Shell ai-agents

Open-source Shell projects categorized as ai-agents

Top 23 Shell ai-agent Projects

  1. awesome-claude-code-subagents

    A collection of 100+ specialized Claude Code subagents covering a wide range of development use cases

    Project mention: Install Sub-agents, Skills, MCP Servers, Slash Commands and Prompts Across AI Tools with agent-add | dev.to | 2026-04-06

    npx -y agent-add \ --mcp '{"playwright":{"command":"npx","args":["-y","@playwright/mcp"]}}' \ --mcp 'https://github.com/modelcontextprotocol/servers.git#.mcp.json' \ --skill 'https://github.com/anthropics/skills.git#skills/pdf' \ --prompt $'# Code Review Rules\n\nAlways review for security issues first.' \ --command 'https://github.com/wshobson/commands.git#tools/security-scan.md' \ --sub-agent 'https://github.com/VoltAgent/awesome-claude-code-subagents.git#categories/01-core-development/backend-developer.md'

  2. SaaSHub

    SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

    SaaSHub logo
  3. ralph-claude-code

    Autonomous AI development loop for Claude Code with intelligent exit detection

    Project mention: Your AI Ships Code While You Sleep. Who Maintains It When You Wake? | dev.to | 2026-03-13

    Ralph for Claude Code - autonomous loops

  4. agent-scripts

    Scripts for agents, shared between my repositories.

    Project mention: Teaching Alfred to Remember with a Neuroscience-Inspired Memory System for AI Agents | dev.to | 2026-04-19

    Now, I am not the first person to think about this for AI agents. I went looking to see who else had wrestled with it. OpenClaw had already built something that went viral so I decided to see how Peter Steinberger handled memory. For those who dont know, OpenClaw is an open source personal AI assistant project. Peter's approach to memory was almost aligned with what I had been reading in cognitive science. They had not just borrowed the vocabulary; they had borrowed the architecture. OpenClaw then became an added inspiration

  5. gaianet-node

    Install, run and deploy your own decentralized AI agent service

    Project mention: Getting Started with Gaia: A Developer's Guide to Building AI Agents with Gaia | dev.to | 2025-09-04

    # Install Gaia node curl -sSfL 'https://github.com/GaiaNet-AI/gaianet-node/releases/latest/download/install.sh' | bash # Initialize with your preferred model gaianet init --config https://raw.githubusercontent.com/GaiaNet-AI/node-configs/main/llama-3-groq-8b-tool/config.json # Start your node gaianet start

  6. Product-Manager-Skills

    Product Management skills framework built on battle-tested methods for Claude Code, Cowork, Codex, and AI agents. (by deanpeters)

    Project mention: How to Write Workflow Skills: Patterns and Best Practices Distilled from 7 Top Projects | dev.to | 2026-04-28

    [5] deanpeters/Product-Manager-Skills — discovery-process: https://github.com/deanpeters/Product-Manager-Skills/tree/main/skills/discovery-process

  7. Generative-Media-Skills

    Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video, and audio generation powered by muapi.ai.

  8. ODS

    Turn your PC, Mac, or Linux box into an AI server. LLM inference, chat UI, voice, agents, workflows, RAG, and image generation.

    Project mention: Show HN: Dream Server – Turn your PC, Mac, or Linux box into a private AI server | news.ycombinator.com | 2026-06-14
  9. agent-safehouse

    Sandbox your local AI agents so they can read/write only what they need

    Project mention: Ask HN: Secure Wrapper for Coding Agents | news.ycombinator.com | 2026-06-30

    https://agent-safehouse.dev/

    Originally posted on HN https://news.ycombinator.com/item?id=47301085

  10. selfhost-ai

    🚀 Self-hosted AI automation platform. Deploy n8n, Ollama, Flowise, RAG, Supabase & 30+ tools with one command. Auto HTTPS. Free Zapier/Make alternative.

  11. claude_code_agent_farm

    Orchestration framework for running 20+ Claude Code agents in parallel: automated bug fixing, best-practices sweeps, lock-based coordination, and real-time tmux monitoring

  12. llm-functions

    Easily create LLM tools and agents using plain Bash/JavaScript/Python functions.

  13. Aegis

    Make AI coding agents architecture-aware: baseline-first, evidence-verified, drift-checked, and safe across long tasks. (by GanyuanRan)

    Project mention: Aegis: A Method Pack for More Reliable AI Coding Agents | dev.to | 2026-05-17

    GitHub: https://github.com/GanyuanRan/Aegis

  14. ContextKit

    Claude Code context engineering & planning system for individual AI development workflows

  15. GAAI-framework

    Turns AI coding tools into reliable software delivery systems. Drop a .gaai/ folder into any project — Discovery defines what to build, Delivery executes autonomously until criteria pass. Works with Claude Code, Codex CLI, Gemini CLI, Cursor, and more. No SDK. No package. Markdown + YAML + bash.

    Project mention: Show HN: GAAI – One agent plans, one codes. A Markdown folder governs both | news.ycombinator.com | 2026-03-12
  16. forall

    Coding agent for code modernization

    Project mention: Atlas: Coding Agent for Legacy Codebases | news.ycombinator.com | 2025-12-02
  17. agentsystems

    Self-hosted app store and runtime for AI agents. Install third-party agents, run them on your infrastructure with your own model providers (Ollama, Bedrock, OpenAI, etc.). Container isolation, credential injection, default-deny egress.

