Search Results for "less"
Sort By:
Showing 84 open source projects for "less"
View related business solutions-
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
Our Free Plans just got better! | Auth0You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
-
1
whisper.cpp
Port of OpenAI's Whisper model in C/C++
...The command downloads the base.en model converted to custom ggml format and runs the inference on all .wav samples in the folder samples. whisper.cpp supports integer quantization of the Whisper ggml models. Quantized models require less memory and disk space and depending on the hardware can be processed more efficiently. -
2
Octelium
A next-gen FOSS self-hosted unified zero trust secure access platform
...One of its key strengths is identity-based, application-layer (L7) aware control, meaning access decisions are made per request, with context and policy rather than simple network-level allow/block rules. It supports both client-based (e.g., WireGuard/QUIC tunnels) and client-less access models, which makes it flexible for both human users and automated workloads. The project also highlights self-hosted, no hidden “server-side” locked components, giving organizations greater ownership and control over access, rather than relying on proprietary SaaS. -
3
Hunyuan3D-1
A Unified Framework for Text-to-3D and Image-to-3D Generation
Hunyuan3D-1 is an earlier version in the same 3D generation line (the unified framework for text-to-3D and image-to-3D tasks) by Tencent Hunyuan. It provides a framework combining shape generation and texture synthesis, enabling users to create 3D assets from images or text conditions. While less advanced than version 2.1, it laid the foundations for the later PBR, higher resolution, and open-source enhancements. (Note: less detailed public documentation was found for Hunyuan3D-1 compared to 2.1.). Community and ecosystem support (e.g. usage via Blender addon for geometry/texture). Integration into user-friendly tools/platforms. -
4
Instructor
Structured outputs for llms
...Instructor is trusted by engineers from platforms like Langflow, underscoring its reliability and effectiveness in managing structured outputs powered by LLMs. Instructor is powered by Pydantic, which is powered by type hints. Schema validation and prompting are controlled by type annotations; less to learn, and less code to write, and it integrates with your IDE. -
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
5
Tokenizers
Fast State-of-the-Art Tokenizers optimized for Research and Production
...These tokenizers are also used in Transformers. Train new vocabularies and tokenize, using today’s most used tokenizers. Extremely fast (both training and tokenization), thanks to the Rust implementation. Takes less than 20 seconds to tokenize a GB of text on a server’s CPU. Easy to use, but also extremely versatile. Designed for both research and production. Full alignment tracking. Even with destructive normalization, it’s always possible to get the part of the original sentence that corresponds to any token. Does all the pre-processing: Truncation, Padding, add the special tokens your model needs. -
6
caveman
Why use many token when few token do trick
...The project often serves as a foundation for developers who want to build applications quickly without being constrained by heavy conventions or extensive configuration. It may include utilities for routing, state handling, or simple server logic, depending on its implementation scope. Caveman embraces a philosophy of “less is more,” encouraging developers to focus on core functionality rather than framework overhead. Its design makes it particularly useful for experimentation, small tools, or proof-of-concept applications. -
7
Paperless-ngx
A community-supported supercharged version of paperless
Paperless-ngx is a community-supported open-source document management system that transforms your physical documents into a searchable online archive so you can keep, well, less paper. -
8
DeepGEMM
Clean and efficient FP8 GEMM kernels with fine-grained scaling
DeepGEMM is a specialized CUDA library for efficient, high-performance general matrix multiplication (GEMM) operations, with particular focus on low-precision formats such as FP8 (and experimental support for BF16). The library is designed to work cleanly and simply, avoiding overly templated or heavily abstracted code, while still delivering performance that rivals expert-tuned libraries. It supports both standard and “grouped” GEMMs, which is useful for architectures like Mixture of... -
9
Claude Code Haha
Claude Code leaked source - locally runnable version
...While it retains the core functionality of analyzing and modifying codebases, the project introduces variations that highlight both the strengths and quirks of autonomous coding assistants. It serves as a sandbox for testing how agents interpret instructions, manage context, and execute development tasks in a less formal or more exploratory setting. The repository likely includes playful modifications, custom prompts, or unconventional workflows that reveal edge cases in agent behavior. Despite its informal tone, it still provides insight into how coding agents can be structured and extended. It is particularly useful for understanding limitations, failure modes, and creative applications of AI-driven development tools. -
Train ML Models With SQL You Already KnowBuild and deploy ML models using familiar SQL. Automate data prep with built-in Gemini. Query 1 TB and store 10 GB free monthly.
