# #llm — MDRSS hashtag feed

> Public MDRSS cards tagged #llm.
> Canonical feed: https://mdrss.com/feeds/llm

## Cards (56)

### [Preference Optimization](https://mdrss.com/llm-engineering/training-and-fine-tuning/901373/901373.md)

This skill assumes finetuning-method-selection already routed here because the data shape is preference pairs or unpaired thumbs-up/down feedback, not demonstrations (that's lora-qlora-recipes) or a verifiable reward signal (that's grpo-rlvr-training). What follows is metho. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [GRPO & RLVR Training](https://mdrss.com/llm-engineering/training-and-fine-tuning/901368/901368.md)

This skill assumes finetuning-method-selection already routed here because the target behavior has a verifiable pass/fail signal — not demonstrations (lora-qlora-recipes) or preference pairs (preference-optimization). What follows is when RL is the right tool, the reference. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Judge Calibration Protocol](https://mdrss.com/llm-engineering/training-and-fine-tuning/901365/901365.md)

The full procedure behind SKILL.md's "Judge Calibration Is a Prerequisite" section. Any grader routed to an LLM-judge follows this before its verdicts count toward a pass rate or a checkpoint promotion decision. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Fine-tune for: $ARGUMENTS](https://mdrss.com/llm-engineering/training-and-fine-tuning/901357/901357.md)

This command orchestrates the eval-gated fine-tuning lifecycle across seven phases, each owned by a specialist agent and gated by the artifact the prior phase produced:. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Llm finetuning training engineer](https://mdrss.com/llm-engineering/training-and-fine-tuning/901356/901356.md)

You are the fine-tuning training engineer: the workhorse who takes a training-brief.md someone else already justified and turns it into a dataset, a running job, and an exported artifact. You don't re- litigate method or model choice, and you don't decide whether a checkpoint s. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Llm finetuning architect](https://mdrss.com/llm-engineering/training-and-fine-tuning/901354/901354.md)

You are the fine-tuning architect: a skeptical strategist who decides whether fine-tuning is the right tool at all before anyone opens a training config. You are the gate-keeper standing between "the user wants to fine-tune" and the first line of a training script — most requests. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Ai engineer](https://mdrss.com/ai-agents/agent-design-and-orchestration/901338/901338.md)

You are an AI engineer specializing in production-grade LLM applications, generative AI systems, and intelligent agent architectures. Use it to give an agent explicit responsibilities, steps and constraints.

Classification: ai-agents/agent-design-and-orchestration · Feed: ai-agents · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [LLM (Large Language Models) FineTuning Projects and notes on common practical techniques](https://mdrss.com/llm-engineering/training-and-fine-tuning/901107/901107.md)

logo : https://github.com/rohan-paul/rohan-paul/blob/master/assets/png. Use it when a task needs concrete terminology, constraints or implementation detail.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [Awesome LLM Security](https://mdrss.com/ai-agents/prompting-and-agent-evaluation/901057/901057.md)

A curation of awesome tools, documents and projects about LLM Security. Use it to navigate the topic and choose relevant methods, papers or tools.

Classification: ai-agents/prompting-and-agent-evaluation · Feed: ai-agents · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [AQLM](https://mdrss.com/llm-engineering/inference-and-quantization/901037/901037.md)

Official PyTorch implementation for Extreme Compression of Large Language Models via Additive Quantization. Use it to navigate the topic and choose relevant methods, papers or tools.

Classification: llm-engineering/inference-and-quantization · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [SAM3-LoRA: Efficient Fine-Tuning with Low-Rank Adaptation](https://mdrss.com/llm-engineering/training-and-fine-tuning/901032/901032.md)

Quick Start • Architecture • Training • Validation • Inference • Examples • Configuration • Troubleshooting. Use it to ground design choices in named patterns, trade-offs and examples.

Classification: llm-engineering/training-and-fine-tuning · Feed: llm-engineering · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [LLM Zoomcamp: Retrieval and LLM Engineering Curriculum](https://mdrss.com/learning/courses-roadmaps-and-reference/901009/901009.md)

LLM Zoomcamp: Free Course on Building LLM Applications with RAG, Agents & Vector Search Go from LLM basics to a production-ready AI assistant in 10 weeks. Use it to build a structured path from fundamentals to hands-on practice.