    Project mention: Federated app store for self-hosted AI agents (Apache-2.0) | dev.to | 2025-11-04

    GitHub: https://github.com/agentsystems/agentsystems

  18. beadbox

    Native macOS, Windows and Linux GUI for the beads git-backed issue tracker. Built with Tauri, Next.js, and React.

    Project mention: I ship software with 13 AI agents. Here's what that actually looks like | dev.to | 2026-03-03

    The project is Beadbox, a real-time dashboard for monitoring AI coding agents. It's built by the very agent fleet it monitors. The agents write the code, test it, review it, package it, and ship it. I coordinate.

  19. pew-pew-plaza-packs

    AI-powered project management framework based on an opinionated view on effective prompts and a highly modular approach to building effective agents, workflows, templates, prompts and context documents.

  20. shepard-obs-stack

    Self-hosted observability for AI coding agents. Clone. Configure. See.

    Project mention: I Ran Claude Code for 5 Hours and It Burned 26M Tokens. Here's How I Debugged It | dev.to | 2026-03-10

    Originally published on Digital Shepard Repo: shepard-obs-stack

  21. sous-chef

    Claude orchestrates and reviews; Codex CLI implements. A Claude Code plugin for the two-model kitchen: /serve tasks end to end, /simmer goals until green. Your head chef doesn't chop onions.

    Project mention: Sous-Chef, a Claude Code plugin where Fable reviews, Codex implements | news.ycombinator.com | 2026-07-02
  22. claude-code-setup

    Persistent memory system for Claude Code via Markdown. Setup with /init-project, resume with /catchup, wrap with /wrapup. Includes coding standards, MCP servers, and modular skills. Solves context loss after /clear.

    Project mention: Show HN: Claude Code Setup – Persistent context, consistent code, one workflow | news.ycombinator.com | 2026-01-27
  23. claude-code-session-bridge

    Let your Claude Code sessions talk to each other 🤖💬

    Project mention: Session-bridge plugin for Claude Code | news.ycombinator.com | 2026-03-15
  24. git-native-issue

    Distributed issue tracking embedded in Git — track issues locally, sync anywhere, no server required

    Project mention: Show HN: Git-native-issue – issues stored as commits in refs/issues/ | news.ycombinator.com | 2026-02-24

    I built git-native-issue (https://github.com/remenoscodes/git-native-issue), a distributed issue tracker that stores issues as Git commits under refs/issues/.

    In April 2007, during a flame war about the Linux 2.6.21 release, Linus wrote:

    "There must be some better form of bug tracking than bugzilla. Some really distributed way of letting people work together, without having to congregate on some central web-site kind of thing. A 'git for bugs', where you can track bugs locally and without a web interface."

    Source: https://lore.kernel.org/all/alpine.LFD.0.98.0704290848360.99...

    19 years later, nobody shipped this. 10+ tools tried (Bugs Everywhere, ticgit, git-bug, git-dit, git-appraise, git-issue). All failed for similar reasons — mostly file-based storage that breaks on merge, and no format spec for ecosystem adoption.

    The core insight: issues are append-only event logs, and Git is a distributed append-only database. So I mapped issue tracking directly to Git primitives:

      - Commits = issue events (creation, comments, state changes)

NOTE: The open source projects on this list are ordered by number of github stars. The number of mentions indicates repo mentiontions in the last 12 Months or since we started tracking (Dec 2020).

Shell ai-agents discussion

Log in or Post with

Shell ai-agents related posts

  • Day 2: My human removed himself from the experiment — so I pivoted from developers to Portuguese guesthouses

    1 project | dev.to | 7 Jul 2026
  • Show HN: L0/L1/L2 agents, leases, gates, audits, Git-worktree isolation

    1 project | news.ycombinator.com | 24 Jun 2026
  • Show HN: Agentic coding workflows built on Git worktrees and task evidence

    1 project | news.ycombinator.com | 20 Jun 2026
  • Ask HN: Is anyone using the A2A protocol yet?

    3 projects | news.ycombinator.com | 18 Jun 2026
  • Show HN: Dream Server – Turn your PC, Mac, or Linux box into a private AI server

    1 project | news.ycombinator.com | 14 Jun 2026
  • Turn Anything into an AI Server

    1 project | news.ycombinator.com | 14 Jun 2026
  • Loopcraft: Stop Prompting, Start Designing Loops

    4 projects | dev.to | 13 Jun 2026
  • A note from our sponsor - SaaSHub
    www.saashub.com | 15 Jul 2026
    SaaSHub helps you find the best software and product alternatives Learn more →

Index

What are some of the best open-source ai-agent projects in Shell? This list will help you:

# Project Stars
1 awesome-claude-code-subagents 23,132
2 ralph-claude-code 9,524
3 agent-scripts 5,707
4 gaianet-node 5,022
5 Product-Manager-Skills 3,844
6 Generative-Media-Skills 3,807
7 ODS 2,934
8 agent-safehouse 1,909
9 selfhost-ai 897
10 claude_code_agent_farm 852
11 llm-functions 759
12 Aegis 251
13 ContextKit 168
14 GAAI-framework 150
15 forall 139
16 agentsystems 109
17 beadbox 92
18 pew-pew-plaza-packs 82
19 shepard-obs-stack 70
20 sous-chef 58
21 claude-code-setup 56
22 claude-code-session-bridge 54
23 git-native-issue 45

Sponsored
SaaSHub - Software Alternatives and Reviews
SaaSHub helps you find the best software and product alternatives
www.saashub.com

Did you know that Shell is
the 8th most popular programming language
based on number of references?