Search Results for "token"
Sort By:
Showing 49 open source projects for "token"
View related business solutions-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
Secure File Transfer for Windows with Cerberus by RedwoodCerberus supports unlimited users and connections on a single IP, with built-in encryption, 2FA, and a browser-based web client — all deployable in under 15 minutes with a 25-day free trial.
-
1
Token-Oriented Object Notation
Token-Oriented Object Notation (TOON)
Token-Oriented Object Notation is an open specification and toolkit for a data serialization format called Token-Oriented Object Notation (TOON), designed specifically to optimize how structured data is passed to large language models. The format aims to reduce token overhead compared with traditional formats like JSON while remaining human-readable and structurally expressive. -
2
rtk
CLI proxy that reduces LLM token consumption
rtk is an open-source command-line proxy designed to optimize interactions between AI coding agents and the terminal by reducing unnecessary token consumption. When AI assistants execute shell commands during software development tasks, the resulting terminal output often contains large amounts of repetitive or irrelevant information that can overwhelm the model’s context window. RTK intercepts these command outputs and compresses them into concise summaries before sending them to the language model. ... -
3
DeepSeek-V3
Powerful AI language model (MoE) optimized for efficiency/performance
DeepSeek-V3 is a robust Mixture-of-Experts (MoE) language model developed by DeepSeek, featuring a total of 671 billion parameters, with 37 billion activated per token. It employs Multi-head Latent Attention (MLA) and the DeepSeekMoE architecture to enhance computational efficiency. The model introduces an auxiliary-loss-free load balancing strategy and a multi-token prediction training objective to boost performance. Trained on 14.8 trillion diverse, high-quality tokens, DeepSeek-V3 underwent supervised fine-tuning and reinforcement learning to fully realize its capabilities. ... -
4
TokenCost
Easy token price estimates for 400+ LLMs. TokenOps
TokenCost is an open-source developer utility designed to estimate the cost of using large language model APIs by calculating token usage and translating it into real monetary values. The tool focuses on helping developers understand how much their prompts and generated completions cost when interacting with commercial AI models. It works by counting tokens in prompts and responses before or after sending requests and then applying pricing information associated with different models. ... -
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.
-
5
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. TONL isn’t just a format — it includes a rich API for querying, indexing, modifying, and streaming data, along with tools for schema validation and TypeScript code generation. The platform comes with a complete command-line interface that supports interactive dashboards and cross-platform usage in browsers and server environments, and its high test coverage gives developers confidence in stability. -
6
DeepSeek R1
Open-source, high-performance AI model with advanced reasoning
...DeepSeek R1 offers unrestricted access for both commercial and academic use. The model employs a Mixture of Experts (MoE) architecture, comprising 671 billion total parameters with 37 billion active parameters per token, and supports a context length of up to 128,000 tokens. DeepSeek-R1's training regimen uniquely integrates large-scale reinforcement learning (RL) without relying on supervised fine-tuning, enabling the model to develop advanced reasoning capabilities. This approach has resulted in performance comparable to leading models like OpenAI's o1, while maintaining cost-efficiency. ... -
7
webclaw
Fast, local-first web content extraction for LLMs
...It is built in Rust and operates without a headless browser, using advanced techniques such as TLS fingerprinting to bypass common scraping barriers and mimic real browser behavior. The tool addresses a major inefficiency in AI workflows by removing irrelevant elements like navigation menus, ads, and scripts, significantly reducing token usage when feeding data into language models. It supports multiple modes of operation, including CLI usage, REST API access, and an MCP server for direct integration with agent-based systems. Webclaw also provides advanced capabilities such as recursive crawling, structured JSON extraction, summarization, and content comparison, making it suitable for research and data pipelines. ... -
8
Lunary
The production toolkit for LLMs. Observability, prompt management
Lunary helps developers of LLM Chatbots develop and improve them. -
9
MiniOneRec
Minimal reproduction of OneRec
...The framework provides an end-to-end pipeline for building generative recommender systems, including semantic identifier construction, supervised fine-tuning, and reinforcement learning-based optimization. Semantic IDs are created using techniques such as quantized variational autoencoders to convert item features into token sequences that can be modeled by transformer architectures. Developers can train and evaluate recommendation models using different backbone language models while benefiting from the generative framework’s parameter efficiency and scalability. -
