Search Results for "token" - Page 2
Sort By:
Showing 161 open source projects for "token"
View related business solutions-
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
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
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. -
2
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. -
3
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. -
4
DFlash
Block Diffusion for Ultra-Fast Speculative Decoding
...It acts as a “drafter” that proposes likely continuations which the main model then verifies, enabling significant throughput gains compared to traditional autoregressive decoding methods that generate token by token. This approach has been shown to deliver lossless acceleration on models like Qwen3-8B by combining block diffusion techniques with efficient batching, making it ideal for applications where latency and cost matter. The project includes support for multiple draft models, example integration code, and scripts to benchmark performance, and it is structured to work with popular model serving stacks like SGLang and the Hugging Face Transformers ecosystem. -
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.
-
5
Continuous Claude v3
Context management for Claude Code. Hooks maintain state via ledgers
...The project orchestrates many specialized agents and skills—109 skills and 32 agents—so that complex coding tasks can be broken down, analyzed, and executed collaboratively by different components. It also includes a layered code analysis pipeline to reduce token usage and maintain relevant context efficiently. This continuous learning environment enables workflows such as bug fixing, refactoring, planning, and exploratory investigation while minimizing the need to re-explain context manually. -
6
Gitingest
Create prompt-friendly codebase digests from any Git repository URL
...In addition to producing the code digest, Gitingest also calculates statistics about the extracted content such as repository structure, total size of the extract, and token count. Gitingest can be used as a command line utility or integrated directly into Python applications. -
7
AWS Agent Skills
AWS Skills for Agents
...Instead of streaming giant documentation sets or relying on episodic web search, this project compresses AWS best practices, usage patterns, edge cases, and real-world engineering guides into pre-structured skill definitions that are token-efficient and tailored for reasoning. The skills cover critical AWS services such as IAM, Lambda, DynamoDB, S3, API Gateway, EKS, and many more, letting agents offer actionable advice on infrastructure as code, debugging, security configurations, and architectural workflows. Skills are kept up to date with weekly documentation checks, ensuring they reflect current AWS patterns and service changes. -
8
Tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models
tiktoken is a high-performance, tokenizer library (based on byte-pair encoding, BPE) designed for use with OpenAI’s models. It handles encoding and decoding text to token IDs efficiently, with minimal overhead. Because tokenization is a fundamental step in preparing text for models, tiktoken is optimized for speed, memory, and correctness in model contexts (e.g. matching OpenAI’s internal tokenization). The repo supports multiple encodings (e.g. “cl100k_base”) and lets users switch encoding names to match different model contexts. ... -
9
Code-Mode
Plug-and-play library to enable agents to call MCP and UTCP tools
...The repository contains both TypeScript and Python libraries, plus a code-mode-mcp component for integrating with MCP and UTCP ecosystems. Benchmarks in the README highlight improvements in latency and token cost for scenarios involving multiple tools, showing that code execution often outperforms traditional JSON-based function calling. -
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
10
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.). -
11
MCP Text Editor
Provides line-oriented text file editing capabilities
The MCP Text Editor Server provides line-oriented text file editing capabilities through a standardized API, optimized for integration with Large Language Models (LLMs). It enables efficient partial file access, minimizing token usage while ensuring safe concurrent editing. -
12
InfiAgent
Build your own Cowork, AI Scientist and other SoTA Agents
...Designed as a “Multi-Level Agent” (MLA) system, it externalizes persistent state to the file system so that agents can operate over unlimited runtime without the need for token-intensive context compression, enabling workflows such as research paper drafting, experiments, coding, and document generation to run reliably. The framework uses a serial multi-agent hierarchy where specialized agents coordinate in tree-structured paths for clear task delegation and minimal tool conflicts, while batch file operations and persistent workspaces ensure reproducibility and traceability. ... -
13
WavTokenizer
SOTA discrete acoustic codec models with 40/75 tokens per second
WavTokenizer is a state-of-the-art discrete acoustic codec designed specifically for audio language modeling, capable of compressing 24 kHz audio into just 40 or 75 tokens per second while preserving high perceptual quality. It is built to represent speech, music, and general audio with extremely low bitrate, making it ideal as a front-end for large audio language models like GPT-4o and similar architectures. The model uses a single-quantizer design together with temporal compression to... -
14
Text Generation Inference
Large Language Model Text Generation Inference
Text Generation Inference is a high-performance inference server for text generation models, optimized for Hugging Face's Transformers. It is designed to serve large language models efficiently with optimizations for performance and scalability. -
15
DeepSeek-OCR 2
Visual Causal Flow
DeepSeek-OCR-2 is the second-generation optical character recognition system developed to improve document understanding by introducing a “visual causal flow” mechanism, enabling the encoder to reorder visual tokens in a way that better reflects semantic structure rather than strict raster scan order. It is designed to handle complex layouts and noisy documents by giving the model causal reasoning capabilities that mimic human visual scanning behavior, enhancing OCR performance on documents... -
16
SAM 3
Code for running inference and finetuning with SAM 3 model
SAM 3 (Segment Anything Model 3) is a unified foundation model for promptable segmentation in both images and videos, capable of detecting, segmenting, and tracking objects. It accepts both text prompts (open-vocabulary concepts like “red car” or “goalkeeper in white”) and visual prompts (points, boxes, masks) and returns high-quality masks, boxes, and scores for the requested concepts. Compared with SAM 2, SAM 3 introduces the ability to exhaustively segment all instances of an... -
17
WhisperSpeech
An Open Source text-to-speech system built by inverting Whisper
...The project aims to be for speech what Stable Diffusion is for images: powerful, hackable, and safe for commercial use, with code under Apache-2.0/MIT and models trained only on properly licensed data. Its architecture follows a token-based, multi-stage pipeline inspired by AudioLM and SPEAR-TTS: Whisper is used to produce semantic tokens, EnCodec compresses the waveform into acoustic tokens, and Vocos reconstructs high-fidelity audio from those tokens. The repository includes notebooks and scripts for inference, long-form synthesis, and finetuning, as well as pre-trained models and converted datasets hosted on Hugging Face. ... -
18
minted
minted is a LaTeX package that provides syntax highlighting
minted is a LaTeX package that enables advanced syntax highlighting of source code using the Pygments library. It supports customization via LaTeX and Python integration, allowing fine-grained control over code snippets in documents. -
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
LangGraph
Build resilient language agents as graphs
LangGraph is a library for building stateful, multi-actor applications with LLMs, used to create agent and multi-agent workflows. Compared to other LLM frameworks, it offers these core benefits: cycles, controllability, and persistence. LangGraph allows you to define flows that involve cycles, essential for most agentic architectures, differentiating it from DAG-based solutions. As a very low-level framework, it provides fine-grained control over both the flow and state of your application,... -
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
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. -
23
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. -
24
GPT Researcher
LLM based autonomous agent that does online comprehensive research
Say Hello to GPT Researcher, your AI agent for rapid insights and comprehensive research. GPT Researcher is the leading autonomous agent that takes care of everything from accurate source gathering to organization of research results. -
25
SGLang
SGLang is a fast serving framework for large language models
SGLang is a fast serving framework for large language models and vision language models. It makes your interaction with models faster and more controllable by co-designing the backend runtime and frontend language.
