Search Results for "sarvesh-project" - Page 33
Sort By:
Showing 3484 open source projects for "sarvesh-project"
View related business solutions-
Forever Free Full-Stack Observability | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
1
rLLM
Democratizing Reinforcement Learning for LLMs
...With rLLM, developers can define custom “agents” and “environments,” and then train those agents via reinforcement learning workflows, possibly surpassing what vanilla fine-tuning or supervised learning might provide. The project is designed to support large-scale language models (including support for big models via integrated training backends), making it relevant for state-of-the-art research and production use. The framework includes tools for defining workflows, specifying objectives or reward functions, and managing training/policy updates across possibly distributed settings. -
2
BlogWizard
Generate blog articles from video or audio
BlogWizard is a demo/utility project built on top of Groq’s LLM infrastructure that converts video or audio content into well-structured blog posts, enabling creators to repurpose multimedia content into text — useful for SEO, accessibility, or reaching audiences that prefer reading. The tool uses transcription (e.g. via Whisper) to extract text from audio/video, then runs an LLM-based generation pipeline to transform that content into coherent, readable blog-format posts — with sections, formatting, and possibly metadata. ... -
3
OpenAGI
When LLM Meets Domain Experts
...Agents are organized in a well-defined folder structure that includes code (agent.py), configuration (config.json), and extra requirements (meta_requirements.txt), which makes them easy to package, share, and reuse. The project includes tooling for registering agents with AIOS by uploading them via a command-line interface, enforcing a consistent naming scheme that matches the local folder layout. A companion tooling layer lets agents call external tools described in the tools.md documentation, enabling them to orchestrate APIs, retrieval pipelines, and other utilities in response to LLM decisions. -
4
USO
Open-sourced unified customization model
...By decoupling style and subject, USO enables reuse of learned style/style-embeddings across different subjects, or vice versa, which makes generation more modular and controllable. The project provides tooling (in Python) including inference and workflow scripts, example configurations, and support for generation pipelines; and as of 2025, USO is also natively supported in some mainstream generative-art UI pipelines (e.g. ComfyUI) to ease adoption. -
AI-powered service management for IT and enterprise teamsGive your IT, operations, and business teams the ability to deliver exceptional services—without the complexity. Maximize operational efficiency with refreshingly simple, AI-powered Freshservice.
-
5
Poetiq
Reproduction of Poetiq's record-breaking submission to the ARC-AGI-1
poetiq-arc-agi-solver is the open-source codebase from Poetiq that replicates their record-breaking submission to the challenging benchmark suite ARC-AGI (both ARC-AGI-1 and ARC-AGI-2). The project demonstrates a system that orchestrates large language models (LLMs) — like those from major providers — with carefully engineered prompting, reasoning workflows, and dynamic strategies, to tackle the abstract, logic-heavy problems in ARC-AGI. Instead of relying on a single prompt or fixed strategy, their solver dynamically adapts the reasoning path, selecting what to ask or analyze next depending on intermediate results — effectively compositing reasoning, perception, and program synthesis (or symbolic manipulation) in a loop. ... -
6
FastKoko
Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model
...It is designed to be easy to deploy via Docker, with separate CPU and GPU images so that users can choose between pure CPU inference and NVIDIA GPU acceleration. The project exposes an OpenAI-compatible speech endpoint, which means existing code that talks to the OpenAI audio API can often be pointed at a Kokoro-FastAPI instance with minimal changes. It supports multiple languages and voicepacks and allows phoneme based generation for more accurate pronunciation and prosody. The server also offers per-word timestamped captions, which makes it useful for creating subtitles or aligning audio with text. ... -
7
MLX-Audio
A text-to-speech, speech-to-text and speech-to-speech library
...Because it uses MLX and targets Apple Silicon, inference is fast and can take advantage of hardware acceleration and quantization for efficient on-device performance. The project provides a straightforward CLI (mlx_audio.tts.generate) as well as a Python API for programmatic generation of audio, including parameters for voice choice, speed, language hints, output format, and sample rate. It includes examples such as audiobook generation to demonstrate long-form synthesis and joined audio segments. On top of that, MLX-Audio offers a modern web interface powered by FastAPI, with real-time waveform and 3D visualizations, file upload, and audio management. -
8
Meta-World
Collections of robotics environments
...The environments adhere to the Gymnasium API, which makes them easy to plug into existing RL pipelines, and they support both synchronous and asynchronous vectorized execution for running many environments in parallel. Installation is done via pip, with official support for Python versions 3.8 through 3.11 on Linux and macOS, and the project is licensed under MIT to encourage broad academic and industry use. -
9
Janus
Unified Multimodal Understanding and Generation Models
Janus is a sophisticated open-source project from DeepSeek AI that aims to unify both visual understanding and image generation in a single model architecture. Rather than having separate systems for “look and describe” and “prompt and generate”, Janus uses an autoregressive transformer framework with a decoupled visual encoder—allowing it to ingest images for comprehension and to produce images from text prompts with shared internal representations. -
Gemini 3 and 200+ AI Models on One PlatformBuild, govern, and optimize agents and models with Gemini Enterprise Agent Platform.
