Search Results for "so" - Page 12
Sort By:
Showing 1302 open source projects for "so"
View related business solutions-
Cut Data Warehouse Costs by 54%BigQuery delivers 54% lower TCO with exabyte scale and flexible pricing. Free migration tools handle the SQL translation automatically.
-
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.
-
1
Serena
Agent toolkit providing semantic retrieval and editing capabilities
Serena is a coding-focused agent toolkit that turns an LLM into a practical software-engineering agent with semantic retrieval and editing over real repositories. It operates as an MCP server (and other integrations), exposing IDE-like tools so agents can locate symbols, reason about code structure, make targeted edits, and validate changes. The toolkit is LLM-agnostic and framework-agnostic, positioning itself as a drop-in capability for different chat UIs, orchestrators, or custom agent stacks. It emphasizes symbol-level understanding rather than naive file-wide diffs, enabling more precise refactors and additions. ... -
2
Pearl
A Production-ready Reinforcement Learning AI Agent Library
...Tutorials demonstrate end-to-end workflows on OpenAI Gym tasks and contextual-bandit setups derived from tabular datasets, emphasizing reproducibility and clear baselines. Pearl’s design favors clarity and deployability: metrics, logging, and evaluation harnesses are integrated so you can monitor learning, compare agents, and catch regressions. -
3
Tiktoken
tiktoken is a fast BPE tokeniser for use with OpenAI's models
...The repo supports multiple encodings (e.g. “cl100k_base”) and lets users switch encoding names to match different model contexts. It also offers extension mechanisms so that custom encodings can be registered. Internally, it includes the core tokenizer logic (often implemented in Rust or efficient lower-level code), APIs for encoding, decoding, and counting tokens, and binding layers to Python (and sometimes other languages) for easy use. -
4
You-Get
Dumb downloader that scrapes the web
You-Get is a small command-line utility for downloading media (video, audio and images) from the Web when there are no other means to do so. It can download video and audio files from such popular web sites as YouTube, Twitter, Niconico, Vimeo, Flickr, Instagram and a whole lot more. You-Get is a great option for when you want to enjoy your favorite videos, audio or images from the internet without having to open any web browsers or get interrupted by ads. It’s also a good choice for when you want to get rid of any closed-source technology or proprietary JavaScript code from running on your computer. -
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.
-
5
Style-Bert-VITS2
Style-Bert-VITS2: Bert-VITS2 with more controllable voice styles
Style-Bert-VITS2 is a text-to-speech system based on Bert-VITS2 that focuses on highly controllable voice styles and emotional expression. It takes the original Bert-VITS2 v2.1 and its Japanese-Extra variant and extends them so you can control emotion and speaking style with fine-grained intensity, not just choose a generic tone. The project targets both power users and beginners: Windows users without Git or Python can install and run it using bundled .bat scripts, while advanced users can work with virtual environments, uv, and Python tooling. It includes a full GUI editor to script dialogue, set different styles per line, edit dictionaries, and save/load projects, plus a separate web UI and Colab notebooks for training and experimentation. ... -
6
litelm
litellm without the bloat
...It supports provider/model routing, streaming, embeddings, text completions, tool calling, and the OpenAI Responses API. The package mirrors LiteLLM function names and response shapes so existing code can often switch with only an import change. It routes requests across 19 providers and can also target OpenAI-compatible local servers through a custom API base. Async variants are available for the major operations. Provider errors are normalized into a shared exception hierarchy. The project intentionally omits load-balancing routers, caching, budgets, token counting, agents, image generation, and other heavier features. -
7
PRAXIST
Autonomous research system for measurable computer-executable research
...Parallel research peers explore competing hypotheses and implementations while evaluators convert outcomes into structured evidence. That evidence is carried across generations so later work can build on promising strategies and avoid repeating weak ones. The system supports multi-metric evaluation, quality-diversity methods, resource-aware scheduling, and durable evidence tracking. Runs can be monitored, stopped, resumed, and replayed, with the task project remaining the source of truth for objectives, metrics, baselines, and domain constraints. -
8
codex-keysmith
Version-independent Codex instruction deployment
Codex Keysmith is a zero-dependency Python utility for deploying versioned instruction files into Codex configuration directories. It updates the global model instruction setting so every new Codex session under that configuration loads the selected Markdown file. The tool previews changes by default and requires explicit confirmation before writing. It creates backups, isolates existing hooks, and records file ownership in a manifest for controlled recovery. Status checks and dry runs show the target directories, prompt source, and planned modifications before deployment. ... -
9
Defending Code Reference Harness
Skills for threat modeling, scanning, triage, patching, etc.
