License-aware Markdown snapshots collected from GitHub
This repository is a collection of reference implementations for the Model Context Protocol (MCP), as well as references to community-built servers and additional resources. The servers in this repository showcase the versatility and extensibility of MCP, demonstrating how it can be used to give Large Language Models (LLMs) secure, controlled access to tools and data sources.
English| 简体中文 Official Website | Docs | Contribution Guide RuleGo is a lightweight, high-performance, embedded, orchestrable component-based rule engine built on the Go language. It can help you quickly build loosely coupled and flexible systems that can respond and adjust to changes in business requirements in real time.
• Documentation • PowerShell-Native AI Agents & Multi-Agent Orchestration PSAI is a high-agency framework designed to bridge the gap between robust systems engineering and Large Language Models. Built for developers and architects, it transforms AI from a "chatbot" into a functional engineering component within your existing PowerShell ecosystem.
API Dash is a beautiful AI powered open-source cross-platform API Client that can help you easily create & customize your API requests, visually inspect responses (full list of supported mime-types) and generate API integration code (full list) on the go. Dashbot is the AI assistant available in API Dash (powered by local or cloud LLM) so that you can interact with your requests to debug it, generate code, generate doc, and many more.
pg-mem is an experimental in-memory emulation of a postgres database. ⭐ this repo if you like this package, it helps to motivate me :) 👉 See it in action with pg-mem playground As always, it starts with an: Then, assuming you're using something like webpack, if you're targeting a browser: Pretty straightforward :) ❤ Head to the pgsql-ast-parser repo The sql syntax parser is home-made.
The LLM ecosystem has amazing infrastructure (LoRAX, PEFT, vLLM), but lacks standardized, high-quality capability adapters. Problem: Base models limited to 32K context, need 2M tokens for large repositories Solution: Progressive curriculum learning with vLLM + Unsloth hybrid approach Key Innovation: Hybrid optimization combining vLLM's inference speed with Unsloth's training efficiency - achieving 61x context extension with minimal compute!
LLM Finetuning toolkit is a config-based CLI tool for launching a series of LLM fine-tuning experiments on your data and gathering their results. From one single yaml config file, control all elements of a typical experimentation pipeline - prompts, open-source LLMs, optimization strategy and LLM testing.
中文 Rainbond helps teams build, deploy, upgrade, operate, and privately deliver applications without deeply learning Kubernetes. It is better suited for private deployment, offline delivery, Xinchuang adaptation, application marketplace delivery, and AI application privatization scenarios.
![alt text][logo] ![alt text][overview] To start using POCO, see the Guided Tour and Getting Started documents. Most Unix/Linux systems already have OpenSSL preinstalled.
Training and inference code for audio generation models Requires PyTorch 2.5 or later for Flash Attention and Flex Attention support. Development for the repo is done in Python 3.10.
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.
Version, test, and monitor every prompt and agent with robust evals, tracing, and regression sets. --- This library provides convenient access to the PromptLayer API from applications written in python.
A quick reminder of all relevant SQL queries and examples on how to use them. This repository is constantly being updated and added to by the community.
KoboldCpp is an easy-to-use AI text-generation software for GGML and GGUF models, inspired by the original KoboldAI. It's a single self-contained distributable that builds off llama.cpp and adds many additional powerful features.
code examples with explanations, different use cases and links to further readings. It is a playground because you may change or add the code to see how it works and test it out using assertions.
SEOTools - SEO Tools for Laravel and Lumen SEOTools is a package for Laravel 5.8+ and Lumen that provides helpers for some common SEO techniques. For license information check the LICENSE-file.
We also introduce a diffusion-based value model that reduces variance and improves stability during optimization. Based on TraceRL, we derive a series of diffusion language models, TraDo, which achieve state-of-the-art performance on math and coding reasoning tasks.
A Laravel and Filament-powered accounting platform featuring full double-entry accrual accounting, delivering modern automation for professional financial management. While ERPSAAS is open-source, maintaining it requires significant time and resources.
Agentic Document Extraction (ADE), from your terminal. The ade command drives LandingAI's ADE v2 document APIs — parse turns visually complex documents (tables, figures, charts) into grounded markdown and elements; extract pulls schema-shaped fields with page-and-box evidence — and persists everything it produces in a local store (~/.ade), serving every read from it.
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.
