Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and VPS.

Native macOS radial task switcher for the Codex desktop app

Multi-account Claude proxy with automatic quota-based rotation

Codex/ChatGPT multiple account load balancer & proxy with usage tracking, dashboard, and OpenCode-compatible endpoints

Markdown knowledge graph — LSP for your editor, CLI + MCP memory for your AI agents

More than a SideNotes alternative.

Move whole tables between databases fast — Postgres, MySQL, ClickHouse, BigQuery. Rust engine, one-line Python API, bounded memory.

the runtime your coding agents live on

AI review, human decision — a local human-in-the-loop interface for GitHub pull request reviews

A live, local dashboard to browse, search, resume & manage every Claude Code session on your machine — full conversation transcripts, an artifacts view, and usage stats. Pure Python stdlib, no depe…

Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they…

AI Kanban & Development Environment. Orchestrate multiple agents, review changes, open PRs. Multi-provider, self-hostable, no telemetry.

macOS video editor built for AI

File-based message queue for local agent-to-agent communication (Maildir-style)

Bridge Claude Code to OpenAI models — OpenAI API key or ChatGPT/Codex-plan OAuth

Your AI agent reads the codebase. You speedread the report. An agent skill + one-file RSVP reader for markdown reports.

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

A free, fully private, one-page mind-mapping web app. No accounts, no server, no tracking.

Unofficial SDK for Codex agents controlling visible ChatGPT web sessions

Zero-dependency browser video editor that AI agents can drive — JSON timeline, MCP + REST, live-reloading UI

Frontier IDE built for AI coding.

#1 open-source code reviewer on Code-Review-Bench

Mine your Claude Code and Codex logs into a local you.md agent profile.

Run Claude Design locally as an Agent Skill — Cursor, Claude Code & more. Produce polished UI mockups, prototypes, decks & wireframes as self-contained HTML, without claude.ai/design. Best with Opu…

Isolated dev environments for parallel AI coding agents — worktree, auto ports, one command up/down.

Run Claude Code workflow scripts, unmodified, on the OpenAI Codex CLI — fable plans, codex executes, fable verifies. Parallel agent fleets, builder–verifier loops, token budgets, full-screen TUI.

Turns corrections into Preferences, Project-specific skills, and Shared skills for Claude Code, Codex, and OpenCode.

A skill to stop your coding agent from burying the answer. ADHD-friendly output.

Your AI agent skills, finally organized. A macOS app to browse, edit, and manage skills across Claude Code, Cursor, Codex, Windsurf, and Amp.

A composable dev process for agentic coding harnesses, packaged as modular skills. Turbo has sibling editions for Claude Code and Codex.