SuperAPI AI Directory

AI coding

2,763 results · Page 32 of 77

octomind

AI coding

Octomind is an open-source AI coding agent and agent runtime, delivered as a single binary, supporting any model with native MCP integration. It can run in the terminal, CI, or as a background daemon, with the same session engine supporting multiple entry points such as interactive, piped stdin, WebSocket server, and as an ACP subagent. Models, tools, roles, guardrails, and budgets are all configured via TOML, with no framework code required. It can call MCP tools to accomplish real work such as reading and writing files, executing shell commands, searching code, and delegating to subagents. The built-in default tap provides expert roles such as developer:general. It supports using an Octomind Cloud subscription via octomind login, or you can bring your own key for any provider (OpenRouter, Anthropic, OpenAI, DeepSeek, Ollama, etc.). It provides policy-as-code-based guardrails, cost control, adaptive context compression, and intent-driven on-demand capability activation. It can be installed via cargo install octomind (requires Rust 1.95+) or built from source.

Read more

OneCompiler

AI coding

OneCompiler is an online coding and code-running platform. It states that it has helped more than 12.8 million users worldwide write code online. It provides iFrame embedding capabilities for the Editor and Challenges, allowing websites to quickly gain code execution functionality; it also provides an API for backend applications to call in order to run code, read reports, and more, and its team can be contacted to customize workflows not covered by the API. In addition, the editor has a built-in coding agent that can read the workspace, edit files in place, create new files, and clean up after itself, with all changes passing through rollback-capable checkpoints and no installation required; it supports multiple model sources, including free models.

Read more

OpenHands

AI coding

OpenHands is a self-hosted developer control center for running coding agents and automating tasks. It supports running OpenHands, Claude Code, Codex, Gemini, Pi, OpenCode, or any ACP-compatible agent, and can connect to local, remote, and cloud backends. Its Agent Canvas interface turns coding agents into a persistent engineering team, used to start conversations and automate everyday tasks, such as generating reports and posting them to Slack, or automatically breaking down GitHub issues into tasks. It runs locally by default, and can also connect to agent backends in Docker containers, virtual machines, or company infrastructure, and can optionally use OpenHands Cloud or OpenHands Enterprise infrastructure.

Read more

PackyCode

AI coding

PackyCode (PackyAPI) is an AI API aggregation gateway for developers worldwide, providing one-stop access to mainstream large models such as Claude, Claude Code, GPT, Codex, Gemini, Azure OpenAI, and more. It connects global large model resources through a unified domain, keys, and risk control policies, featuring intelligent failover, full-stack observability and risk control, on-demand scaling, and cost optimization. It is compatible with the OpenAI interface protocol and provides SDKs, examples, and a Web Playground, helping teams use large models reliably and quickly implement AI innovation.

Read more

parallel-code

AI coding

Parallel Code is a free and open-source tool (MIT license) for scheduling multiple AI coding agents in parallel. It supports tools such as Claude Code, Codex CLI, Gemini CLI, and Copilot CLI, automatically creating a separate git branch and worktree for each task, so multiple agents can run simultaneously in the same interface without conflicts. Users can view the diff of each session, review, and merge results. It offers keyboard-first operation, a built-in diff viewer, code Q&A, mobile remote monitoring, and other features, making it suitable for developers who want to improve multitasking development efficiency.

Read more