Piebald-AI/awesome-gemini-cli

A curated list of awesome tools, extensions, and resources for Gemini CLI.

What it solves

Gemini CLI is an open-source AI agent that brings Google's Gemini model directly into your terminal. With so many community-built tools, extensions, and resources around it, it's hard to discover what's useful. This project is a single, curated list that collects the best of them in one place, so you don't have to search across GitHub, blogs, and forums.

How it works

The list is organized into categories like Official tools, Interfaces, Forks, Agent orchestration, Commands & extensions, MCP servers, Neovim plugins, and more. Each entry includes a short description and a link. Community members can contribute by adding their own projects via a contributing guide. The list also points to a companion list specifically for Gemini CLI extensions.

Who it’s for

Developers who use (or want to use) Gemini CLI and want to extend its capabilities, find alternative UIs, manage multiple coding agents, or integrate it into their workflow. It’s also useful for builders who want to see what kinds of tools are possible and where they could contribute.

Highlights

  • Official resources: the core Gemini CLI, its cookbook, and a GitHub Action for CI/CD.
  • Alternative interfaces: desktop apps, mobile SSH clients, and web UIs for non-terminal access.
  • Forks that support other LLMs, like Qwen and multi-provider options.
  • A wide range of agent orchestration tools, from parallel runners to chat-based supervisors.
  • Extensions and commands that add custom features, notifications, memory, and more.
  • MCP servers and Neovim plugins are explicitly covered.

Related

  • Project
    catlog22/maestro-flow

    Maestro‑Flow is a TypeScript/Node.js framework that turns natural‑language intents into full‑stack development pipelines executed by multiple LLM agents (Claude, Gemini, Codex, etc.). Its Ralph engine classifies intents into 40+ command chains, dynamically decides at “decision” checkpoints whether to continue, roll back, or insert repair loops, and stores discovered patterns in a SQLite knowledge graph that is automatically injected into later runs. It supports four coordination modes (Delegate, Team, Wave, Swarm), long‑running autonomous loops via the Odyssey command, and precise literal/semantic code search. Installation is via `npm i -g maestro-flow`, and the tool provides extensive CLI and web‑dashboard documentation.

  • Project
    TsinghuaC3I/MARTI

    An open-source framework for training LLM-based multi-agent systems using reinforcement learning, featuring tree search augmentation for complex reasoning and code generation.

  • Project
    SakanaAI/AI-Scientist-v3

    Agentic Scientist is an open‑source pipeline that turns LLM coding agents into virtual scientists. Starting from a simple task description, it runs a six‑stage process—drafting, investigation, ablations, final evaluation, post‑hoc analysis, and paper generation—each isolated in Docker containers. Users configure agents, models, budgets, and GPU resources via Hydra overrides, run examples like a circle‑packing benchmark, and obtain a reproducible run directory with logs, artefacts, and a compiled manuscript. The project is licensed under Apache 2.0.

  • Project
    FoundationAgents/ReCode

    ReCode is an LLM agent framework that uses recursive code generation to unify high-level planning and low-level action, enabling dynamic granularity control for complex tasks.