Search Results for "compact"
Sort By:
56 projects for "compact" with 2 filters applied:
-
Auth0 B2B Essentials: SSO, MFA, and RBAC Built InAuth0's B2B Essentials plan gives you everything you need to ship secure multi-tenant apps. Unlimited orgs, enterprise SSO, RBAC, audit log streaming, and higher auth and API limits included. Add on M2M tokens, enterprise MFA, or additional SSO connections as you scale.
-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
1
Humanizer Skill
Claude Code skill that removes signs of AI-generated writing from text
...It provides a suite of algorithms that convert timestamps, identifiers, file sizes, code tokens, and structured data into phrases that resemble typical human phrasing rather than compact machine output. For example, date and time values can be expressed as relative terms (“two hours ago”), and file sizes can be shown in intuitive units instead of raw bytes. It also includes functions for transforming camelCase, snake_case, or PascalCase identifiers into spaced and capitalized representations suitable for user interfaces, reports, or documentation. ... -
2
Sunfish
Sunfish: a Python Chess Engine in 111 lines of code
sunfish is a minimalist yet surprisingly strong chess engine written in Python, designed to demonstrate how powerful algorithms can be implemented in a highly compact codebase. Despite being only around a hundred lines of core logic, the engine achieves competitive performance, reaching ratings above 2000 on online platforms. It implements classic chess engine techniques such as alpha-beta pruning and efficient board representation while maintaining readability and simplicity. The project is often used as an educational tool for understanding game AI, search algorithms, and evaluation functions without the complexity of larger engines. ... -
3
GLM-4.5
GLM-4.5: Open-source LLM for intelligent agents by Z.ai
GLM-4.5 is a cutting-edge open-source large language model designed by Z.ai for intelligent agent applications. The flagship GLM-4.5 model has 355 billion total parameters with 32 billion active parameters, while the compact GLM-4.5-Air version offers 106 billion total parameters and 12 billion active parameters. Both models unify reasoning, coding, and intelligent agent capabilities, providing two modes: a thinking mode for complex reasoning and tool usage, and a non-thinking mode for immediate responses. They are released under the MIT license, allowing commercial use and secondary development. ... -
4
1D Visual Tokenization and Generation
This repo contains the code for 1D tokenizer and generator
The 1D Visual Tokenization and Generation project from ByteDance introduces a novel “one-dimensional” tokenizer designed for images: instead of representing images with large grids of 2D tokens (as in many prior generative/image-modeling systems), it compresses images into as few as 32 discrete tokens (or more, optionally) — thereby achieving a very compact, efficient representation that drastically speeds up generation and reconstruction while retaining strong fidelity. This compact representation makes sampling and generation many times faster compared to previous tokenization methods (claims of ~410× speedups relative to heavyweight models) while still producing competitive image quality. ... -
Stop Cyber Threats with VM-Series Next-Gen Firewall on AzureGain integrated visibility across all traffic in a single pass. Deploy Palo Alto Networks VM-Series to determine application identity and content while automating security policy updates via rich APIs.
-
5
model2Vec
Fast State-of-the-Art Static Embeddings
model2vec is an innovative embedding framework that converts large sentence transformer models into compact, high-speed static embedding models while preserving much of their semantic performance. The project focuses on dramatically reducing the computational cost of generating embeddings, achieving significant improvements in speed and model size without requiring large datasets for retraining. By using a distillation-based approach, it can produce lightweight models that run efficiently on CPUs, making it suitable for edge applications and large-scale processing pipelines. ... -
6
Open Deep Research
An AI-powered research assistant that performs iterative research
...Its core goal is to provide the simplest possible implementation of a deep research workflow so developers can study and extend agent behavior without dealing with large, opaque codebases. The system exposes parameters such as breadth and depth to control how widely and how deeply the agent explores information sources. It is intentionally kept compact, with a codebase under roughly 500 lines, making it highly approachable for experimentation and learning. The architecture demonstrates how modern agent pipelines can continuously gather evidence, extract learnings, and adjust research direction over time. -
7
Step3-VL-10B
Multimodal model achieving SOTA performance
Step3-VL-10B is an open-source multimodal foundation model developed by StepFun AI that pushes the boundaries of what compact models can achieve by combining visual and language understanding in a single architecture. Despite having only about 10 billion parameters, it delivers performance that rivals or even surpasses much larger models (10×–20× larger) on a wide range of multimodal benchmarks covering reasoning, perception, and complex tasks, positioning it as one of the most powerful models in its class. ... -
8
Supertonic
