Coding agents

A local-first, cross-platform desktop AI workbench unifying multi-provider chat, ACP coding agents, a knowledge base, MCP tools and an API gateway, keeping application data and files under the user's own control.

• Coding agents
• Inference

A production-oriented, token-efficient Python rebuild of Claude Code's reference TypeScript implementation, adding persistent multi-agent teams, a session supervisor and measured token-compression of command output.

• Coding agents

A Rust terminal multiplexer purpose-built for running several AI coding agents side by side, tracking each agent's state, tokens and cost across persistent, Git-worktree-aware workspaces.

• Coding agents
• Terminals

An open-source AI slide studio that runs inside the Codex CLI, turning a prompt, a repository or a folder of files into an image-native presentation deck through a visible research, outline, style, render and export pipeline.

• Coding agents
• Design tools

A graph-based mindmap system, of markdown-file and terminal-agent nodes connected by edges, for building human-in-the-loop multi-agent coding systems that can recursively decompose tasks and share memory with a person.

• Coding agents
• Agent memory

A lightweight desktop command center for Codex CLI, Claude Agent and other Agent Client Protocol agents, with a task scheduler, Git worktree management, remote control and a skills marketplace in one workspace.

• Coding agents

A terminal-first AI coding agent built specifically for DeepSeek, reporting roughly 98 percent prompt-cache hit rates and 1M-token context, with JavaScript-scriptable multi-agent workflows and MCP tool support.

• Coding agents

An open-source desktop control console that installs, configures and gives a visual workspace to local coding agents such as Claude Code, Codex, OpenClaw and Hermes Agent, with model routing and runtime metrics in one window.

• Coding agents

An Emacs package that integrates the Aider AI pair-programming tool, giving Emacs users AI-assisted coding with model selection, Ediff integration for reviewing AI changes, and Emacs-native file management.

• Coding agents
• Editors

A desktop workspace that gives the Pi, OMP and Prime Agent coding-agent harnesses a shared interface on macOS, Linux and Windows, while leaving each harness in charge of its own models, logins and sessions.

• Coding agents

A terminal-and-desktop coding-agent runtime built around a cognitive virtual machine that externalizes goals, state, evidence and permissions from the conversation history, so a model's own claim of being finished must pass runtime-checked delivery evidence.

• Coding agents

A free, open-source native macOS app that assembles focused, reviewable code context, files, structure maps and Git diffs, for AI coding agents, and bundles an MCP server so several agents can share a native orchestration interface.

• Coding agents
• MCP servers

A lightweight bridge that exposes the Codex desktop app's user interface in a browser, running on Linux, Windows or Termux on Android.

• Coding agents

A terminal and browser tool that reads a Claude Code or Codex session transcript and draws it as a live, replayable flow graph of the main agent, the agents it spawns, and the tools each one runs.

• Coding agents
• AI evals

A Vercel template for Foreman, an AI software factory that moves a task from GitHub or Linear through triage, planning, implementation and independent review, and delivers a draft pull request.

• Coding agents
• Agent frameworks

An open-source Electron desktop workbench that manages multiple pi and DSH coding-agent sessions across local project workspaces, importing existing Codex and Claude session history for unified browsing.

• Coding agents

A shared context, memory and supervision layer that connects coding agents such as Claude Code, Codex and Gemini CLI to each other and to enrolled machines, which authorized agents can operate directly with scoped commands and remote desktop access.

• Coding agents
• Agent memory

A native cross-platform app that gives every local AI coding agent one command center, running each agent in its own tmux pane over an end-to-end encrypted peer-to-peer or relayed connection between machines.

• Coding agents

A GitHub Action that installs and runs Claude Code inside a workflow so a team can build custom automation on top of it; it enforces no trust boundary of its own, so untrusted-input workflows should use the separate claude-code-action instead.

• Coding agents
• CI/CD

A modular runtime that orchestrates a marketplace of plugins, agents and skills into structured pipelines for AI-assisted software development, installed for Claude Code, Codex, OpenCode, Cursor and Kiro.

• Coding agents
• Agent frameworks

A runtime built on AgentField that spins up an autonomous team of planning, coding, review and testing agents from a single API call to produce production-grade pull requests.

• Coding agents
• Agent frameworks

FanBox is a macOS desktop app putting a local file browser, live file previews and a real embedded terminal in one window, so a developer can find scattered agent-created projects, run Claude Code or Codex, and watch exactly which files it changes.

• Coding agents

Parallel Code is a free, open-source desktop app that runs Claude Code, Codex and Gemini side by side, each isolated in its own git worktree and branch, so several coding agents can work on different tasks at once without touching each other's changes.

• Coding agents

ECA is an editor-agnostic, LSP-inspired protocol and server, written in Clojure, for AI pair programming: it gives chat, rewrite and completion the same behavior in Emacs, VS Code, IntelliJ, Neovim or a desktop client, all configured once regardless of which editor is running it.

• Coding agents
• Editors