AI coding agents 19

Project management platform for human and AI coding-agent teams Multica is an open-source project management platform for human and coding-agent teams. It helps teams assign tasks to AI agents, track progress, manage complete task lifecycles, reuse shared skills, monitor local and cloud runtimes, and coordinate human and agent activity in one workspace. Multica supports more than 20 coding tools, offers local and cloud runtime management, and can be self-hosted through Docker Compose, a single binary, or Kubernetes.

Open-source toolkit for building custom AI-powered design apps Toolcraft is a free, open-source starter kit and UI library for building custom design applications with AI. It provides an application architecture for creative tools, including a canvas, toolbar, layers, timeline, and keyframe workflows. Its embedded AI skills, performance instructions, and visual testing rules are intended to help AI agents generate more consistent creative apps. Toolcraft works with Codex, Claude, Cursor, and other AI agents.

Cloud development environments designed for running parallel AI coding agents. Boxes.dev is a cloud development environment platform specifically built for agentic coding. It provides full, isolated Linux virtual machines (VMs) for each individual Claude Code or Codex chat thread. This allows developers to run coding agents in parallel, let them work overnight while the laptop is closed, and monitor or steer them seamlessly from mobile, desktop, or CLI interfaces without resource constraints or complicated dev setup scripts.

Shared project workspace for teams using AI coding agents Joxo is a shared collaboration project for teams using AI coding agents such as Claude Code, Codex, Cursor, Gemini CLI, and OpenCode. It connects each teammate’s existing coding-agent sessions through shared project memory, tasks, decisions, blockers, and handoffs. Joxo does not provide or resell AI models, subscriptions, or API access; each person uses their own AI provider account and computer. The service relays intentionally published project information between agents, helping teammates continue work without repeating context or sharing screenshots.

Open-source Agent Development Environment for parallel AI coding agents. Orca is an open-source, cross-platform Agent Development Environment (ADE) specifically designed for running and orchestrating AI coding agents. Unlike traditional IDEs, Orca allows developers to run multiple AI command-line interface (CLI) agents—such as Claude Code, Codex, Gemini, and OpenCode—simultaneously in isolated git worktrees. This parallel setup enables users to multi-task across branches, test solutions, and review AI outputs efficiently within an environment featuring Ghostty-inspired WebGL terminals, an embedded Chromium browser for Design Mode feedback, native GitHub/Linear integration, and an editor.

Open-source workspace for running and managing AI coding agents ADE is a local-first, open-source Agentic Development Environment that brings AI coding agents such as Claude Code, Codex, Cursor, Factory Droid, and OpenCode into one synchronized workspace. It runs across macOS, Windows, Linux, the web, terminal, and iOS, allowing developers to manage parallel coding tasks using isolated Git worktrees, agent chats, terminals, pull requests, built-in tools, and remote machines.

Versioned filesystem for persistent, collaborative AI agent workspaces Mesa is a versioned filesystem and virtual filesystem platform built for AI agents. It allows agents to access persistent files, create isolated branches, run parallel agent swarms, track changes, request human approvals, and roll back work through one API. Mesa supports POSIX-compatible filesystem access, large files, shared memories, documents, code, datasets, models, and media. It provides sub-50ms reads and writes through MesaFS, instant workspace forks, strong consistency, fine-grained access controls, and enterprise deployment options.

AI platform for building scalable production-ready software 8080.AI is an AI-powered software development platform that uses scalable, specialized AI agents to build production-grade websites, SaaS products, and applications. Users can describe an idea in natural language, then guide AI-generated requirements, user flows, designs, architecture, tasks, code, testing, and Kubernetes deployments through human approval gates. The platform includes collaborative workspaces, isolated task branches, a browser-based VS Code editor, visual testing, staging and production deployments, auto-scaling infrastructure, and multi-agent engineering workflows.

Self-hosted cloud development environment for developers and AI coding agents. Coder is a self-hosted cloud development environment platform that enables developers and AI coding agents to work together in context-rich environments on your infrastructure. It delivers self-hosted development environments, provisioned as code and ready for developer activity on day one. Coder gives developers and AI coding agents the infrastructure they need—with the control and isolation required to deploy agents safely at scale.

Open-source desktop environment for running multiple coding agents in parallel. Emdash is an open-source desktop app and agentic development environment designed for running multiple coding agents in parallel. It serves as a centralized dashboard where developers can monitor AI agent sessions, review code diffs, and seamlessly turn software issues into pull requests. By leveraging isolated Git worktrees for each task, Emdash allows engineers to orchestrate multiple agents simultaneously without taxing their local machine, offering a highly scalable and async-friendly native coding environment.

