Top 23 Shell LLM Projects

LLM

• Add a project

1. llm-d

   1 4 4,028 9.9 Shell

   Achieve state of the art inference performance with modern accelerators on Kubernetes

   

   Project mention: Reading list (17th to 28th March) | dev.to | 2026-03-28

   llm-d is a high-performance distributed inference serving stack optimized for production deployments on Kubernetes. We help you achieve the fastest "time to state-of-the-art (SOTA) performance" for key OSS large language models across most hardware accelerators and infrastructure providers with well-tested guides and real-world benchmarks. - link [code-repo] - ( Added: 2026-03-24 11:31:22 )

2. SaaSHub

   www.saashub.com sponsored

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

   

3. Bonsai-demo

   2 6 2,222 8.7 Shell

   Bonsai Demo

   

   Project mention: Bonsai 27B: The First 27B-Class Model to Run on a Phone | news.ycombinator.com | 2026-07-14

   Depending on which model you're running, you might need to use the custom forks.

   Details are here -> https://github.com/PrismML-Eng/Bonsai-demo/blob/main/README....

4. agent-safehouse

   3 15 1,977 9.4 Shell

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

   

   Project mention: Auto mode is now the default in Claude Code | news.ycombinator.com | 2026-08-09

   If you use macOS, take a look at Agent Safehouse: https://agent-safehouse.dev

   > macOS-native sandboxing for local agents. Move fast, break nothing.

5. multi-agent-shogun

   4 1 1,412 9.5 Shell

   Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with shogun → karo → ashigaru hierarchy.

   

   Project mention: Show HN: Multi-agent-shogun – tmux and YAML mailbox for parallel AI agents | news.ycombinator.com | 2026-02-10

6. selfhost-ai

   5 1 916 9.4 Shell

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

   

7. llm-functions

   6 1 759 8.1 Shell

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

   

8. ell

   7 6 433 9.0 Shell

   A command-line interface for LLMs written in Bash. (by simonmysun)

   

9. boltmcp

   8 1 367 7.1 Shell

   

10. acip

    9 1 328 8.9 Shell

    The Advanced Cognitive Inoculation Prompt

    

11. ezrknpu

    10 1 251 4.3 Shell

    Easy installation and usage of Rockchip's NPUs found in RK3588 and similar SoCs

    

    Project mention: OrangePi 5 Ultra Review: An ARM64 SBC Powerhouse | news.ycombinator.com | 2025-09-23

    For a quick bring-up and implementation, take a look at this repo: https://github.com/Pelochus/ezrknpu

12. humanscript

    11 1 237 5.7 Shell

    A truly natural scripting language

    

13. total-recall

    12 3 200 7.0 Shell

    Persistent memory plugin for Claude Code. Tiered memory system with write gates, correction propagation, and slash commands.

    

    Project mention: Show HN: Total Recall – write-gated memory for Claude Code | news.ycombinator.com | 2026-02-05

    Opened a design issue for this if anyone wants to follow along or weigh in: https://github.com/davegoldblatt/total-recall/issues/2

14. second-brain

    13 1 197 - Shell

    LLM-maintained personal knowledge base for Obsidian. Based on Andrej Karpathy's LLM Wiki pattern. (by NicholasSpisak)

    

    Project mention: How to Build Karpathy's LLM Wiki: The Complete Guide to AI-Maintained Knowledge Bases | dev.to | 2026-04-22

15. claude-container

    14 5 173 8.3 Shell

    Docker container with Claude Code pre-installed and ready to use. ⚠️ development has moved to VibePod

    

    Project mention: Show HN: VibePod CLI – Run AI agents with isolation and better observability | news.ycombinator.com | 2026-03-03

    - What kind of visibility do you want into agent behavior?

    For context, this grew out of lessons learned building claude-container: https://github.com/nezhar/claude-container

    Would really appreciate thoughts from people actively using multiple AI coding tools.

16. pls

    15 15 146 2.4 Shell

    CLI to convert natural language to terminal commands (by mxdkl)

    

17. agentsystems

    16 2 111 8.8 Shell

    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. Flatty

    17 1 108 8.8 Shell

    transform an entire GitHub repo into a simple text file so that you can upload it to an LLM (Claude, ChatGPT, etc.) (by mattmireles)

    

19. tmux-ai-agent-helper

    18 6 104 9.2 Shell

    Share your TMUX screen with ai chat

    

    Project mention: Improving 15 LLMs at Coding in One Afternoon. Only the Harness Changed | news.ycombinator.com | 2026-02-12

    I use damaru levenshtein distance to assert the edits to be replaced and if the similarity is over some threshold the edit goes through

    Really works well

    https://github.com/day50-dev/sidechat/blob/db9c8f9d834967442...

20. claude-brain

    19 1 78 8.0 Shell

    Sync your Claude Code brain across machines — memory, skills, agents, rules, and settings with intelligent semantic merge. Git-based, auto-sync hooks. (by toroleapinc)

    

    Project mention: Show HN: Claude-brain – Sync your Claude Code brain across machines via Git | news.ycombinator.com | 2026-03-03

21. llmcat

    20 3 77 7.0 Shell

    Prepare files and directories for LLM consumption

    

22. faff

    21 1 47 7.3 Shell

    Drop the faff, dodge the judgment. Another bloody AI commit generator, but this one stays local 🦙

    

23. shellm

    22 1 32 7.5 Shell

    A one-file Ollama CLI client written in bash (by Biont)

    

24. agent-images

    23 1 29 9.3 Shell

    Sandboxed OCI container images for AI coding agents, built reproducibly with Nix.

    

    Project mention: A way to exclude sensitive files issue still open for OpenAI Codex | news.ycombinator.com | 2026-06-28

    I've contributed to https://github.com/0xferrous/agent-box which allows you to bind-mount git repositories into containers that agents operate in. Your usual .gitignore can then be used to ignore files to be bind-mounted, which preventa agents from accessing them at all.

    I've also created https://github.com/nothingnesses/agent-images which allows you to use Nix to reproducibly spin up OCI containers containing agents and use these with agents-box.

    I use both at the moment to work on some personal projects with agents, where I set up multiple separate git worktrees for the agents to work in and that prevents them from trampling over each other's work.

Shell LLM related posts

• Auto Mode will be the default in Claude Code – because humans can't be trusted

  1 project | news.ycombinator.com | 8 Aug 2026

• How to stop Claude from saying load-bearing

  11 projects | news.ycombinator.com | 14 Jul 2026

• My Agentic Engineering Workflow

  10 projects | dev.to | 21 Jun 2026

• Building Cost-Effective AI Workflows: Open Source + Paid Tools Done Right

  1 project | dev.to | 20 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

• Watch an LLM Think

  1 project | dev.to | 6 Jun 2026
• A note from our sponsor - SaaSHub
  www.saashub.com | 16 Aug 2026

  SaaSHub helps you find the best software and product alternatives Learn more →

Index

Sponsored

SaaSHub - Software Alternatives and Reviews

SaaSHub helps you find the best software and product alternatives

www.saashub.com

Do not miss the trending Shell projects with our weekly report!