Classification: learning/courses-roadmaps-and-reference · Feed: learning · Updated: 2026-08-04T13:54:51.641Z · Version: 1

### [medAlpaca: Finetuned Large Language Models for Medical Question Answering](https://mdrss.com/llm-engineering/evaluation/2676/2676.md)

MedAlpaca expands upon both Stanford Alpaca and AlpacaLoRA to offer an advanced suite of large language models specifically fine-tuned for medical question-answering and dialogue applications. Our primary objective is to deliver an array of open-source language models, paving the way for seamless development of medical chatbot solutions.

Classification: llm-engineering/evaluation · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Integuru v0](https://mdrss.com/ai-agents/agent-frameworks/2662/2662.md)

This repo contains the earliest version of the Integuru agent we released publicly. It shows the original approach: using browser network requests to generate runnable integration code for platforms without official APIs.

Classification: ai-agents/agent-frameworks · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Claude Design System Prompt](https://mdrss.com/ai-agents/coding-agents/2366/2366.md)

Reverse-engineered system prompt of Claude Design from Anthropic. A system prompt and skill library that turns an LLM into an opinionated, accessibility-aware, AI-slop-resistant design collaborator.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [ZodGPT](https://mdrss.com/llm-engineering/models-and-training/2330/2330.md)

Get structured, fully typed, and validated JSON outputs from OpenAI and Anthropic models. Under the hood, zod-gpt uses functions to coerce the model to always respond as function calls.

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Desktop App](https://mdrss.com/learning/writing-and-communication/2287/2287.md)

MarkPDFDown English | 中文 | 日本語 | Русский | فارسی | العربية  ! Size huburl   ! Pulls huburl   ! Tag tagurl   ! License licenseurl  A powerful tool that leverages multimodal large language models to transcribe PDF files into Markdown format. Try our desktop application for a more user-friendly experience!

Classification: learning/writing-and-communication · Feed: learning · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Why LoongForge?](https://mdrss.com/llm-engineering/models-and-training/2269/2269.md)

English | 简体中文 A unified, high-performance framework for training LLMs, VLMs, diffusion, and embodied models. 🌐 Website  ·  📖 Docs  ·  ✍️ Blog  ·  ⚡ Quick Start  ·  📊 Performance  ·  🏛️ Supported Models  ·  💬 Contact LoongForge is a unified training framework for LLMs, VLMs, diffusion, and embodied models, covering pre-training, continued pre-training, and SFT.

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Prompt Decorators Framework](https://mdrss.com/ai-agents/prompting/2245/2245.md)

Prompt Decorators extend the functionality of large language models by allowing structured, modular control over reasoning, style, and behavior. Each decorator enforces specific response rules, enabling users to declaratively modify how the model thinks and writes — without retraining.

Classification: ai-agents/prompting · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [wllama - Wasm binding for llama.cpp](https://mdrss.com/llm-engineering/models-and-training/2180/2180.md)

For embeddings, please see examples/embeddings/index.html WebGPU support is introduced via PR #215. Upon updating to V3.1, WebGPU will be enabled automatically.

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [The invariant: agents outlive callers](https://mdrss.com/ai-agents/agent-frameworks/2176/2176.md)

Kheish Persistent agent runtime and control plane for long-lived, tool-using AI workflows.   --- Kheish enforces one rule: Everything else in this README is a consequence of that single invariant.

Classification: ai-agents/agent-frameworks · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [METATRON](https://mdrss.com/software-craft/testing-and-quality/2083/2083.md)

AI-powered penetration testing assistant using local LLM on linux (Parrot OS) --- Metatron is a CLI-based AI penetration testing assistant that runs entirely on your local machine — no cloud, no API keys, no subscriptions. It runs real recon tools (nmap, whois, whatweb, curl, dig, nikto), feeds all results to a locally running AI model, and the AI analyzes the target, identifies vulnerabilities, suggests exploits, and recommends fixes.

Classification: software-craft/testing-and-quality · Feed: software-craft · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [rwkv.cpp](https://mdrss.com/llm-engineering/serving-and-retrieval/2075/2075.md)

This is a port of BlinkDL/RWKV-LM to ggerganov/ggml. Besides the usual FP32, it supports FP16, quantized INT4, INT5 and INT8 inference.