Lightning-fast, on-device TTS, running natively via ONNX
...It focuses on running entirely locally, eliminating the need for cloud APIs and providing low latency and strong privacy guarantees, even on constrained devices like Raspberry Pi boards and e-readers. The core model is highly compact at around 66 million parameters, yet benchmarks show it can generate speech up to 167× faster than real time on modern consumer hardware and significantly outpace popular cloud TTS APIs in throughput and real-time factor. Supertonic is designed to handle real-world text gracefully, including numbers, dates, currency symbols, abbreviations, and technical units, without requiring heavy pre-processing or custom text normalization. ... -
9
MOSS-TTS-Nano
MOSS-TTS-Nano is an open-source multilingual tiny speech generation
MOSS-TTS-Nano is a lightweight text-to-speech model designed for real-time voice generation in resource-constrained environments. It is part of the broader MOSS-TTS family and focuses on delivering high-quality speech synthesis with a compact architecture. The model operates efficiently on CPU-only systems, enabling deployment without specialized hardware. It supports multilingual voice cloning and produces high-fidelity audio with low latency. The system uses an autoregressive audio tokenization pipeline to generate natural-sounding speech. It is suitable for local applications, web services, and embedded systems. ... -
Atera - an All-in-one platform for IT managementYour IT essentials, integrated & elevated. Take your IT management from automated to autonomous, download Atera's agent to start your free trial!
-
10
Z-Image
Image generation model with single-stream diffusion transformer
...The project includes several variants: Z-Image-Turbo, a distilled version optimized for speed and low resource consumption; Z-Image-Base, the full-capacity foundation model; and Z-Image-Edit, fine-tuned for image editing tasks. Despite its compact size, Z-Image produces outputs that closely rival those from much larger models — including strong rendering of bilingual (English and Chinese) text inside images, accurate prompt adherence, and good layout and composition. -
11
GLM-OCR
Accurate × Fast × Comprehensive
...Designed to handle text recognition, table parsing, formula extraction, and general information retrieval from documents containing mixed content, GLM-OCR excels across major benchmarks while remaining highly efficient with a relatively compact parameter size (~0.9B), enabling deployment in high-concurrency services and edge environments. The model’s multimodal capabilities allow it to reason across image and text content holistically, capturing structured and unstructured information from pages that include dense tables, seals, code snippets, and varied document graphics. ... -
12
VibeThinker
Diversity-driven optimization and large-model reasoning ability
VibeThinker is a compact but high-capability open-source language model released by WeiboAI (Sina AI Lab). It contains about 1.5 billion parameters, far smaller than many “frontier” models, yet it is explicitly optimized for reasoning, mathematics, and code generation tasks rather than general open-domain chat. The innovation lies in its training methodology: the team uses what they call the Spectrum-to-Signal Principle (SSP), where a first stage emphasizes diversity of reasoning paths (the “spectrum” phase) and a second stage uses reinforcement techniques (the “signal” phase) to refine toward correctness and strong reasoning. ... -
13
SkillOpt
Text-space optimizer that trains reusable natural-language skills
SkillOpt is a Microsoft research project for improving frozen LLM agents by optimizing reusable natural-language skill documents. Instead of changing model weights, it treats a compact skill file as the trainable state of the agent. The system learns from agent rollouts, reflection, bounded edits, and validation gates to produce better instructions over time. Its output is a deployable best_skill.md artifact that can be reused across agent tasks. The project is focused on making agents more effective through text-space optimization rather than traditional fine-tuning. ... -
14
mini SWE-agent
The 100 line AI agent that solves GitHub issues
mini SWE-agent is a lightweight, minimalist AI-powered software engineering agent designed to autonomously solve GitHub issues and assist developers directly from the command line using large language models. Unlike more complex frameworks, it emphasizes simplicity and efficiency, consisting of roughly 100 lines of code while still achieving strong performance on benchmarks such as SWE-bench Verified, where it demonstrates competitive problem-solving capabilities. The agent operates by... -
15
dots.ocr
Multilingual Document Layout Parsing in a Single Vision-Language Model
...The model is designed to recognize virtually any human script, making it highly effective for global and low-resource language scenarios. It achieves state-of-the-art performance on document parsing benchmarks while maintaining a relatively compact model size, demonstrating efficiency without sacrificing accuracy. Beyond standard OCR tasks, it extends its capabilities to parse complex visual elements such as charts, diagrams, and web interfaces, converting them into structured outputs like SVG code. -
16
LongCat-Image
Foundation model for image generation
