Search Results for "token"
Sort By:
Showing 161 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.
-
Your monitoring isn't a stack. It's a pile. Fix that.Replace Datadog, New Relic, and Sentry without adding three more dashboards.
-
1
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. ... -
2
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. -
3
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. -
4
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. -
Go from Code to Production URL in SecondsSkip the Kubernetes configs. Cloud Run handles HTTPS, scaling, and infrastructure automatically. Two million requests free per month.
-
5
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. ... -
6
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. ... -
7
Step-Audio-EditX
LLM-based Reinforcement Learning audio edit model
...Rather than treating audio editing as low-level waveform manipulation, this model converts speech into a sequence of discrete “audio tokens” (via a dual-codebook tokenizer) — combining a linguistic token stream and a semantic (prosody/emotion/style) token stream — thereby abstracting audio editing into high-level token operations. This allows users to modify not only what is said (the text) but also how it's said: emotion, tone, speaking style, prosody, accent, even paralinguistic cues. Because the model is trained with a “large-margin learning” objective over many synthesized and natural speech samples, it gains robust control over expressive attributes, and can perform iterative editing: e.g. you could record a line, then ask the model to “make it sadder,” “speak slower,” or “change accent to X.” -
8
caveman
Why use many token when few token do trick
Caveman is a lightweight and experimental project focused on simplifying backend or full-stack development workflows through minimalistic abstractions and rapid prototyping principles. It is designed to reduce the complexity of modern frameworks by offering a stripped-down approach that prioritizes speed, clarity, and ease of use. The project often serves as a foundation for developers who want to build applications quickly without being constrained by heavy conventions or extensive... -
9
reg-factory
Google Mail registration
...It combines browser automation, environment-based configuration, and a local web control panel to run multi-step registration scripts. The project includes modules for email registration, platform sign-up flows, token handling, cookie export, and account workflow management. It uses local scripts and external tool integrations to coordinate browser profiles, network settings, Android-based Gmail workflows, and runtime logs. The included panel helps users launch scripts, fill parameters, monitor tool status, and review process output from one place. ... -
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.
-
10
Claude Cognitive
Persistent context and multi-instance coordination
...It introduces an attention-based context router that prioritizes files and content relevant to the current development discussion — tagging them as HOT, WARM, or COLD based on recency and keyword activation — so Claude Code doesn’t waste token budget rereading irrelevant code. This context routing dramatically reduces redundant token usage and accelerates large codebase interactions by focusing only on what truly matters to the current task. Additionally, Claude-Cognitive includes a pool coordinator to share state across multiple Claude Code instances, preserving what’s been learned or completed and preventing repetitive debugging or redundant exploration. -
11
Phenaki - Pytorch
Implementation of Phenaki Video, which uses Mask GIT
Implementation of Phenaki Video, which uses Mask GIT to produce text-guided videos of up to 2 minutes in length, in Pytorch. It will also combine another technique involving a token critic for potentially even better generations. A new paper suggests that instead of relying on the predicted probabilities of each token as a measure of confidence, one can train an extra critic to decide what to iteratively mask during sampling. This repository will also endeavor to allow the researcher to train on text-to-image and then text-to-video. ... -
12
Flask-JWT-Extended
An open source Flask extension that provides JWT support
...Automatic user loading (current_user). Custom claims validation on received tokens. Refresh tokens, first-class support for fresh tokens for making sensitive changes. Token revoking/blocklisting. Storing tokens in cookies and CSRF protection. Adding custom claims to JSON Web Tokens. Automatic user loading (current_user). Custom claims validation on received tokens. Refresh tokens. First-class support for fresh tokens for making sensitive changes. Token revoking/blocklisting. Storing tokens in cookies and CSRF protection. -
13
Headroom
Compress tool outputs, logs, files, and RAG chunks
Headroom is a context optimization layer for LLM applications that compresses information before it reaches the model. It sits between an application and an LLM provider, intercepting requests and forwarding a shorter optimized prompt. The project is designed to reduce token usage while preserving the answer quality needed for agent workflows. It can compress tool outputs, logs, RAG chunks, files, and conversation history. Headroom can be used as a transparent proxy, a Python function, a TypeScript SDK, or through integrations with frameworks such as LangChain and LiteLLM. It is useful for teams building AI agents, research tools, or LLM products where context size, cost, and latency matter. -
14
Claw Compactor
14-stage Fusion Pipeline for LLM token compression
...It addresses the challenge of finite context windows in language models by compressing or summarizing historical interactions while preserving essential information. The system works by transforming older conversation data into condensed representations that maintain continuity without exceeding token limits. This approach allows long-running agent sessions to continue operating efficiently without losing critical context. It is especially useful in autonomous workflows where agents accumulate large volumes of interaction history over time. The project aligns with broader strategies in AI systems that balance memory retention with computational constraints. ... -