Open-source runtime for safely running coding agents without constant supervision Agent AFK is an open-source, local-first runtime for running coding agents unattended. It allows developers to start coding tasks, walk away, and later review verified results through traces, terminal states, and receipts of agent activity. The runtime supports permission boundaries, reversibility gates, isolated worktrees, parallel subagents, adversarial verification, persistent session memory, and Telegram supervision. It works with Claude, Cursor, Claude Code, Codex, custom agents, and other model providers while keeping the runtime and data on the user's machine.

AI-native platform for orchestrating governed software delivery Skaftor is an AI-native software delivery platform that connects existing development tools, captures product and technical intent, converts requirements into architecture and executable work orders, and orchestrates coding agents through review and deployment. It provides organizational memory, knowledge graph connections, impact analysis, duplicate detection, governance controls, approval workflows, audit trails, and traceability from requirements to shipped code.

A macOS workspace for orchestrating parallel AI coding agents and automating development workflows. Scape is a macOS application for running and managing unlimited Claude Code, Codex, and OpenCode agents across isolated Git worktrees. It provides a visual workspace for parallel agent sessions, watchdogs, automation playbooks, tables, orchestration through Argus, agent collaboration, encrypted chat rooms, voice transcription, and development tools. Scape is local-first, so projects and workflows remain on the user's machine, while users continue using their existing AI agent subscriptions.

Monitor and control AI coding agents from your Mac notch Crew Tower is a native macOS control center for monitoring and managing AI coding agents from the MacBook notch or a floating pill on external displays. It supports agents such as Claude Code, Codex, Cursor, Gemini CLI, Qwen Code, and OpenCode. Users can review permission requests, approve or deny commands, answer agent questions, review plans, monitor progress and context usage, receive completion notifications, and jump directly to the correct terminal tab without leaving their current work. Crew Tower communicates locally through agent hooks and Unix sockets, keeping code, prompts, and transcripts on the Mac.

Disposable Linux environments for AI agents to test apps end to end TryCase provides disposable Linux environments for AI coding agents to run apps, test changes end to end, capture screenshots and recordings, collect logs and artifacts, and return verified results instead of requiring manual testing.

Knowledge graph for precise AI coding-agent codebase context GitNexus is an open-source knowledge graph engine by Akon Labs that indexes codebases into a deterministic graph of dependencies, callers, imports, call chains, execution flows, clusters, and cross-repository relationships. It connects to coding agents through MCP, allowing them to query structured code context instead of relying only on file searches, embeddings, or similarity guesses. GitNexus supports impact analysis, blast-radius detection, git-diff analysis, architecture discovery, hybrid search, and multi-repository graph analysis. Its local version keeps code, indexing, and queries on the user's machine, while Enterprise provides managed SaaS or self-hosted deployments with features such as automated PR review, auto-reindexing, unified multi-repo graphs, SSO, and dedicated support.

Free AI code editor for building, debugging, and managing software projects Visual Studio Code is a free, open-source AI code editor from Microsoft for building, debugging, and managing modern web and cloud applications. It supports AI agents that can plan, code, and debug, as well as multi-agent workflows across Linux, macOS, and Windows. The editor also provides rich language support, extensions, integrated source control, debugging tools, terminals, remote development, browser access, and customizable themes and profiles.

Local CLI that reduces coding-agent token waste JFrog Boost is a free, local-first command-line tool that compresses noisy terminal output, MCP responses, file contents, and other tool data before it reaches coding agents such as Cursor, Claude Code, Codex, GitHub Copilot, and OpenCode. It reduces token usage while preserving important information such as errors, failures, summaries, and relevant context. Boost uses reversible compression and retrieval, allowing agents or developers to restore the original output when needed. It also provides graph-based code retrieval, file optimization, observability, telemetry, and enterprise-focused privacy.

Shared GPU infrastructure and community for running open AI models through an OpenAI-compatible API. NaN is a paid community and shared GPU inference platform for builders who want to run open AI models without managing their own infrastructure. It provides an OpenAI-compatible API, shared dedicated GPUs, EU-based processing, zero prompt and response logging, and access to language, embedding, reranking, text-to-speech, and speech-to-text models. Members can use the shared inference cluster, participate in a private Discord community, attend events, and vote on future models. The platform also offers a premium GLM 5.2 tier with published token allowances.