License-aware Markdown snapshots collected from GitHub
This repository is a collection of reference implementations for the Model Context Protocol (MCP), as well as references to community-built servers and additional resources. The servers in this repository showcase the versatility and extensibility of MCP, demonstrating how it can be used to give Large Language Models (LLMs) secure, controlled access to tools and data sources.
English| 简体中文 Official Website | Docs | Contribution Guide RuleGo is a lightweight, high-performance, embedded, orchestrable component-based rule engine built on the Go language. It can help you quickly build loosely coupled and flexible systems that can respond and adjust to changes in business requirements in real time.
• Documentation • PowerShell-Native AI Agents & Multi-Agent Orchestration PSAI is a high-agency framework designed to bridge the gap between robust systems engineering and Large Language Models. Built for developers and architects, it transforms AI from a "chatbot" into a functional engineering component within your existing PowerShell ecosystem.
API Dash is a beautiful AI powered open-source cross-platform API Client that can help you easily create & customize your API requests, visually inspect responses (full list of supported mime-types) and generate API integration code (full list) on the go. Dashbot is the AI assistant available in API Dash (powered by local or cloud LLM) so that you can interact with your requests to debug it, generate code, generate doc, and many more.
pg-mem is an experimental in-memory emulation of a postgres database. ⭐ this repo if you like this package, it helps to motivate me :) 👉 See it in action with pg-mem playground As always, it starts with an: Then, assuming you're using something like webpack, if you're targeting a browser: Pretty straightforward :) ❤ Head to the pgsql-ast-parser repo The sql syntax parser is home-made.
The LLM ecosystem has amazing infrastructure (LoRAX, PEFT, vLLM), but lacks standardized, high-quality capability adapters. Problem: Base models limited to 32K context, need 2M tokens for large repositories Solution: Progressive curriculum learning with vLLM + Unsloth hybrid approach Key Innovation: Hybrid optimization combining vLLM's inference speed with Unsloth's training efficiency - achieving 61x context extension with minimal compute!
LLM Finetuning toolkit is a config-based CLI tool for launching a series of LLM fine-tuning experiments on your data and gathering their results. From one single yaml config file, control all elements of a typical experimentation pipeline - prompts, open-source LLMs, optimization strategy and LLM testing.
中文 Rainbond helps teams build, deploy, upgrade, operate, and privately deliver applications without deeply learning Kubernetes. It is better suited for private deployment, offline delivery, Xinchuang adaptation, application marketplace delivery, and AI application privatization scenarios.
![alt text][logo] ![alt text][overview] To start using POCO, see the Guided Tour and Getting Started documents. Most Unix/Linux systems already have OpenSSL preinstalled.
Training and inference code for audio generation models Requires PyTorch 2.5 or later for Flash Attention and Flex Attention support. Development for the repo is done in Python 3.10.
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.
Version, test, and monitor every prompt and agent with robust evals, tracing, and regression sets. --- This library provides convenient access to the PromptLayer API from applications written in python.
A quick reminder of all relevant SQL queries and examples on how to use them. This repository is constantly being updated and added to by the community.
KoboldCpp is an easy-to-use AI text-generation software for GGML and GGUF models, inspired by the original KoboldAI. It's a single self-contained distributable that builds off llama.cpp and adds many additional powerful features.
code examples with explanations, different use cases and links to further readings. It is a playground because you may change or add the code to see how it works and test it out using assertions.
SEOTools - SEO Tools for Laravel and Lumen SEOTools is a package for Laravel 5.8+ and Lumen that provides helpers for some common SEO techniques. For license information check the LICENSE-file.
We also introduce a diffusion-based value model that reduces variance and improves stability during optimization. Based on TraceRL, we derive a series of diffusion language models, TraDo, which achieve state-of-the-art performance on math and coding reasoning tasks.
A Laravel and Filament-powered accounting platform featuring full double-entry accrual accounting, delivering modern automation for professional financial management. While ERPSAAS is open-source, maintaining it requires significant time and resources.
Agentic Document Extraction (ADE), from your terminal. The ade command drives LandingAI's ADE v2 document APIs — parse turns visually complex documents (tables, figures, charts) into grounded markdown and elements; extract pulls schema-shaped fields with page-and-box evidence — and persists everything it produces in a local store (~/.ade), serving every read from it.
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.