-
10
Google Toolbox for Mac
Google Toolbox for Mac
...The library includes modules for networking, logging, testing, data handling, and user interface extensions, helping developers avoid reinventing common functionality. Its modular design allows developers to integrate only the components they need, improving project flexibility and performance. With well-documented interfaces and consistent coding standards, Google Toolbox for Mac serves as a reliable foundation for both small and large-scale applications. It continues to be widely used across open source and internal projects that target Apple ecosystems. -
11
Materials Discovery: GNoME
AI discovers 520000 stable inorganic crystal structures for research
Materials Discovery (GNoME) is a large-scale research initiative by Google DeepMind focused on applying graph neural networks to accelerate the discovery of stable inorganic crystal materials. The project centers on Graph Networks for Materials Exploration (GNoME), a message-passing neural network architecture trained on density functional theory (DFT) data to predict material stability and energy formation. Using GNoME, DeepMind identified 381,000 new stable materials, later expanding the dataset to include over 520,000 materials within 1 meV/atom of the convex hull as of August 2024. ... -
12
Tracking Any Point (TAP)
DeepMind model for tracking arbitrary points across videos & robotics
TAPNet is the official Google DeepMind repository for Tracking Any Point (TAP), bundling datasets, models, benchmarks, and demos for precise point tracking in videos. The project includes the TAP-Vid and TAPVid-3D benchmarks, which evaluate long-range tracking of arbitrary points in 2D and 3D across diverse real and synthetic videos. Its flagship models—TAPIR, BootsTAPIR, and the latest TAPNext—use matching plus temporal refinement or next-token style propagation to achieve state-of-the-art accuracy and speed on TAP-Vid. ... -
13
FastAPI-MCP
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools
...A tiny bootstrap is enough to stand up an MCP server and, if desired, mount an HTTP transport for remote clients. The docs emphasize a FastAPI-first workflow: keep your schemas, reuse your middleware, and surface endpoints to agents without rewriting controllers. The project is active, with examples and a dedicated site that shows getting started, security, and transport options. -
14
Standard Webhooks
The Standard Webhooks specification
Standard Webhooks is a community-driven specification and set of open-source tools designed to make webhooks consistent, secure, and interoperable across providers. The project defines strict guidelines covering aspects like signature formats, headers, timestamps, replay protection, and forward compatibility. It includes reference implementations for signature verification and signing across multiple languages such as Python, JavaScript/TypeScript, Go, Rust, Ruby, PHP, C#, Java, and Elixir, along with additional community SDKs. ... -
15
MegaLinter
Mega-Linter analyzes 50 languages, 22 formats, 21 tooling formats etc.