15
Claude Code Usage Monitor
Real-time Claude Code usage monitor with predictions and warnings
Claude Code Usage Monitor is a developer-focused terminal tool that provides real-time visibility into Claude Code token consumption and session behavior. The project is designed to help users avoid unexpectedly hitting usage caps by continuously tracking token burn rate, message counts, and estimated costs during active sessions. It presents analytics through a visually rich terminal interface built with modern Python tooling, making it easy to interpret usage trends at a glance. ... -
16
Django Two-Factor Authentication
Complete Two-Factor Authentication for Django
...Built on top of the one-time password framework django-otp and Django's built-in authentication framework django.contrib.auth for providing the easiest integration into most Django projects. Inspired by the user experience of Google's Two-Step Authentication, allowing users to authenticate through call, text messages (SMS), by using a token generator app like Google Authenticator or a YubiKey hardware token generator (optional). If you run into problems, please file an issue on GitHub, or contribute to the project by forking the repository and sending some pull requests. The package is translated into English, Dutch and other languages. Please contribute your own language using Transifex. ... -
17
Kaggle CLI
The official CLI to interact with Kaggle
...The tool is useful for data scientists who want to automate Kaggle workflows inside scripts, CI jobs, notebooks, or reproducible local environments. It supports both traditional API-token authentication and an OAuth login flow, which makes it more flexible for different usage patterns. kaggle-cli is especially practical when working with large datasets or repeated competition submissions that would be slow to handle manually. Its main value is turning Kaggle’s web-based data science platform into a scriptable developer workflow. -
18
Hermes Web UI
The best way to use Hermes Agent from the web or from your phone
...It is built using simple technologies like Python and vanilla JavaScript, avoiding complex frontend frameworks. The UI supports real-time interaction, context tracking, and visualization of token usage. It connects to a self-hosted agent that continuously learns and evolves over time. The project emphasizes usability, accessibility, and seamless integration with existing workflows. -
19
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. ... -
20
Flask-WTF
Simple integration of Flask and WTForms, including CSRF
Simple integration of Flask and WTForms, including CSRF, file upload, and reCAPTCHA. Integration with WTForms. Secure Form with CSRF token. Global CSRF protection. reCAPTCHA support. File upload that works with Flask-Uploads. Internationalization using Flask-Babel. -
21
HunyuanImage-3.0
A Powerful Native Multimodal Model for Image Generation
...It unifies multimodal understanding and generation in a single autoregressive framework, combining text and image modalities seamlessly rather than relying on separate image-only diffusion components. It uses a Mixture-of-Experts (MoE) architecture with many expert subnetworks to scale efficiently, deploying only a subset of experts per token, which allows large parameter counts without linear inference cost explosion. The model is intended to be competitive with closed-source image generation systems, aiming for high fidelity, prompt adherence, fine detail, and even “world knowledge” reasoning (i.e. leveraging context, semantics, or common sense in generation). The GitHub repo includes code, scripts, model loading instructions, inference utilities, prompt handling, and integration with standard ML tooling (e.g. ... -
22
RecursiveMAS
Offical Implementation for "Recursive Multi-Agent Systems"
...It also incorporates an inner–outer loop training approach that optimizes the entire system collectively rather than tuning each agent separately. This design improves efficiency, reduces token usage, and stabilizes learning during iterative reasoning. -
23
OpenSpace
OpenSpace: Make Your Agents: Smarter, Low-Cost, Self-Evolving
...The platform emphasizes collective intelligence, enabling multiple agents to share learned behaviors and benefit from each other’s experiences. It also focuses on cost efficiency by reducing redundant computations and reusing successful workflows, significantly lowering token usage in repeated tasks. The framework includes monitoring and evaluation mechanisms to track skill performance and ensure reliability as systems evolve. It supports integration with various agent platforms, making it flexible and extensible across different environments. -
24
Claude Engineer v3
Claude Engineer is an interactive command-line interface (CLI)
...The project is designed to let Claude identify missing capabilities, generate new tools, load them dynamically, and use them in later conversations. It includes real-time token tracking, conversation state management, tool usage indicators, and structured configuration options. The web interface supports image upload, Markdown rendering, syntax highlighting, and responsive design. Overall, it is an experimental framework for developers who want an AI assistant that can expand its own toolset while helping with software tasks. -
25
Tribler
Privacy enhanced BitTorrent client with P2P content discovery
Tribler is a decentralized, privacy-enhanced BitTorrent client developed by researchers at Delft University of Technology. It introduces built-in anonymity using a Tor-like onion routing network and integrates its own blockchain for economic incentives and trust management. Tribler supports standard torrenting features along with distributed search, self-contained channels, and peer reputation. Its goal is to provide a fully autonomous file-sharing network without relying on external...