-
10
Memvid
Video-based AI memory library. Store millions of text chunks in MP4
Memvid encodes text chunks as QR codes within MP4 frames to build a portable “video memory” for AI systems. This innovative approach uses standard video containers and offers millisecond-level semantic search across large corpora with dramatically less storage than vector DBs. It's self-contained—no DB needed—and supports features like PDF indexing, chat integration, and cloud dashboards. -
11
DSharpPlus
A .NET Standard library for making bots using the Discord API
...If you want to use the latest features on Discord, you should use the nightlies Despite the nature of pre-release software, all changes to the library are held under a level of scrutiny; for this library, unstable does not mean bad quality, rather it means that the API can be subject to change without prior notice (to ease rapid iteration) and that consumers of the library should always remain on the latest version available (to immediately get the latest fixes and improvements). You will usually want to use this version. The latest stable release is always available on NuGet. Stable versions are released less often, but are guaranteed to not receive any breaking API changes without a major version bump. -
12
ChatLLM.cpp
Pure C++ implementation of several models for real-time chatting
chatllm.cpp is a pure C++ implementation designed for real-time chatting with Large Language Models (LLMs) on personal computers, supporting both CPU and GPU executions. It enables users to run various LLMs ranging from less than 1 billion to over 300 billion parameters, facilitating responsive and efficient conversational AI experiences without relying on external servers. -
13
Upscale-A-Video
Temporal-Consistent Diffusion Model for Real-World Video
...It upscales low-resolution videos while using text prompts to guide the enhancement process. The model is designed for real-world videos where compression artifacts, blur, aging, or generated-video defects can make ordinary upscaling less reliable. The repository includes inference code, example inputs, configuration structure, pretrained model instructions, and optional LLaVA-assisted prompt support. It includes example workflows for AIGC videos, old videos, movies, and animations. It also provides color correction options to help reduce visual mismatch between the input and enhanced output. -
14
Lightpanda Browser
Lightpanda: the headless browser designed for AI and automation
...The browser is implemented using the Zig programming language and integrates the V8 JavaScript engine to run modern web applications and scripts efficiently. Because it avoids graphical rendering and other heavy browser components, the system uses significantly less memory and launches almost instantly compared to conventional browsers such as Chrome. -
15
R-KV
Redundancy-aware KV Cache Compression for Reasoning Models
...R-KV introduces a method for compressing the KV cache during decoding, allowing models to maintain reasoning performance while reducing memory consumption and computational overhead. The approach focuses on identifying which attention heads and cache components are most important for maintaining reasoning quality, allowing less critical information to be compressed or discarded. This results in more efficient inference without significantly degrading model performance. -
16
TabFM
scikit-learn compatible tabular foundation model
...It supports both JAX and PyTorch backends and can automatically download pretrained TabFM v1.0.0 weights. The project is useful for practitioners who want strong tabular predictions with less manual feature engineering, tuning, and repeated model training. -
17
GSD Core
Meta-prompting, context engineering, spec-driven development system
...It supports installation across several AI coding runtimes and offers profiles for different levels of workflow surface area. The system is especially useful for developers who use AI agents heavily and need more discipline around planning, execution, and review. It acts less like a single app and more like an execution layer for shipping software with agents. -
18
CTranslate2
Fast inference engine for Transformer models
...The project implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU. The execution is significantly faster and requires less resources than general-purpose deep learning frameworks on supported models and tasks thanks to many advanced optimizations: layer fusion, padding removal, batch reordering, in-place operations, caching mechanism, etc. The model serialization and computation support weights with reduced precision: 16-bit floating points (FP16), 16-bit integers (INT16), and 8-bit integers (INT8). ... -
19
Gajae-Code
Gajae Code MVP
...It includes tmux-backed execution options for coordinating parallel workers when a task is large enough to benefit from them. Gajae-Code is useful for developers who want coding agents to behave less like single-prompt assistants and more like disciplined project collaborators. Its main value is giving AI coding work a clearer loop for interviews, plans, goals, execution checks, and evidence. -
20
RWKV Runner
A RWKV management and startup tool, full automation, only 8MB
...So it's combining the best of RNN and transformer - great performance, fast inference, fast training, saves VRAM, "infinite" ctxlen, and free text embedding. Moreover it's 100% attention-free. Default configs has enabled custom CUDA kernel acceleration, which is much faster and consumes much less VRAM. If you encounter possible compatibility issues, go to the Configs page and turn off Use Custom CUDA kernel to Accelerate. -
21
Kitten TTS
State-of-the-art TTS model under 25MB
KittenTTS is an open-source, ultra-lightweight, and high-quality text-to-speech model featuring just 15 million parameters and a binary size under 25 MB. It is designed for real-time CPU-based deployment across diverse platforms. Ultra-lightweight, model size less than 25MB. CPU-optimized, runs without GPU on any device. High-quality voices, several premium voice options available. Fast inference, optimized for real-time speech synthesis. -
22
LightGBM
Gradient boosting framework based on decision tree algorithms
...Compared to other boosting frameworks, LightGBM offers several advantages in terms of speed, efficiency and accuracy. Parallel experiments have shown that LightGBM can attain linear speed-up through multiple machines for training in specific settings, all while consuming less memory. LightGBM supports parallel and GPU learning, and can handle large-scale data. It’s become widely-used for ranking, classification and many other machine learning tasks. -
23
OpenAdapt
Open Source Generative Process Automation
OpenAdapt is the open source software adapter between Large Multimodal Models (LMMs) and traditional desktop and web Graphical User Interfaces (GUIs). OpenAdapt learns to automate your desktop and web workflows by observing your demonstrations. Spend less time on repetitive tasks and more on work that truly matters. Boost team productivity in HR operations. Automate candidate sourcing using LinkedIn Recruiter, LinkedIn Talent Solutions, GetProspect, Reply.io, outreach.io, Gmail/Outlook, and more. Streamline legal procedures and case management. Automate tasks like generating legal documents, managing contracts, tracking cases, and conducting legal research with LexisNexis, Westlaw, Adobe Acrobat, Microsoft Excel, and more. -
24
Cody
Type less, code more: Cody is an AI code assistant
Cody is an AI coding assistant that uses advanced search and codebase context to help you understand, write, and fix code faster. Generate code on demand using AI. Cody also unblocks you when you’re jumping into new projects or trying to understand legacy code. Run Cody's one-click prompts or create your own custom prompts to execute AI workflows. Cody generates single lines, or whole functions, in any programming language, configuration file, or documentation. Cody uses your code graph plus... -
25
R1-V
Witness the aha moment of VLM with less than $3
R1-V is an initiative aimed at enhancing the generalization capabilities of Vision-Language Models (VLMs) through Reinforcement Learning in Visual Reasoning (RLVR). The project focuses on building a comprehensive framework that emphasizes algorithm enhancement, efficiency optimization, and task diversity to achieve general vision-language intelligence and visual/GUI agents. The team's long-term goal is to contribute impactful open-source research in this domain.