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
Claude Code Bridge
Real-time multi-AI collaboration: Claude, Codex & Gemini
...The system allows developers to coordinate interactions between models such as Claude, Codex, and Gemini so that they can work together on programming tasks. By maintaining persistent shared context between these models, the tool reduces redundant prompts and minimizes token usage while allowing each AI system to contribute specialized capabilities. The architecture functions as a unified launcher that manages communication between multiple AI providers and coordinates their responses within the same development session. Developers can run the tool in terminal environments and integrate it with terminal multiplexers such as tmux or advanced terminal emulators. -
11
Transformer Explainer
Learn How LLM Transformer Models Work with Interactive Visualization
...Through visual diagrams and interactive interfaces, the tool reveals how tokens are processed through layers such as embeddings, attention mechanisms, and feed-forward networks. Users can observe how attention weights change as the model predicts the next token, offering insight into how transformer architectures capture relationships between words. The design of the platform emphasizes educational accessibility, allowing students, researchers, and developers to explore complex machine learning concepts without requiring specialized hardware or installations. -
12
MoBA
MoBA: Mixture of Block Attention for Long-Context LLMs
MoBA, short for Mixture of Block Attention, is an open-source research implementation of a novel attention mechanism designed to improve the efficiency of large language models processing extremely long contexts. The architecture adapts ideas from Mixture-of-Experts networks and applies them directly to the attention mechanism of transformer models. Instead of forcing each token to attend to every other token in the sequence, MoBA divides the context into blocks and dynamically routes queries to only the most relevant segments of information. This routing strategy reduces the computational cost associated with traditional attention while preserving performance on reasoning and long-context tasks. The approach allows language models to scale to significantly longer input contexts without the quadratic computational cost normally associated with transformer attention mechanisms. -
13
Kaleidoscope-SDK
User toolkit for analyzing and interfacing with Large Language Models
...Users must authenticate using their Vector Institute cluster credentials. This can be done interactively instantiating a client object. This will generate an authentication token that will be used for all subsequent requests. The token will expire after 30 days, at which point the user will be prompted to re-authenticate. -
14
OpenAI Forward
An efficient forwarding service designed for LLMs
OpenAI Forward is an open-source forwarding and reverse proxy service for large language model APIs, designed to sit between client applications and model providers. Its main purpose is to make model access more manageable and efficient by adding operational controls such as request rate limiting, token rate limiting, caching, logging, routing, and key management around existing LLM endpoints. The project can proxy both local and cloud-hosted language model services, which makes it useful for teams that want a single control layer regardless of whether they are using something like LocalAI or a hosted provider compatible with OpenAI-style APIs. ... -
15
dLLM
dLLM: Simple Diffusion Language Modeling
dLLM is an open-source framework designed to simplify the development, training, and evaluation of diffusion-based large language models. Unlike traditional autoregressive models that generate text sequentially token by token, diffusion language models generate text through an iterative denoising process that refines masked tokens over multiple steps. This approach allows models to reason over the entire sequence simultaneously and potentially produce more coherent outputs with bidirectional context. The project provides an integrated pipeline that standardizes how diffusion language models are trained, evaluated, and deployed, helping researchers reproduce experiments and compare results more easily. ... -
16
DevDocs by CyberAGI
Completely free, private, UI based Tech Documentation MCP server
...Instead of sending entire documents to a language model, DevDocs organizes documentation into sections so that only the most relevant portions are retrieved during a query. This approach reduces token usage and improves the accuracy of responses generated by AI coding assistants. The platform is designed to integrate easily with modern developer tools and AI environments such as Cursor, Cline, and Claude-based workflows. It includes a user interface that allows developers to browse documentation repositories and connect them to AI systems while keeping the data private. -
17
Tongyi DeepResearch
Tongyi Deep Research, the Leading Open-source Deep Research Agent
