Search Results for "so" - Page 18
Sort By:
Showing 1302 open source projects for "so"
View related business solutions-
Fully Managed MySQL, PostgreSQL, and SQL ServerCloud SQL handles your database ops end to end, so you can focus on your app.
-
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.
-
1
Claude Code Tools
Practical productivity tools for Claude Code, Codex-CLI
...It includes tools that allow developers to search conversation logs quickly, manage environment variables securely, and execute interactive terminal workflows that AI agents can control. Some components enable Claude Code to interact with terminal multiplexers such as tmux so that it can run programs, debug applications, and interact with scripts that require user input. The toolkit also provides safety mechanisms that prevent potentially dangerous shell commands from being executed automatically by AI agents. -
2
mergekit
Tools for merging pretrained large language models
mergekit is an open-source toolkit designed to combine multiple pretrained language models into a single unified model through parameter merging techniques. The framework enables developers to merge model checkpoints so that the resulting model inherits capabilities from several source models without requiring additional training. This approach allows researchers to combine specialized models into a more versatile system capable of performing multiple tasks. mergekit implements a variety of merging algorithms and strategies that control how model parameters are blended together during the merging process. ... -
3
Continuous Claude v3
Context management for Claude Code. Hooks maintain state via ledgers
...Rather than relying on a single session’s context, Continuous Claude uses mechanisms like ledgers, YAML handoffs, and a memory system to preserve and recall state across multiple sessions, ensuring that learned insights and plans are not lost when context compaction occurs. 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. -
4
Top Deep Learning Projects
A list of popular github projects related to deep learning
TopDeepLearning is a curated index of the most popular GitHub projects related to deep learning, ranked by their star count. Rather than being a library itself, it serves as a curated roadmap and reference guide for anyone exploring the deep learning ecosystem — from beginners to experienced practitioners. By aggregating high-star projects across frameworks (TensorFlow, PyTorch), tools (computer vision, NLP, reinforcement learning), tutorials, and research code, it helps users quickly... -
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
5
OpenAGI
When LLM Meets Domain Experts
OpenAGI is a package for AI agent creation designed to connect large language models with domain-specific tools and workflows in the AIOS (AI Operating System) ecosystem. It provides a structured Python framework, pyopenagi, for defining agents as modular units that encapsulate execution logic, configuration, and dependency metadata. Agents are organized in a well-defined folder structure that includes code (agent.py), configuration (config.json), and extra requirements... -
6
FastKoko
Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model
FastKoko is a self-hosted text-to-speech server built around the Kokoro-82M model and exposed through a FastAPI backend. 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. ... -
7
CosyVoice
Multi-lingual large voice generation model, providing inference
...The model supports multiple languages, including Chinese, English, Japanese, Korean, and a range of Chinese dialects such as Cantonese, Sichuanese, Shanghainese, Tianjinese, and Wuhanese. It is designed for zero-shot voice cloning and cross-lingual or mix-lingual scenarios, so a single reference voice can be used to synthesize speech across languages and in code-switching contexts. CosyVoice 2.0 significantly improves on version 1.0 by boosting accuracy, stability, speed, and overall speech quality, making it more suitable for production environments. The repository contains training recipes, inference pipelines, deployment scripts, and integration examples, positioning it as a comprehensive toolkit rather than just a set of model weights. -
8
Positron
Positron, a next-generation data science IDE
Positron is a next-generation integrated development environment (IDE) created by Posit PBC (formerly RStudio Inc) specifically tailored for data science workflows in Python, R, and multi-language ecosystems. It aims to unify exploratory data analysis, production code, and data-app authoring in a single environment so that data scientists move from “question → insight → application” without switching tools. Built on the open-source Code-OSS foundation, Positron provides a familiar coding experience along with specialized panes and tooling for variable inspection, data-frame viewing, plotting previews, and interactive consoles designed for analytical work. ... -
9
Blik
Self hosted & open source anonymous 360 review software
...The system is built using the Django framework, with a PostgreSQL backend, and is packaged for easy deployment via Docker Compose, making it accessible for small teams or startups to spin up on their own infrastructure. One of the core design choices is true anonymity: reviewers use token-based links rather than user accounts, and the architecture is designed so that even administrators cannot trace responses back to individuals under normal operation. -
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.
