bradAGI/awesome-cli-coding-agents

Curated directory of terminal-native AI coding agents and the harnesses that orchestrate them. Covers open-source tools (Pi, OpenCode, Aider, Goose), platform agents (Claude Code, Codex, Gemini CLI), parallel runners, autonomous loops, and agent infrastructure.

What it solves

This project provides a curated directory of over 150 CLI coding agents. These tools solve the problem of needing an AI assistant that can interact directly with your local development environment—reading files, running shell commands, executing tests, and fixing errors—rather than just providing text-based code snippets in a chat window.

How it works

CLI coding agents act as AI pair programmers that live in your terminal. They are granted access to your filesystem and development tools, allowing them to autonomously perform tasks like editing code, committing changes, and iterating on bugs. The repository categorizes these tools into various types, including open-source agents, closed-source options, and specialized harnesses that manage agent orchestration, sandboxing, and session control.

Who it’s for

This list is for developers and engineers looking to integrate autonomous AI agents into their command-line workflows. It is useful for those who want to compare different agent architectures, find tools that support specific LLM providers, or explore advanced agentic features like persistent memory, multi-agent swarms, and sandboxed execution environments.

Highlights

  • Extensive Curation: A list of 150+ CLI coding agents and orchestration harnesses.
  • Diverse Ecosystem: Includes tools ranging from lightweight, single-binary agents to complex, multi-agent frameworks.
  • Feature-Rich Categorization: Identifies agents by their capabilities, such as MCP (Model Context Protocol) support, autonomous loops, and sandboxed execution.
  • Provider Flexibility: Highlights agents that support a wide range of LLM providers, including local models via Ollama or vLLM, and cloud-based APIs.

Related

  • Project
    ai-builders-foundation/ai-builders-curriculum

    A free, vendor-neutral curriculum and set of starter kits that teach developers how to build, govern, and deploy full-stack AI applications from scratch.

  • Project
    yohey-w/multi-agent-shogun

    A system that orchestrates multiple AI coding CLI instances in parallel using a feudal hierarchy and YAML-based communication to eliminate API coordination costs.

  • Project
    mbailey/voicemode

    A voice interface for Claude Code and other MCP-capable agents that enables natural, hands-free conversations using either cloud or local speech services.

  • Project
    nrslib/takt

    TAKT is a Node‑JS CLI that orchestrates AI coding agents (Claude, Codex, Cursor, etc.) via declarative YAML workflows. It runs each step in isolated Git worktrees, enforces review/fix loops, logs every action, and can auto‑create PRs. Designed to make AI‑driven development repeatable, auditable, and less dependent on fragile prompts.