Projects sharing features with LLMLingua

ClawWork is a suite of tools designed to monitor agent finances, provide isolated execution environments, simulate economic behaviors, and benchmark performance. It functions as an autonomous agent sandbox where AI agents can run code and generate professional business deliverables. The project focuses on the financial sustainability of AI assistants through an economic simulation environment. This includes tools for tracking token expenditures and income generation, as well as simulations that analyze the trade-offs between immediate earnings and long-term skill acquisition. The system incl

PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and execution of complex workflows. It functions as a multi-agent orchestration framework, a workflow builder, and a Model Context Protocol server, while also providing retrieval-augmented generation through vector knowledge bases. Agents can interact via CLI, web, or standardized protocols with sandboxed code execution. The platform distinguishes itself with a rich set of agent communication protocols, including A2A, REST, WebSocket, voice and telephony integration, and MCP, allo

This project is a comprehensive framework for the orchestration, evaluation, and context management of large language model agents. It provides a set of architectural patterns and standards for designing agent interactions, integrating external tools, and establishing memory architectures to persist knowledge across sessions. The system focuses on optimizing the limited memory of language models through token-aware context compression and filesystem-based context offloading. It incorporates secure execution environments using sandboxed virtual machines and isolated containers to safely run ba

Intel XPU LLM Acceleration Library is a toolkit designed to accelerate large language model inference and finetuning on Intel CPUs, GPUs, and NPUs. It provides a distributed inference engine for scaling models across multiple accelerators, a multimodal model runtime for vision and speech tasks, and a low-bit model quantization tool for converting weights into INT4, FP8, and GGUF formats. The project features a parameter-efficient finetuning framework that enables model adaptation using QLoRA and DPO on Intel hardware. It distinguishes itself by providing specialized optimizations for Intel XP

AgentOps is an observability platform and developer toolkit for monitoring the execution, performance, and reliability of autonomous agents powered by large language models. It serves as a system for tracking AI agent behavior, debugging complex workflows, and benchmarking model performance. The platform is distinguished by its ability to visualize multi-agent workflows through execution path graphing and session replays. It provides specific tools for calculating financial spend across various language model providers and supports a self-hosted observability stack for users who require full

OmniRoute is a unified LLM API gateway that connects multiple AI providers to a single endpoint. Its primary purpose is to simplify the integration of various AI models into tools and agents by translating different provider formats into a standardized API. The project distinguishes itself through a multi-strategy request routing system that optimizes for cost, speed, and availability, including automatic model fallbacks and a circuit-breaker resilience model to isolate provider failures. It employs a local-first security posture, using AES-256-GCM encryption to store API keys and conversatio

AidLearning-Framework is an integrated development platform for building and deploying AI applications on ARM-based devices. It combines Android and Linux operating systems running simultaneously on a single device, providing a unified runtime environment for cross-system AI development. The platform includes hardware acceleration across CPU, GPU, and NPU, with a unified API that automatically selects the optimal compute backend for inference. The framework distinguishes itself by enabling Python-based AI projects to be packaged directly into Android APK files for installation on mobile devic

LMOps is a research-driven operations framework for optimizing the deployment, fine-tuning, and performance of large language models. It provides a specialized toolkit for foundation model adaptation, inference acceleration, prompt optimization, and context orchestration. The framework distinguishes itself through an inference accelerator that reduces token generation latency by verifying and copying overlapping text spans from reference documents. It also features a prompt engineering optimizer that employs reinforcement learning, beam search, and non-natural language markers to automaticall

AITemplate is an ahead-of-time deep learning compiler that translates PyTorch neural networks into standalone C++ source code. It functions as a PyTorch to C++ compiler and a GPU kernel fusion engine, producing self-contained executable binaries that run inference without requiring a Python interpreter or deep learning framework runtime. The project generates optimized CUDA and HIP C++ code specifically for NVIDIA TensorCores and AMD MatrixCores. It focuses on maximizing throughput for half-precision floating-point operations through a system that combines multiple neural network operators in

models.dev is a directory and intelligence system for large language models that provides a standardized catalog of technical specifications, provider mappings, and pricing data. It serves as a central index for model metadata, including context windows, output limits, and release dates. The project functions as a capability index and pricing comparison tool, allowing for the analysis of token costs across different hosting providers. It maps generic model names to the specific API identifiers required by various third-party platforms and tracks support for functional features such as tool ca

GenericAgent is an LLM agent framework and autonomous system controller designed to manage local systems, web browsers, and hardware interfaces through action and observation loops. It functions as a tool orchestrator that routes model calls to local executors, enabling the automation of complex tasks on a host machine. The project is distinguished by its self-evolving AI agent capabilities, which convert successful execution paths into reusable procedural scripts and skill trees to reduce future reasoning overhead. It employs a context optimization engine that utilizes layered memory hierarc

GPTCache is a semantic caching layer and response optimizer for large language models. It functions as pluggable middleware for orchestration frameworks, utilizing vector database caching to store and retrieve model responses based on the semantic similarity of prompts rather than exact text matches. The system uses embeddings to determine cache hits by comparing the distance between new queries and stored vectors. It employs a hybrid storage model that persists original prompts in relational databases while maintaining high-dimensional embeddings in vector stores. The project covers a broad

This project is a deep learning framework designed for constructing, training, and deploying neural networks across diverse hardware environments. It functions as a high-performance tensor computation library that provides both imperative and symbolic programming interfaces, allowing developers to balance flexible, step-by-step model building with the efficiency of compiled computation graphs. The framework distinguishes itself through a hybrid execution engine that integrates declarative graph compilation with imperative runtime logic. It supports scalable, distributed training across multip

