llm

Fully Configurable RAG Pipeline for Bengali Language RAG Applications. Supports both Local and Huggingface Models, Built with Langchain.

Testing speed and accuracy of RAG with, and without Cross Encoder Reranker.

Git for Agent Memory: Copy-On-Write vector branching for embedded multi-agent memory (83x faster, 3000x smaller snapshots)

[⛔️ DEPRECATED] Friendli: the fastest serving engine for generative AI

LLM Powered discord bot, Character Card enabled Chat page, Stable Diffusion discord bot, and overall AI tool. All from one app, TalOS.

A Unified Framework for Benchmarking Generative Electrocardiogram-Language Models (ELMs)

Stop paying for AI APIs during development. LocalCloud runs everything locally - GPT-level models, databases, all free.

Arks is a cloud-native inference framework running on Kubernetes

Open source Enterprise AI Gateway for API, MCP and agent, and AI model traffic. One Apache-2.0 binary: 72 native providers behind an OpenAI-compatible API, or serve vLLM and llama.cpp on your own GPUs. Keys, budgets, guardrails, semantic cache, WAF.

An AI-powered tool for summarizing YouTube videos by generating scene descriptions, translating them, and creating subtitled videos with text-to-speech narration

A comprehensive platform for managing, testing, and leveraging Ollama AI models with advanced features for customization, workflow automation, and collaborative development.

Route every prompt to the best LLM — for you specifically.

Perplexity style AI answer engine for AI PCs with CPU,GPU and NPU support

Open-source Legal AI workspace for evidence-grounded legal drafting, matter analysis and verifiable answers.

Scryptian - translating any text on the screen via Ctrl + Alt. Windows OS

A terminal coding agent, and a Python SDK for embedding on-device models in your own apps.

Lightweight replication study of DeepSeek-R1-Zero. Interesting findings include "No Aha Moment", "Longer CoT ≠ Accuracy", and "Language Mixing in Instruct Models".

Practical guide and toolkit for physicists and mathematicians using Claude Code — built from months on a real research project

CLI tool for bundling project files as LLM context.

A practical LLM learning path from clear prompting to tool use, IDE collaboration, MCP, Skills, and harness-driven agent workflows.