...It’s built to act like a research agent: synthesizing, reasoning, retrieving information via the web and documents, and backing its outputs with evidence. The model is about 30.5 billion parameters in size, though at any given token only ~3.3B parameters are active. It uses a mix of synthetic data generation, fine-tuning and reinforcement learning; supports benchmarks like web search, document understanding, question answering, “agentic” tasks; provides inference tools, evaluation scripts, and “web agent” style interfaces. The aim is to enable more autonomous, agentic models that can perform sustained knowledge gathering, reasoning, and synthesis across multiple modalities (web, files, etc.). -
18
MiniMax-01
Large-language-model & vision-language-model based on Linear Attention
...MiniMax-Text-01 uses a hybrid attention architecture that blends Lightning Attention, standard softmax attention, and Mixture-of-Experts (MoE) routing to achieve both high throughput and long-context reasoning. It has 456 billion total parameters with 45.9 billion activated per token and is trained with advanced parallel strategies such as LASP+, varlen ring attention, and Expert Tensor Parallelism, enabling a training context of 1 million tokens and up to 4 million tokens at inference. MiniMax-VL-01 extends this core by adding a 303M-parameter Vision Transformer and a two-layer MLP projector in a ViT–MLP–LLM framework, allowing the model to process images at dynamic resolutions up to 2016×2016. -
19
GLM-4.6
Agentic, Reasoning, and Coding (ARC) foundation models
GLM-4.6 is the latest iteration of Zhipu AI’s foundation model, delivering significant advancements over GLM-4.5. It introduces an extended 200K token context window, enabling more sophisticated long-context reasoning and agentic workflows. The model achieves superior coding performance, excelling in benchmarks and practical coding assistants such as Claude Code, Cline, Roo Code, and Kilo Code. Its reasoning capabilities have been strengthened, including improved tool usage during inference and more effective integration within agent frameworks. ... -
20
MiniMax-M1
Open-weight, large-scale hybrid-attention reasoning model
...Architecturally, it combines Mixture-of-Experts layers with lightning attention, enabling the model to support a native context length of 1 million tokens while using far fewer FLOPs than comparable reasoning models for very long generations. The team emphasizes efficient scaling of test-time compute: at 100K-token generation lengths, M1 reportedly uses only about 25 percent of the FLOPs of some competing models, making extended “think step” traces more feasible. M1 is further trained with large-scale reinforcement learning over diverse tasks. -
21
Qwen3
Qwen3 is the large language model series developed by Qwen team
Qwen3 is a cutting-edge large language model (LLM) series developed by the Qwen team at Alibaba Cloud. The latest updated version, Qwen3-235B-A22B-Instruct-2507, features significant improvements in instruction-following, reasoning, knowledge coverage, and long-context understanding up to 256K tokens. It delivers higher quality and more helpful text generation across multiple languages and domains, including mathematics, coding, science, and tool usage. Various quantized versions,... -
22
uqlm
Uncertainty Quantification for Language Models, is a Python package
...The library includes both black-box and white-box approaches to uncertainty estimation. Black-box methods evaluate model outputs through multiple generations or comparative analysis, while white-box methods rely on token probabilities produced during inference. UQLM also supports ensemble strategies and model-as-judge approaches for evaluating responses. By combining multiple uncertainty metrics, the system provides more reliable indicators of when language model outputs may be unreliable. -
23
GPUStack
Performance-optimized AI inference on your GPUs
GPUStack is an open-source GPU cluster management platform designed to simplify the deployment and operation of artificial intelligence models across heterogeneous hardware environments. The system aggregates GPU resources from multiple machines into a unified cluster so developers and administrators can run large language models and other AI workloads efficiently across distributed infrastructure. Instead of requiring complex orchestration systems such as Kubernetes, GPUStack provides a... -
24
LLM Telegram Bot
A Telegram bot for Large Language Models
...The system supports multiple modes or personas, enabling users to switch between different conversational styles or use cases. It also allows fine-tuning of generation parameters such as temperature and token limits, giving users control over response behavior. The architecture is modular, making it easy to extend or adapt for different workflows or integrations. -
25
FastDeploy
High-performance Inference and Deployment Toolkit for LLMs and VLMs
...The platform enables developers to deploy trained models quickly using optimized inference pipelines that support GPUs, specialized AI accelerators, and other hardware architectures. FastDeploy includes advanced acceleration technologies such as speculative decoding, multi-token prediction, and efficient KV cache management to improve throughput and latency during inference. It also offers compatibility with OpenAI-style APIs and vLLM-like interfaces, allowing developers to integrate deployed models easily into existing applications and services.