Classification: llm-engineering/serving-and-retrieval · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [News](https://mdrss.com/llm-engineering/evaluation/1925/1925.md)

This is the official repository for ICLR 2025 paper "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Magpie generates high-quality alignment data by prompting aligned LLMs with their pre-query templates.

Classification: llm-engineering/evaluation · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [go-agent](https://mdrss.com/ai-agents/agent-frameworks/1856/1856.md)

go-agent is a Go framework for building AI agents with pluggable LLM providers, memory, file context, guardrails, UTCP tool orchestration, and multi-agent coordination. Use it when you want agent runtime pieces that stay idiomatic in Go: For this repository: The module currently targets Go 1.25.10.

Classification: ai-agents/agent-frameworks · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [RouteLLM](https://mdrss.com/llm-engineering/models-and-training/1821/1821.md)

RouteLLM is a framework for serving and evaluating LLM routers.  Blog    Paper   Our core features include: From PyPI From source Let's walkthrough replacing an existing OpenAI client to route queries between LLMs instead of using only a single model.

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Key Features](https://mdrss.com/llm-engineering/models-and-training/1774/1774.md)

MASFactory is a graph-centric framework for orchestrating Multi-Agent Systems with Vibe Graphing: Start from intent, generate a graph design, preview and refine it in a visual environment, compile it into an executable workflow, and trace node states, messages, and shared state at runtime. Turn natural-language intent into a structural design, then iteratively converge to an executable, reusable workflow.

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [About UltraRAG](https://mdrss.com/llm-engineering/models-and-training/1608/1608.md)

Designed for research exploration and industrial prototyping, UltraRAG standardizes core RAG components (Retriever, Generation, etc.) as independent MCP Servers, combined with the powerful workflow orchestration capabilities of the MCP Client. Developers can achieve precise orchestration of complex control structures such as conditional branches and loops simply through YAML configuration.

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [AutoRAG](https://mdrss.com/llm-engineering/serving-and-retrieval/1593/1593.md)

A self-evolving librarian agent for document collections. AutoRAG searches your PDFs, wikis, notes, research papers, and knowledge bases — then curates the results into clean, numbered knowledge units.

Classification: llm-engineering/serving-and-retrieval · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Instructor Php](https://mdrss.com/ai-agents/agent-frameworks/1575/1575.md)

This monorepo contains a set of dev-friendly, framework agnostic components offering 3 main capabilities: Framework integration packages: The library offers a set of small, focused building blocks. Purpose: turn messy model output into typed PHP data.

Classification: ai-agents/agent-frameworks · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Demo](https://mdrss.com/llm-engineering/models-and-training/1557/1557.md)

A self-contained image bundles the tool + the Claude Code and Codex CLIs. You log in once and the sessions persist in named volumes — no re-login on later runs.

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale](https://mdrss.com/ai-agents/agent-frameworks/1549/1549.md)

Towards Async, Omni-Modal RL at Scale, Just Relax. 📖 English | 📖 中文 Relax (Reinforcement Engine Leveraging Agentic X-modality) is a high-performance reinforcement learning post-training framework open-sourced by the Xiaohongshu AI Infra Team for multimodal large language models.

Classification: ai-agents/agent-frameworks · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [llama.rn](https://mdrss.com/web-mobile/mobile-development/1537/1537.md)

React Native binding of llama.cpp - LLM inference in C/C++ Key Features: llama.rn downloads the pre-built ios/rnllama.xcframework and android/src/main/jniLibs from the matching GitHub release during postinstall. Existing downloads are reused, and each archive is verified with SHA-256 before extraction.

Classification: web-mobile/mobile-development · Feed: web-mobile · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [LLM Zoo: democratizing ChatGPT](https://mdrss.com/llm-engineering/serving-and-retrieval/1511/1511.md)

⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡  Tech Report (assets/llmzoo.pdf) technology gifted by the creator. For example, many pioneers have made great efforts to spread the use of light bulbs and vaccines to developing countries.

Classification: llm-engineering/serving-and-retrieval · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [DocStrange](https://mdrss.com/learning/writing-and-communication/1499/1499.md)

DocStrange converts documents to Markdown, JSON, CSV, and HTML quickly and accurately. --- August 2025 --- Convert and extract data from PDF, DOCX, images, and more into clean Markdown and structured JSON.