PaddleDetection is an object detection framework designed for the end-to-end development, training, and deployment of computer vision models. It provides a comprehensive library of modular neural network architectures and pipelines that support object detection, instance segmentation, and multi-object tracking tasks. The project distinguishes itself through a configuration-driven approach that decouples model components like backbones and heads, allowing for the flexible assembly of custom vision workflows. It incorporates advanced techniques such as anchor-free detection logic, joint detecti

This project is a command-line utility designed to monitor and analyze token consumption and financial expenditure for AI coding assistants. By parsing local session logs directly on the user's machine, it provides a privacy-focused way to track development activity without transmitting sensitive data to external servers. The tool distinguishes itself through its ability to aggregate disparate log formats from multiple coding assistants into a unified, schema-agnostic representation. It features a decoupled pricing engine that allows users to apply custom model-specific cost multipliers, over

Deep-Live-Cam is a generative video transformation tool designed for real-time facial manipulation and cinematic enhancement. It functions as a local-first AI runtime, performing all media processing directly on the user's hardware to ensure complete data privacy without external network dependencies. By utilizing a high-performance processing pipeline, the application enables live face swapping and interactive video modifications during active streaming sessions or on pre-recorded media. The system distinguishes itself through a hardware-abstraction execution layer that dynamically routes co

MindSpore is a deep learning framework designed for building and training neural networks across cloud, edge, and mobile environments. It functions as a distributed training system and a hardware accelerated AI toolkit capable of executing workloads on CPUs, GPUs, and specialized AI processors. The project includes an automatic differentiation engine that computes gradients through source transformation and static compilation. It enables distributed model training by splitting workloads across hardware using data and model parallelism. The framework covers cross-platform AI deployment and mo

Sana is a framework for high-resolution image and video synthesis based on a linear diffusion transformer. It provides a toolkit for the training, fine-tuning, and execution of text-to-image and text-to-video models, as well as a video generative world model capable of simulating physical environments with precise spatial control. The project is distinguished by its use of linear complexity layers to handle high resolutions and its support for long-form, minute-length video generation in real time. It implements a two-stage inference paradigm that separates structural generation from visual t

ComfyUI-SeedVR2_VideoUpscaler is an AI video upscaling tool that uses diffusion models to increase the resolution of videos and images while maintaining visual consistency across frames. The project implements distributed video rendering by splitting datasets into chunks for parallel processing across multiple GPUs. It utilizes model compilation and specialized attention backends to reduce inference latency and increase throughput. Additional capabilities include video color correction using wavelet and LAB matching methods to preserve color fidelity. Hardware memory is managed through block

TaskWeaver is an LLM agent framework that interprets natural language requests and executes them as Python code, SQL queries, or shell commands. It functions as a conversational code interpreter that maintains stateful data structures across turns, generating executable code from user prompts within a session-based environment. The system is designed as a self-hosted AI agent platform that can be deployed in Docker, managing sessions and providing a web UI for data analytics and automation tasks. The framework distinguishes itself through a role-based multi-agent architecture that divides the

LARK is a development toolkit for training, fine-tuning, and deploying large language models and multimodal models based on PaddlePaddle. It functions as a comprehensive framework that includes an LLM training orchestrator, an inference server, and a multimodal model framework for processing text, image, and video inputs. The project features a retrieval-augmented generation system for building conversational applications that integrate web search and private knowledge bases. It provides specific capabilities for multimodal reasoning and complex logic, enabling the extraction of structured da

Spark NLP is a toolkit for scalable text analysis and machine learning built on the Apache Spark distributed computing framework. It provides a multimodal machine learning framework and a distributed pipeline system for sequencing annotators to process large-scale linguistic data. The library includes a transformer text processor for generating contextual vector embeddings and a dedicated inference engine for managing large language models. The project distinguishes itself through its ability to process heterogeneous data types, including text, audio, and images, within a unified vision-langu

AutoGluon is an automated machine learning framework and multimodal library designed to automate the end-to-end pipeline from data preprocessing to high-accuracy model training and validation. It functions as an automated model trainer for tabular, image, text, and time series data, as well as a tool for time series forecasting and foundation model finetuning. The project is distinguished by its ability to jointly process and fuse different data types, allowing for the construction of multimodal neural networks that integrate images, text, and structured tables. It supports zero-shot inferenc

Kreuzberg is a document extraction engine that converts PDFs, Office files, images, and over 90 other formats into clean, structured text and metadata. It is built around a compiled Rust core that can be used as a native library, a command-line tool, a REST API server, or a WebAssembly module for browser-based processing. The system is designed to run entirely on self-hosted infrastructure, with no data leaving the user's environment. What distinguishes Kreuzberg is its breadth of integration surfaces and its pipeline architecture. It exposes extraction capabilities through native bindings fo

InstantID is a diffusion-based identity preservation framework designed for zero-shot image generation. It allows for the synthesis of images featuring a specific person's facial identity using a single reference photo without requiring additional model training or fine-tuning. The project distinguishes itself through the use of consistency model distillation to accelerate inference, reducing the number of steps needed to produce high-quality results. It combines identity-preserving feature extraction with multi-modal prompt integration to merge visual embeddings from a reference image with t

Koog is an LLM agent framework used to build autonomous entities that execute tool-based workflows. It utilizes a graph-based workflow engine to define agent behaviors and decision paths as a directed graph of nodes and edges. The framework distinguishes itself through a model provider orchestrator that enables dynamic switching, load balancing, and automatic fallbacks between different AI backends. It implements the Model Context Protocol to connect agents to remote tool servers and features a RAG memory system using vector embeddings to maintain long-term conversation context. The project