...Projects need to contain clean code, in order to avoid technical debt, which makes evolutive maintenance harder and time-consuming. By using code formatters and code linters, you ensure that your code base is easier to read and respects best practices, from the kick-off to each step of the project lifecycle. Not all developers have the good habit to use linters in their IDEs, making code reviews harder and longer to process. -
16
NVIDIA FLARE
NVIDIA Federated Learning Application Runtime Environment
NVIDIA Federated Learning Application Runtime Environment NVIDIA FLARE is a domain-agnostic, open-source, extensible SDK that allows researchers and data scientists to adapt existing ML/DL workflows(PyTorch, TensorFlow, Scikit-learn, XGBoost etc.) to a federated paradigm. It enables platform developers to build a secure, privacy-preserving offering for a distributed multi-party collaboration. NVIDIA FLARE is built on a componentized architecture that allows you to take federated... -
17
DVC
Data Version Control | Git for Data & Models
DVC is built to make ML models shareable and reproducible. It is designed to handle large files, data sets, machine learning models, and metrics as well as code. Version control machine learning models, data sets and intermediate files. DVC connects them with code and uses Amazon S3, Microsoft Azure Blob Storage, Google Drive, Google Cloud Storage, Aliyun OSS, SSH/SFTP, HDFS, HTTP, network-attached storage, or disc to store file contents. Version control machine learning models, data sets,... -
18
django-organizations
Multi-user accounts for Django projects
Separate individual user identity from accounts and subscriptions. Django Organizations adds user-managed, multi-user groups to your Django project. Use Django Organizations whether your site needs organizations that function like social groups or multi-user account objects to provide account and subscription functionality beyond the individual user. Works with your existing user model, whether django.contrib.auth or a custom model. No additional user or authentication functionality is required. ... -
19
Django OAuth Toolkit
OAuth2 goodies for the Djangonauts!
Django OAuth Toolkit can help you by providing, out of the box, all the endpoints, data, and logic needed to add OAuth2 capabilities to your Django projects. Django OAuth Toolkit makes extensive use of the excellent OAuthLib, so that everything is rfc-compliant. OAuth is an open standard for access delegation, commonly used as a way for Internet users to grant websites or applications access to their information on other websites but without giving them the passwords. Django is a high-level... -
20
Seldon Core
An MLOps framework to package, deploy, monitor and manage models
...Advanced deployments with experiments, ensembles and transformers. Our open-source framework makes it easier and faster to deploy your machine learning models and experiments at scale on Kubernetes. The Kubeflow project is dedicated to making deployments of machine learning (ML) workflows on Kubernetes. -
21
wemake-python-styleguide
The strictest and most opinionated python linter ever!
...Reduce code redundancy - Sometimes we write complex code as we are thinking in a certain way about a problem. The linter offers suggestions that can help simplify the code and eliminate redundant statements. The ultimate goal of this project is to make all people write exactly the same Python code. -
22
Pwntools
CTF framework and exploit development library
...Written in Python, it is designed for rapid prototyping and development, and intended to make exploit writing as simple as possible. Whether you’re using it to write exploits, or as part of another software project will dictate how you use it. Historically pwntools was used as a sort of exploit-writing DSL. Simply doing from pwn import in a previous version of pwntools would bring all sorts of nice side-effects. This version imports everything from the toplevel pwnlib along with functions from a lot of submodules. This means that if you do import pwn or from pwn import , you will have access to everything you need to write an exploit. ... -
23
SuggestArr
Request recommended movies, TV shows and anime to Jellyseer/Overseer
SuggestArr is an open-source automation platform designed to recommend and automatically request movies, TV shows, and anime based on a user’s viewing history in self-hosted media servers. The project integrates with popular media management systems such as Jellyfin, Plex, and Emby, allowing it to analyze recently watched content and identify similar titles using metadata from the TMDb database. Once potential recommendations are identified, SuggestArr can automatically send download or request instructions to services like Jellyseer or Overseerr, which then coordinate with media download tools and libraries. ... -
24
kubectl-aliases
Programmatically generated handy kubectl aliases
kubectl-aliases is a small but extremely handy project that generates hundreds of shell aliases for kubectl so you no longer have to type long commands and flags repeatedly. It ships a prebuilt .kubectl_aliases file for Bash/Zsh, plus variants for Fish and Nushell, which you drop into your home directory and source from your shell config. The aliases are programmatically generated from permutations of common verbs, resources, flags, and options, so you get short forms like kgpo for kubectl get pod and more complex ones that include namespaces, label selectors, and output formats. ... -
25
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.
