Search Results for "token"
Sort By:
Showing 727 open source projects for "token"
View related business solutions-
$300 Free Credits to Build on Google CloudStart your next project with $300 in free Google Cloud credit. Spin up VMs, run containers, query petabytes in BigQuery, or build agents with Gemini Enterprise Agent Platform. Once your credits are used, keep building with 20+ always-free tier products including Compute Engine, Cloud Storage, GKE, and Cloud Run functions. No commitment required—just sign up and start building.
-
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.
-
1
claude-token-efficient
One CLAUDE.md file. Keeps Claude responses terse
claude-token-efficient is a lightweight configuration-based optimization project designed to reduce the verbosity and token usage of Claude-powered coding workflows through a structured instruction file. Instead of modifying model architecture or APIs, it uses a drop-in CLAUDE.md file that constrains how the model responds, enforcing concise output and eliminating unnecessary phrasing patterns. -
2
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. -
3
Java JWT
Java implementation of JSON Web Token (JWT)
A Java implementation of JSON Web Token (JWT) - RFC 7519. This library requires Java 8 or higher. The last version that supported Java 7 was 3.11.0. The library implements JWT Verification and Signing using several algorithms. The Algorithm defines how a token is signed and verified. It can be instantiated with the raw value of the secret in the case of HMAC algorithms, or the key pairs or KeyProvider in the case of RSA and ECDSA algorithms. -
4
kubelogin
kubectl plugin for Kubernetes OpenID Connect authentication
...If the cached ID token has expired, kubelogin will refresh the token using the refresh token. If the refresh token has expired, kubelogin will perform re-authentication (you will have to login via browser again). -
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.
-
5
jwt-auth
JSON web token authentication for Laravel and Lumen
jwt-auth provides a simple means of authentication within Laravel using JSON Web Tokens (spec). There are several ways to create a token within the package. There are simple ways to do it, and more advanced methods if you want greater control. The most common way to create a token would be to authenticate the user via their login credentials, and if successful return a token corresponding to that user. You can also skip user authentication and just pass in a User object. ... -
6
Gin JWT Middleware
JWT Middleware for Gin framework
Gin JWT Middleware is a JWT authentication middleware for applications built with the Gin web framework in Go. It gives developers ready-to-use handlers for login, logout, token refresh, and protected routes. The middleware supports custom authentication logic, authorization checks, claims, token lookup rules, and response callbacks. It can work with tokens in headers or cookies and includes stronger refresh-token patterns for production use. It also supports Redis-backed refresh token storage, direct token generation, and multi-provider validation strategies. ... -
7
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. ... -
8
Jwt.Net
Jwt.Net, a JWT (JSON Web Token) implementation for .NET
This library supports generating and decoding JSON Web Tokens. By default JSON serialization is performed by JsonNetSerializer implemented using JSON. -
9
Lexik JWT Authentication Bundle
JWT authentication for your Symfony API
LexikJWTAuthenticationBundle is a Symfony bundle that provides JWT (JSON Web Token) authentication for RESTful APIs. It simplifies the process of generating and validating JWTs for secure user authentication. The bundle integrates seamlessly with Symfony’s security system, allowing developers to implement token-based authentication efficiently while maintaining flexibility in user management. -
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
next-firebase-auth
Simple Firebase authentication for all Next.js rendering strategies
Simple Firebase authentication for all Next.js rendering strategies. This package makes it simple to get the authenticated Firebase user and ID token during both client-side and server-side rendering (SSR). We treat the Firebase JS SDK as the source of truth for auth status. When the user signs in, we call an endpoint to generate a refresh token and store the user info, ID token, and refresh token in cookies. Future requests to SSR pages receive the user info and ID token from cookies, refreshing the ID token as needed. ... -
11
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. ... -
12
Aegis Authenticator
A free, secure and open source app for Android
...It supports importing accounts from QR codes, exporting encrypted backups for safe storage, and grouping or labeling tokens so managing dozens of accounts is simple. Aegis also offers options for custom token configuration, including changing issuer names, digits, and intervals, and includes a robust recovery mechanism in case a device is lost. It has a material design interface that makes navigation intuitive, and its open-source license ensures transparency. -
13
Logos
Create ridiculously fast Lexers