Classification: learning/writing-and-communication · Feed: learning · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Magic - Enterprise-Grade Open-Source AI Agent Platform](https://mdrss.com/ai-agents/mcp-and-tools/1436/1436.md)

🦞 OpenClaw is a great personal AI assistant — connecting all major IMs as conversation channels, supporting any LLM, running autonomously 24/7. But when we bring it into an enterprise context, new challenges naturally emerge: data scattered across individual accounts, no budget guardrails, output that stops at plain text, high-risk actions without an approval gate.

Classification: ai-agents/mcp-and-tools · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [text-extract-api](https://mdrss.com/multimodal/vision-and-media/1370/1370.md)

Convert any image, PDF or Office document to Markdown text or JSON structured document with super-high accuracy, including tabular data, numbers or math formulas. The API is built with FastAPI and uses Celery for asynchronous task processing.

Classification: multimodal/vision-and-media · Feed: multimodal · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Augustus - LLM Vulnerability Scanner](https://mdrss.com/llm-engineering/models-and-training/1347/1347.md)

Augustus is a Go-based LLM vulnerability scanner for security professionals. It tests large language models against a wide range of adversarial attacks, integrates with 28 LLM providers, and produces actionable vulnerability reports.

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [GitMCP](https://mdrss.com/ai-agents/mcp-and-tools/1319/1319.md)

What is GitMCP • Features • Getting Started • How It Works • Badge • Examples • FAQ • Privacy • Contributing • License Stop vibe-hallucinating and start vibe-coding! GitMCP is a free, open-source, remote Model Context Protocol (MCP) server that transforms any GitHub project (repositories or GitHub pages) into a documentation hub.

Classification: ai-agents/mcp-and-tools · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Evalscope](https://mdrss.com/llm-engineering/serving-and-retrieval/1280/1280.md)

中文 &nbsp ｜ &nbsp English &nbsp 📖 中文文档 &nbsp ｜ &nbsp 📖 English Documentation EvalScope is a one-stop LLM evaluation framework built by the ModelScope Community. Just one command to start — it supports model capability evaluation, inference performance stress testing, and result visualization.

Classification: llm-engineering/serving-and-retrieval · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU](https://mdrss.com/llm-engineering/serving-and-retrieval/1244/1244.md)

PowerInfer is a CPU/GPU LLM inference engine leveraging activation locality for your device. Project Kanban https://github.com/SJTU-IPADS/PowerInfer/assets/34213478/fe441a42-5fce-448b-a3e5-ea4abb43ba23 PowerInfer v.s.

Classification: llm-engineering/serving-and-retrieval · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Enterprise](https://mdrss.com/llm-engineering/models-and-training/1188/1188.md)

🚅 LiteLLM LiteLLM AI Gateway Open Source AI Gateway for 100+ LLMs. LiteLLM Proxy Server (AI Gateway) | Hosted Proxy | Enterprise Tier | Website --- LiteLLM is an open source AI Gateway that gives you a single, unified interface to call 100+ LLM providers — OpenAI, Anthropic, Gemini, Bedrock, Azure, and more — using the OpenAI format.

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Get Started](https://mdrss.com/ai-agents/mcp-and-tools/1184/1184.md)

# The Unofficial and Awesome Home Assistant MCP Server A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with Home Assistant. Using natural language, control smart home devices, query states, execute services and manage your automations.

Classification: ai-agents/mcp-and-tools · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Awesome-LLM](https://mdrss.com/llm-engineering/models-and-training/1174/1174.md)

🔥 Large Language Models(LLM) have taken the ~~NLP community~~ ~~AI community~~ the Whole World by storm. Here is a curated list of papers about large language models, especially relating to ChatGPT.

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Peft](https://mdrss.com/llm-engineering/models-and-training/1168/1168.md)

🤗 PEFT State-of-the-art Parameter-Efficient Fine-Tuning (PEFT) methods Fine-tuning large pretrained models is often prohibitively costly due to their scale. Parameter-Efficient Fine-Tuning (PEFT) methods enable efficient adaptation of large pretrained models to various downstream applications by only fine-tuning a small number of (extra) model parameters instead of all the model's parameters.

