Tabula is a native macOS database client for PostgreSQL, MySQL/MariaDB, SQLite, MongoDB and Redis. It helps developers browse, query, filter and edit data, with optional keyboard-focused AI assistance for writing and troubleshooting queries.
git-flow-next is a Go-based command-line tool for managing configurable Git branching workflows. It supports Gitflow, GitHub Flow, GitLab Flow, and custom configurations for developers and teams.
Lexmount provides Web Fetch, remote Cloud Browser sessions, Web Search, and task-oriented Agent workflows for AI applications. Developers can extract content from public pages, automate dynamic or signed-in sites, and inspect browser runs through APIs, SDKs, Playwright, and a Playground.
Prompt Deck is a macOS app that brings coding-agent transcripts from eleven supported tools into one searchable interface, alongside reusable prompts and agent memory files. It is intended for developers who work across multiple coding agents and want to review, reuse, and maintain that local context in one place.
Fluxix is a runtime safety and policy layer for AI agents that intercepts tool calls before execution. It helps development and operations teams block risky actions, mask sensitive data, route high-impact requests for approval, and audit agent decisions across supported frameworks and OpenAI-compatible clients.
Shedi is a native Mac cleaner for developers that identifies storage used by Xcode, Docker, node_modules, package caches, build output, and app leftovers. It explains each result and lets users review selected items before moving supported deletions to the Trash.
AgentValley is a free, open-source macOS app that displays Claude Code sessions and sub-agents in a MacBook’s notch. It helps developers monitor activity, identify agents waiting for input, and review project history without switching between terminal windows.
Bloblings is a Mac app that gives each Claude Code, Codex, or terminal coding session a visual pet showing its current state. Users can click a pet to reopen the right thread and project, monitor subagents, and pass short notes between sessions locally.
DotMD is a Markdown reader and editor for Mac that adds passage-level review for AI-generated documents. Connect Claude Code, Codex, Cursor, or another MCP client locally, comment on exact lines, and approve returned changes in context.
Peras is a local CLI and hook guard for Claude Code and Codex that monitors provider usage and applies configurable warnings, holds, or pauses. It helps developers manage shared usage windows, daily or weekly allowances, and unattended coding sessions; an optional macOS menu bar app shows both agents together.
Inyon is an open-source tool for watching, answering, and steering coding agents running in tmux on your own computers. Developers can use its Android app, or an optional self-hosted hub for browser access, to manage supported CLI agents remotely.
Plango is a local Mac security tool for developers using AI coding agents. It checks agent actions, MCP servers, plugins, credentials, Mac privacy settings, and network connections, then explains and logs security decisions in plain English.
Monish is an iPhone app that sends agent progress, results, failures, questions, and metrics to the lock screen and Dynamic Island. It connects to Claude Code, Codex, Cursor, n8n, or cron through a single HTTPS endpoint without an account or computer-side installation.
Ovren is an AI coding tool for making changes to existing products from natural-language requests. It plans and writes the code, opens a pull request for team review, and provides live previews for frontend changes.
Monid gives AI agents and developers a single access layer for discovering and using a broad catalog of data endpoints and APIs. It supports MCP, agent skills, CLI, and HTTP API connections, with usage-based access and documented options for embedding the service in other products.
tetriz-engineering-intelligence is a Go module of libraries for evidence-based analysis of AI-assisted software delivery. It helps engineering teams attribute contributions, assess pull requests, trace defect lineage, measure ROI, link delivery records, and evaluate AI development maturity using supplied data.
CleanSlop is a production-readiness scanner for TypeScript and JavaScript apps that runs from terminal-capable AI agents or the web. It identifies prioritized code and architecture issues, explains the evidence, and can help an agent apply approved fixes and rescan the project.
Whiteboard is an open-source desktop canvas for reviewing software changes through semantic diffs, architecture-level visualizations, source code, and agent trajectories. It helps developers inspect implementation details and share selected context with coding agents.
ESP-Mosaico 是一款基于 ESP32-S31 的模块化 AIoT 与嵌入式开发板,结合设备端 Agent、触控界面和可扩展外设。它面向希望通过自然语言或 PC 端 AI 编程 Agent 构建、测试和部署实体设备应用的创作者与开发者。
Harness² is an open-source framework for refining the prompts, tools, memory, and other components around fixed AI models. It helps researchers and developers run recursive harness-improvement workflows across JobBench, LAB, and WorkBuddy-Bench.