Logos is a lexer generator for Rust, designed to create fast and efficient lexers with minimal code. It leverages Rust's procedural macros to define token patterns, streamlining the process of lexical analysis. -
14
Backtrack Sampler
An easy-to-understand framework for LLM samplers
Backtrack Sampler is a framework designed for experimenting with custom sampling strategies for language models (LLMs), enabling the ability to rewind and revise generated tokens. It allows developers to create and test their own token generation strategies by providing a base structure for manipulating logits and probabilities, making it a flexible tool for those interested in fine-tuning the behavior of LLMs. -
15
Godo
DigitalOcean Go API client
...Some endpoints offer token based pagination. For example, to fetch all Registry Repositories. Each version of the client is tagged and the version is updated accordingly. -
16
Guardian
Elixir Authentication
Guardian is a token based authentication library for use with Elixir applications. Guardian remains a functional system. It integrates with Plug but can be used outside of it. If you're implementing a TCP/UDP protocol directly or want to utilize your authentication via channels in Phoenix, Guardian can work for you. The core currency of authentication in Guardian is the token. -
17
Tokscale
A CLI tool for tracking token usage from OpenCode, Claude Code
Tokscale is a CLI and terminal UI tool that tracks token usage and estimated cost across multiple AI coding assistants and development workflows. It treats tokens like a measurable resource, helping developers understand how much “AI energy” they are consuming over time and where it is being spent. The tool aggregates usage across supported platforms and presents it through interactive views that let users filter, sort, and explore trends without leaving the terminal. -
18
Alova.js
Workflow-Streamlined next-generation request tools
...Automatically manage paging data, and data preloading, reduce unnecessary data refresh, improve fluency by 300%, and reduce coding difficulty by 50%. Send requests immediately by watching state changes, useful in tab switching and condition querying. Global interceptor that supports silent token refresh, as well as providing unified management of token-based login, logout, token assignment, and token refresh. -
19
Voodoo Token
P2P Decentralized Currency on PulseChain
Voodoo Token is a decentralized peer-to-peer meme coin built on the Pulsechain Blockchain. Some key features of Voodoo Token are: fast and cheap transactions, integrating into a gambling DApp, and it's used within DeFi. -
20
OpenSquilla
Token-Efficient AI Agent with same budget, higher intelligence density
OpenSquilla is a token-efficient microkernel AI agent runtime designed for CLI, web UI, and chat-based workflows. It routes each turn through a shared loop that can select lower-cost models when appropriate while preserving tool dispatch, retries, memory, and decision logging. The project supports multiple LLM providers through a pluggable provider layer, making it adaptable to different model ecosystems. -
21
jrean/laravel-user-verification
PHP package built for Laravel 5.* & 6.* & 7.* & 8.* & 9.* & 10.*
jrean/laravel-user-verification is a PHP package built for Laravel 5., 6., 7., 8., 9.* & 10.* to easily handle a user verification and validate the e-mail. -
22
FastVLM
This repository contains the official implementation of FastVLM
...Apple’s research brief frames FastVLM as targeting real-time or latency-sensitive scenarios, where lowering visual token pressure is critical to interactive UX. In short, it’s a practical recipe to make VLMs fast without exotic token-selection heuristics. -
23
Paseto
Platform-Agnostic Security Tokens
Paseto (Platform-Agnostic Security Tokens) is an open-source security token format designed as a more secure alternative to JWT (JSON Web Tokens). Unlike JWT, Paseto eliminates common cryptographic pitfalls by avoiding weak algorithms. It is designed to be secure by default, with built-in cryptographic best practices, making it ideal for applications requiring robust authentication and token management. -
24
MetaMask Browser Extension
The MetaMask browser extension enables browsing Ethereum blockchain
...You always choose what to share and what to keep private. MetaMask provides an essential utility for blockchain newcomers, token traders, crypto gamers, and developers. Over a million downloads and counting! -
25
OpenAI Privacy Filter
Bidirectional token-classification model for identifiable info
OpenAI Privacy Filter is an open-weight machine learning model designed to detect and mask personally identifiable information in text with high efficiency and contextual awareness. It operates as a bidirectional token classification system that labels sensitive data in a single forward pass rather than generating text sequentially, enabling fast processing for large datasets. The model supports long-context inputs, allowing it to analyze extensive documents without chunking, which improves consistency in redaction tasks. It can run locally on standard hardware, ensuring that sensitive information never leaves the user’s environment and supporting privacy-first workflows. ...