...Rather than relying on massive parameter counts typical of many cutting-edge models, LongCat-Image achieves strong photorealism, stable structure, and accurate bilingual (Chinese and English) text rendering with a more compact ~6-billion parameter architecture, making it competitive with much larger alternatives despite its relatively lean design. The model excels at both text-to-image generation and instruction-guided image editing, offering users versatile capabilities for creative and practical tasks—whether generating art, mockups, or adjusting existing visuals with fine control. -
17
Karpathy Skills
A single CLAUDE.md file to improve Claude Code behavior
Karpathy Skills is a compact guidance project built around a single CLAUDE.md file for improving AI coding agent behavior. It translates observations about common LLM coding failures into practical working rules for Claude Code and compatible workflows. The project focuses on reducing wrong assumptions, hidden confusion, overengineered solutions, and unnecessary edits outside the requested scope. -
18
Nano-vLLM
A lightweight vLLM implementation built from scratch
...The project recreates the core functionality of vLLM in a simplified architecture written in approximately a thousand lines of Python, making it easier for developers and researchers to understand how modern LLM inference systems work. Despite its compact design, nano-vllm incorporates advanced optimization techniques such as prefix caching, tensor parallelism, and CUDA graph execution to achieve high performance during model inference. The engine is intended primarily for educational use, experimentation, and lightweight deployments where a full production-grade inference stack may be unnecessary. ... -
19
Cactus Needle
26m function call model that runs on incredibly small devices
Needle is an experimental 26-million-parameter function-calling model designed to run on extremely small devices such as phones, watches, glasses, and low-power personal AI hardware. It is based on a Simple Attention Network architecture and was distilled from a much larger model to focus on fast, compact tool-use behavior. The project provides open weights, training details, dataset generation resources, and a playground for testing the model with custom tools. Needle is optimized for single-shot function calling rather than broad conversational ability, so its core use case is selecting the right tool and producing structured arguments. ... -
20
ReMe
Memory Management Kit for Agents
ReMe is a memory management kit for AI agents that gives them structured, persistent memory capabilities, enabling agents to extract, store, and reuse information across sessions, tasks, and interactions. It is designed to support long-running agent workflows where context matters and working memory alone isn’t enough, helping agents remember user preferences, task histories, and relevant past observations. The toolkit provides APIs to offload large, ephemeral outputs to external storage and... -
21
Monty
A minimal, secure Python interpreter written in Rust for use by AI
...It prioritizes guardrails like resource limits and restricted capabilities, which is especially useful for agentic workflows that need to execute small pieces of Python for data transforms, validation, or tool-like computations. Because it’s written in Rust, it’s positioned to deliver a compact, portable runtime that can be embedded into larger systems that need dependable isolation. -
22
TONL
TONL (Token-Optimized Notation Language)
TONL is a cutting-edge data platform built around a production-ready serialization format designed to be both compact and powerful, combining human readability with performance features that make it suitable for large-scale applications and AI workflows. It provides a serialization format that significantly reduces token usage compared with traditional JSON, which can result in lower costs and more efficient prompt size utilization in LLM-driven systems. -
23
HY-MT
Hunyuan Translation Model Version 1.5
HY-MT (Hunyuan Translation) is a high-quality multilingual machine translation model suite developed to support mutual translation across dozens of languages with strong performance even at smaller model scales. It ships with both an 1.8 B parameter model and a larger 7 B model, the latter optimized not only for direct translation but also for formatted and contextualized output, allowing better handling of terminology and mixed-language content. The project emphasizes both speed and... -
24
nanocode
Minimal Claude Code alternative. Single Python file, zero dependencies
nanocode is a minimalist coding agent implementation designed as a compact alternative to Claude Code, packaged in a single Python file with no external dependencies and totaling around 250 lines of code. It implements a full agentic loop where the model can reason, decide when to use tools, execute those tools, and iterate until producing a final answer, making it useful for simple AI-assisted coding workflows. -
25
Solon
Java enterprise application development framework
Solon is a full-scenario Java enterprise application framework that positions itself as a lean, high-performance alternative to heavy stacks. It advertises large concurrency gains, lower memory use, much faster startup, and dramatically smaller packages while remaining compatible from Java 8 through Java 24. The framework focuses on restrained APIs and an open ecosystem, with modules that cover web, data, cloud, and microservice patterns. Its messaging emphasizes “replaceable Spring”...