-
10
Tabby Web
An SSH/Telnet/Serial client in your browser
...It aims to deliver an experience similar to the desktop Tabby terminal—sessions, profiles, and rich configuration—while being accessible anywhere through a login. The architecture splits concerns: a Django-based control plane manages users, auth, and configuration, while a gateway service handles network transport so browser clients can reach SSH, Telnet, or serial targets. This separation enables multi-user deployments with persistent settings, role-based access, and storage backends for artifacts. It’s useful for organizations that need managed remote access from within a web portal, without installing a full desktop client on every machine. ... -
11
Homemade Machine Learning
Python examples of popular machine learning algorithms
homemade-machine-learning is a repository by Oleksii Trekhleb containing Python implementations of classic machine-learning algorithms done “from scratch”, meaning you don’t rely heavily on high-level libraries but instead write the logic yourself to deepen understanding. Each algorithm is accompanied by mathematical explanations, visualizations (often via Jupyter notebooks), and interactive demos so you can tweak parameters, data, and observe outcomes in real time. The purpose is pedagogical: you’ll see linear regression, logistic regression, k-means clustering, neural nets, decision trees, etc., built in Python using fundamentals like NumPy and Matplotlib, not hidden behind API calls. It is well suited for learners who want to move beyond library usage to understand how algorithms operate internally—how cost functions, gradients, updates and predictions work. -
12
Inspect Petri
An alignment auditing agent capable of exploring alignment hypothesis
...Instead of building bespoke evals, Inspect Petri automatically generates audit environments from seed “special instructions,” orchestrates an auditor model to probe a target model, and simulates tool use and rollbacks to surface risky behaviors. Each interaction transcript is then scored by a judge model using a consistent rubric so results are comparable across runs and models. The system supports major model APIs and comes with starter seeds and judge dimensions, enabling minutes-to-insight workflows for questions like reward hacking, self-preservation, or eval awareness. Petri is designed for parallel exploration: it spins many audits in flight, aggregates findings, and highlights transcripts that deserve human review. -
13
fvcore
Collection of common code shared among different research projects
...A standout capability is FLOP and activation counting, which analyzes arbitrary PyTorch graphs to report cost by operator and by module for precise profiling. The file I/O layer (PathManager) abstracts local/remote storage so the same code can read from disks, cloud buckets, or HTTP endpoints. Because it is small, stable, and well-tested, fvcore is frequently imported by projects like Detectron2 and PyTorchVideo to avoid duplicating infrastructure and to keep research repos. -
14
Large Concept Model
Language modeling in a sentence representation space
...It includes utilities to build concept vocabularies, map supervision signals to those vocabularies, and measure zero-shot or few-shot generalization. Probing tools help diagnose what the model knows—e.g., attribute recognition, relation understanding, or compositionality—so you can iterate on data and objectives. The design is modular, making it straightforward to swap backbones, change objectives, or integrate retrieval components. -
15
DeepSeek VL2
Mixture-of-Experts Vision-Language Models for Advanced Multimodal
DeepSeek-VL2 is DeepSeek’s vision + language multimodal model—essentially the next-gen successor to their first vision-language models. It combines image and text inputs into a unified embedding / reasoning space so that you can query with text and image jointly (e.g. “What’s going on in this scene?” or “Generate a caption appropriate to context”). The model supports both image understanding (vision tasks) and multimodal reasoning, and is likely used as a component in agent systems to process visual inputs as context for downstream tasks. The repository includes evaluation results (e.g. image/text alignment scores, common VL benchmarks), configuration files, and model weights (where permitted). ... -
16
Super Tiny Icons
Super Tiny Icons are miniscule SVG versions of your favourite website
...Designers and developers can embed the icons directly, recolor them via CSS, or combine them in sprites without raster assets. The repository maintains consistent viewboxes and alignment so icons sit neatly alongside text and other UI elements. It is especially useful for landing pages, status banners, and mobile experiences where every byte matters. -