...The project includes skills for threat modeling, scanning, triage, patching, and customizable autonomous analysis workflows. Its default pipeline focuses on finding memory bugs in C and C++ code using ASAN as the crash detector. The overall architecture is meant to be adaptable, so teams can modify it for other languages, bug classes, and detection systems. Its main value is giving defenders a practical framework for exploring AI-assisted secure code review and remediation. -
Demo Series - Small Business Backup By VeeamWatch this on-demand demo series and learn how to protect your Microsoft 365 data with clear, simple, actionable steps that are easy to implement for businesses of all sizes.
-
10
AnySearch Skill
Unified real-time search engine skill for AI agents
...It gives agents a structured way to search the web, run vertical searches, perform parallel batch searches, and extract full-page content. The project is packaged as a skill rather than a standalone search application, so it is meant to be installed into compatible AI-agent environments. It supports multiple domain-specific search categories, making it useful when general web search is too broad. The skill can also fetch page content after a URL is found, which helps agents answer questions from source material rather than snippets alone. Its main value is turning web search into a reusable, agent-friendly capability with consistent inputs and outputs. -
11
Crossbar.io
Crossbar.io - WAMP application router
...It implements the Web Application Messaging Protocol, which allows application components to communicate through routed remote procedure calls and publish-subscribe messaging. The platform is designed to handle the messaging layer so developers can focus on business logic instead of building custom connection, routing, and event systems. It supports real-time application architectures where services, browsers, devices, and backend components need to exchange messages reliably. Crossbar.io is especially useful for event-driven systems, IoT backends, dashboards, collaborative applications, and distributed service environments. ... -
12
Claude Quickstarts
A collection of projects for building deployable applications
Claude Quickstarts is a curated collection of starter projects and templates that help developers quickly begin building applications with the Claude API, making it easier to leverage Anthropic’s Claude models for real use cases. Each quickstart provides a foundational codebase with preconfigured settings and examples for common deployment scenarios, so developers can focus on customizing functionality instead of bootstrapping infrastructure. The repository includes demos, sample integrations, and instructions to get environments running with minimal setup while handling authentication, API calls, and error handling best practices. Because it’s designed as a learning and prototyping resource, Claude Quickstarts supports exploration of interactive applications, backend services, and workflows that benefit from large language model capabilities. -
13
Slack Machine
A simple, yet powerful and extendable Slack bot
Slack Machine is a simple, yet powerful and extendable Slack bot framework. More than just a bot, Slack Machine is a framework that helps you develop your Slack workspace into a ChatOps powerhouse. Slack Machine is built with an intuitive plugin system that lets you build bots quickly but also allows for easy code organization. A plugin can look as simple as this: -
14
RenderCV
LaTeX CV generator from a YAML/JSON input file
RenderCV is a LaTeX CV/resume framework. It allows you to create a high-quality CV as a PDF from a YAML file with full Markdown syntax support and complete control over the LaTeX code. RenderCV offers built-in LaTeX and Markdown templates ready to produce high-quality CVs. However, the templates are entirely arbitrary and can easily be updated to leverage RenderCV's capabilities with your custom CV themes. -
15
Oppia
A free, online learning platform to make quality education accessible
...These activities simulate a one-on-one conversation with a tutor, making it possible for students to learn by doing while getting feedback. Oppia identifies common wrong answers and provides tailored feedback, so that students get a personalized experience. Our lessons keep students engaged through playful characters and use different strategies to solidify their knowledge. Check out our math lessons with proven results! In addition to developing the Oppia platform, the team is also developing and piloting a set of free and effective lessons on basic mathematics. ... -
16
YAPF
A formatter for Python files
...Styles are highly configurable: start from presets like pep8, google, yapf, or facebook, then override dozens of options in .style.yapf, setup.cfg, or pyproject.toml. It supports recursive directory formatting, line-range formatting, and diff-only output so you can check or fix just the lines you touched. -
17
Zipline Reloaded
Zipline, a Pythonic Algorithmic Trading Library
...Strategies can also use libraries such as SciPy, Matplotlib, statsmodels, and scikit-learn for analysis and modeling. The maintained fork updates dependencies and compatibility so the established Zipline workflow remains usable on modern Python environments. -
18
GAIA
Proactive personal AI assistant & companion for daily productivity