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [TencentDB Agent Memory](https://mdrss.com/ai-agents/agent-frameworks/1102/1102.md)

· Team Play · Technical Implementation · Benchmark English · 简体中文 --- Start all three services in one go (memory-core + memory-hub + proxy): Open the panel: http://localhost:8125. Complete installation documentation (standalone Memory Hub deployment, Proxy + Claude Code / CodeBuddy usage, stop and cleanup, port reference, etc.) is available in INSTALL.md (中文: INSTALLCN.md).

Classification: ai-agents/agent-frameworks · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [LLM Course](https://mdrss.com/llm-engineering/serving-and-retrieval/1089/1089.md)

𝕏 Follow me on X • 🤗 Hugging Face • 💻 Blog • 📙 LLM Engineer's Handbook The LLM course is divided into three parts: 1. 🧩 LLM Fundamentals is optional and covers fundamental knowledge about mathematics, Python, and neural networks.

Classification: llm-engineering/serving-and-retrieval · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Welcome](https://mdrss.com/llm-engineering/evaluation/1051/1051.md)

Just like a compass guides us on our journey, OpenCompass will guide you through the complex landscape of evaluating large language models. With its powerful algorithms and intuitive interface, OpenCompass makes it easy to assess the quality and effectiveness of your NLP models.

Classification: llm-engineering/evaluation · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Awesome MCP Servers](https://mdrss.com/ai-agents/mcp-and-tools/1038/1038.md)

A curated, community-driven list of awesome Model Context Protocol (MCP) servers, tools, frameworks, clients, and utilities. MCP is an open protocol that enables AI models to securely interact with local and remote resources through standardized server implementations.

Classification: ai-agents/mcp-and-tools · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [ODS](https://mdrss.com/llm-engineering/serving-and-retrieval/1025/1025.md)

Osmantic Deployment System Turn your PC, Mac, or Linux box into a private AI server. AI server and homelab setup is rapidly becoming a solved problem.

Classification: llm-engineering/serving-and-retrieval · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Open Deep Research](https://mdrss.com/ai-agents/agent-frameworks/999/999.md)

Deep research has broken out as one of the most popular agent applications. This is a simple, configurable, fully open source deep research agent that works across many model providers, search tools, and MCP servers.

Classification: ai-agents/agent-frameworks · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Inference is all you need. Everything else can be owned by you](https://mdrss.com/ai-agents/mcp-and-tools/998/998.md)

Agents, memory, tools, and identity that live on your Mac. Download for Mac · Docs · Models · Discord · Twitter · Plugin Registry --- Models are getting cheaper and more interchangeable by the day.

Classification: ai-agents/mcp-and-tools · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Caveman](https://mdrss.com/ai-agents/coding-agents/828/828.md)

why use many token when few do trick Make your AI coding agent talk like a caveman. 65% fewer output tokens on prose, 8.5% on agentic coding runs .

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Brex's Prompt Engineering Guide](https://mdrss.com/ai-agents/prompting/814/814.md)

This guide was created by Brex for internal purposes. It's based on lessons learned from researching and creating Large Language Model (LLM) prompts for production use cases.

Classification: ai-agents/prompting · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Ponytail](https://mdrss.com/ai-agents/coding-agents/805/805.md)

~54% less code (up to 94%) · ~20% cheaper · ~27% faster · 100% safe Measured on real Claude Code sessions editing a real open-source repo (FastAPI + React), against the same agent with no skill. ~54% is the mean across 12 feature tasks (Haiku 4.5, n=4); it reaches 94% where an agent over-builds (a date picker) and is near zero where the code is already minimal.

Classification: ai-agents/coding-agents · Feed: ai-agents · Updated: 2026-08-04T12:22:38.168Z · Version: 1

### [Awesome LLM](https://mdrss.com/llm-engineering/models-and-training/737/737.md)

--- 🔥 Large Language Models(LLM) have taken the ~~NLP community~~ ~~AI community~~ the Whole World by storm. Here is a curated list of papers about large language models, especially relating to ChatGPT.

Classification: llm-engineering/models-and-training · Feed: llm-engineering · Updated: 2026-08-04T12:22:38.168Z · Version: 1