17
Flama
Fire up your models with the flame
Flama is a python library which establishes a standard framework for development and deployment of APIs with special focus on machine learning (ML). The main aim of the framework is to make ridiculously simple the deployment of ML APIs, simplifying (when possible) the entire process to a single line of code. The library builds on Starlette, and provides an easy-to-learn philosophy to speed up the building of highly performant GraphQL, REST and ML APIs. Besides, it comprises an ideal solution... -
18
Griptape
Python framework for AI workflows and pipelines with chain of thought
...Griptape not only helps developers harness the potential of LLMs but also enforces trust boundaries, schema validation, and tool activity-level permissions. By doing so, Griptape maximizes LLMs’ reasoning while adhering to strict policies regarding their capabilities. -
19
Orion
A machine learning library for detecting anomalies in signals
...Build time series anomaly detection platforms custom to their workflows through our backend database and rest API. A way for machine learning researchers to contribute in a scaffolded way so their innovations are immediately available to the end users. -
20
Simple StyleGan2 for Pytorch
Simplest working implementation of Stylegan2
...If a previous checkpoint contained a better generator, (which often happens as generators start degrading towards the end of training), you can load from a previous checkpoint with another flag. A technique used in both StyleGAN and BigGAN is truncating the latent values so that their values fall close to the mean. The small the truncation value, the better the samples will appear at the cost of sample variety. -
21
spacy-transformers
Use pretrained transformers like BERT, XLNet and GPT-2 in spaCy
...Transfer learning refers to techniques such as word vector tables and language model pretraining. These techniques can be used to import knowledge from raw text into your pipeline, so that your models are able to generalize better from your annotated examples. You can convert word vectors from popular tools like FastText and Gensim, or you can load in any pre trained transformer model if you install spacy-transformers. You can also do your own language model pretraining via the spacy pre train command. You can even share your transformer or another contextual embedding model across multiple components, which can make long pipelines several times more efficient. ... -
22
Django Wiki
A wiki system with complex functionality for simple integration
A wiki system with complex functionality for simple integration and a superb interface. Store your knowledge with style: Use django models. Readability, however, is emphasized above all else. A Markdown-formatted document should be publishable as-is, as plain text, without looking like it's been marked up with tags or formatting instructions. While Markdown's syntax has been influenced by several existing text-to-HTML filters -- including Setext, atx, Textile, reStructuredText, Grutatext,... -
23
django-webpack-loader
Transparently use webpack with django
...Django webpack loader consumes the output generated by webpack-bundle-tracker and lets you use the generated bundles in Django. Test cases cover Django>=2.0 on Python>=3.5. 100% code coverage is the target so we can be sure everything works anytime. It should probably work on older versions of Django as well but the package does not ship any test cases for them. Before configuring django-webpack-loader, let's first configure what's necessary on the webpack-bundle-tracker side. Update your Webpack configuration file (it's usually on webpack.config.js in the project root). ... -
24
Errbot
Chatbot daemon that connects to your favorite chat services
Errbot is a chatbot, a daemon that connects to your favorite chat service and brings your tools into the conversation. The goal of the project is to make it easy for you to write your own plugins so you can make it do whatever you want, a deployment, retrieving some information online, trigger a tool via an API, troll a co-worker, etc. Errbot is being used in a lot of different contexts, chatops (tools for devops), online gaming chatrooms like EVE, video streaming chatrooms like livecoding.tv, home security, etc. Extending Errbot and adding your own commands can be done by creating a plugin, which is simply a class derived from BotPlugin. ... -
25
PyTorch Lightning
The lightweight PyTorch wrapper for high-performance AI research
...PyTorch Lightning can easily be applied for any use case. With just a quick refactor you can run your code on any hardware, run distributed training, perform logging, metrics, visualization and so much more!