...Multi-step workflows may run on schedules or respond to triggers such as new email, calendar changes, or webhooks. Cross-tool memory retains information about people, projects, preferences, and prior conversations so users do not need to repeat context. Integrations cover services such as Gmail, Calendar, Slack, Linear, Notion, WhatsApp, Telegram, and Discord, with support for additional MCP servers. GAIA is available through web, desktop, and mobile interfaces and can also communicate through messaging platforms. The full-stack Nx monorepo includes Next.js, Electron, React Native, FastAPI, LangGraph, bots, voice processing, and Docker-based self-hosting. -
19
Make It heavy
A Python framework that emulates Grok Heavy functionality
Make It heavy is a Python framework for producing deeper AI analysis through multi-agent orchestration. It is designed to emulate the style of Grok Heavy by splitting a user query into several specialized research angles. The system runs four agents in parallel so each one can explore the problem from a different perspective. It then combines their outputs into one unified answer through an intelligent synthesis step. The framework uses OpenRouter for model access and can also run in single-agent mode for simpler tasks. Overall, it is useful for users who want broader research coverage, richer reasoning diversity, and structured multi-agent responses from one command-line workflow. -
20
GoPay Workflow Orchestrator
Lightweight process orchestration framework for regional payment
...It focuses on engineering reliability in multi-stage payment journeys that involve provider redirects, tokenized requests, verification challenges, asynchronous polling, and final status confirmation. The project organizes scattered payment steps into a reproducible and observable process so developers can inspect state transitions and integration failures. It includes an orchestrator-style structure and supporting utilities, including an OTP-forwarding component for controlled testing environments. Because it interacts with payment and verification flows, it should only be used with accounts, systems, and test cases the user is authorized to operate. ... -
21
Meli-Action
Download files from direct links, YouTube, Telegram, Google Play
...It uses GitHub-hosted workflow runners to fetch content from direct links, YouTube, Telegram, Google Play, SoundCloud, and web pages. Downloaded files are committed into the user’s repository so they can be retrieved later through normal GitHub access. The project includes workflows for different content sources, plus a Python script that can render and save web pages as MHTML archives using a headless browser. It also handles large direct-download files by splitting them into smaller chunks that fit repository limits. Its main value is offering a cloud-run, no-local-install workflow for saving files and pages when direct access is unreliable or blocked. -
22
OPAL
Policy and data administration, distribution, and real-time updates
OPAL is an open-source administration layer for keeping authorization policies and authorization data synchronized in real time. It works with policy engines such as OPA and Cedar so applications can make decisions using current policy and data without constantly rebuilding custom sync logic. The project aggregates policy and data from external sources, watches for changes, and distributes updates to connected policy agents. It is built for cloud-native and microservice environments where authorization rules change frequently and need to propagate quickly. ... -
23
machine_learning_examples
A collection of machine learning examples and tutorials
...Many of the examples are accompanied by tutorials and educational materials that explain how the algorithms work and how they can be applied in real-world projects. The code is organized into small independent experiments so that learners can explore specific algorithms or techniques without needing to understand the entire codebase. -
24
List of independent blogs in Chinese
List of independent blogs in Chinese
...The project aims to promote the independent blogging ecosystem by making it easier for readers to discover high-quality personal sites outside major content platforms. It is community-driven, allowing contributors to submit and update blog entries so the directory remains current and diverse. The repository functions both as a discovery index and as a cultural snapshot of the independent Chinese web publishing landscape. It is particularly useful for developers, researchers, and readers interested in decentralized content and personal publishing trends. Overall, the project acts as a living catalog that supports the visibility and longevity of independent blogging communities. -
25
MemMachine
Universal memory layer for AI Agents
MemMachine is a universal memory layer designed for AI agents that provides persistent, rich memory storage and retrieval capabilities so autonomous agent systems can recall context, personal preferences, and long-term interaction history across sessions, models, and use cases. Unlike ephemeral LLM prompt state, MemMachine supports distinct memory types—short-term conversational context, long-term persistent knowledge, and profile memory for personalized facts—persisted in optimized stores (e.g., graph databases for episodic lines of reasoning and SQL for user facts) to support robust, context-aware intelligence in agents. ...
