastAPI backend, Next.js dashboard, CLI setup, and support for the A2A protocol and MCP server integration.

A tiny desktop utility that shows remaining GitHub Copilot credits in the macOS menu bar or Windows system tray, using GitHub CLI login and no token storage.

Desktop app for chatting with coding agents in an MSN Messenger-style buddy list. It supports Claude Code, Codex, Gemini, and OpenCode, with project-based conversations, group chats, reviews, and agent handoffs.

An MIT-licensed Rust framework for building multi-agent systems on the A2A protocol, with A2A 1.0 support, MCP bridging, multiple transports, and companion crates for CLI, client, LLM, and AP2 helpers.

Rubi is a knowledge graph and context manager for AI coding agents. It helps shorten sessions, reduce re-reading, and recall project knowledge for tools like Claude Code, Codex, Gemini CLI, Cursor, Copilot, and local models.

Spotnote is a Vite plugin that lets users click UI elements in a running app, write feedback, and send coding agents a precise file, line, and column target. It also supports MCP, staging builds, and webhook delivery for team workflows.

An open-source Google Research framework for recursive agent harnessing, designed to improve agent behavior through task-level and harness-level recursion without changing model weights.

A read-only MCP server that lets AI agents search and read a user's WhatsApp messages, with deployment on Cloudflare Workers and support for Claude and other MCP clients.

A Claude Code plugin that removes filler words like “uh” and “um” from voice-dictated prompts before they reach the model. It also cleans pasted dictation in the prompt box and preserves code, backticks, and slash commands.

A web tool for estimating how fast local LLMs will run on different hardware before you buy it. It lets users browse by GPU, Mac, CPU, and model, and shows simulated tokens/sec and time-to-first-token based on benchmark data.

A native Android app that generates full songs with vocals on-device using YuE2, with local storage, offline use, stem splitting, a mixer, recording tools, and AI writing aids.

An open-core AI memory engine that stores structured facts in a graph, supports MCP clients, and can run local-first or as a hosted cross-app service.

A guardrails and knowledge-layer tool for coding agents. It briefs agents before tasks, verifies rules with checks, and flags drift when governed files change. Works with Claude Code and other MCP agents.

TaskPocket is a to-do app for web and iPhone with start dates, deadlines, repeats, reminders, file attachments, and task parsing from natural language. It also offers an MCP server/API so users can connect their own AI assistant instead of using built-in AI.

A lightweight, cross-platform offline desktop AI assistant with local-first features like inline writing help, memory vault, command safety checks, meeting notes, and file-based RAG.

A local LLM gateway that redacts secrets before requests reach model providers and restores them locally afterward. It is aimed at agent workflows where prompts and tool calls may contain real credentials.

MIKE is an integrated Kanban environment and LLM harness for software development work, with gVisor-based sandbox isolation, custom extensions, and support for llama.cpp and OpenAI-compatible inference providers.

A self-hosted Go service that turns headless coding-agent CLIs like Claude Code, Codex, and Kimi Code into an OpenAI-compatible API with chat, streaming, tool calling, MCP, sessions, and image support.

DocuMemory is a memory layer for AI coding tools that turns chat sessions into reusable engineering notes, searchable context blocks, and MCP-injectable snippets. The page shows capture, distillation, recall, pricing, and integration details for Claude Code, ChatGPT, Cursor, and other MCP clients.

An open-source code-review training repo with 24 AI-written bug katas in Python and JavaScript. It includes runnable tests, fix-and-verify workflows, and GitHub Actions grading for forks.

Open-source persistent workspace for AI agents to work with market data, run rules, compare results with web sources, keep journals, and optionally place paper orders.

A Node.js deployment tool for shared hosting that backs up files before overwriting them, supports one-command restores, and exposes an MCP server for AI agents and other clients.

A pay-per-crawl system that lets site owners charge AI crawlers per page across WordPress, Next.js, Laravel, Cloudflare, nginx, Python, Go, and more. The page says payments settle in USDC on Base, with no custody, and that each edition includes crawler discovery files and support for x402/MPP-style access control.