Search Results for "mac" - Page 72
Sort By:
Showing 11365 open source projects for "mac"
View related business solutions-
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.
-
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.
-
1
jlens
Companion code for the global workspace interpretability paper
Jacobian Lens is Anthropic’s reference implementation for examining what a language model’s internal activations are inclined to produce as text. It transports residual-stream vectors from selected layers and positions into the final-layer basis using an averaged input-output Jacobian. The transformed vectors are decoded through the model’s own unembedding into ranked vocabulary predictions. The package can fit new lenses, load saved ones, apply them to prompts, and merge results from... -
2
ThinkStats2
Text and supporting code for Think Stats, 2nd Edition
ThinkStats2 is the code and text companion for the second edition of Think Stats, an introduction to statistics and data science for Python programmers. It teaches probability and statistical reasoning through short programs, experiments, and analysis of real datasets. The material emphasizes exploratory methods that help readers ask and answer practical questions with data. Case studies draw from public sources, including health-related datasets, to connect abstract concepts with realistic... -
3
DocuBrowse
This does for Documents what repo-browser does for repos
DocuBrowse is a local AI-powered document search engine for personal or professional file collections. It indexes documents such as PDFs, Word files, spreadsheets, presentations, ebooks, HTML, text, and Markdown. The system combines SQLite FTS5 keyword search with local semantic embeddings for meaning-based retrieval. Users can click search results to generate an AI synopsis before opening the original file. It runs entirely on the user’s machine with Ollama models, so it does not require... -
4
TabFM
scikit-learn compatible tabular foundation model
TabFM is a tabular foundation model from Google Research for zero-shot classification and regression on structured datasets. It is designed to work with mixed numerical and categorical columns without requiring a custom training run for every new table. Instead of fitting model weights to the user’s dataset, TabFM uses in-context learning by reading training examples and test rows together at inference time. The library provides scikit-learn-compatible classifier and regressor interfaces,... -
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.
-
5
AI Berkshire
AI-era Berkshire: a value investing research framework
AI Berkshire is an AI-assisted value investing research framework designed for Claude Code and Codex workflows. It turns the investment methods of Warren Buffett, Charlie Munger, Duan Yongping, and Li Lu into structured research agents. The project is meant to improve research depth, decision discipline, and analytical consistency compared with asking a general AI model for a one-off stock opinion. It uses parallel agent analysis, adversarial viewpoints, financial rigor checks, and... -
6
zhengxi-views
Zheng Xi (Efonda Fund Manager) Investment Research Agent Skill
zhengxi-views is a traceable investment research Agent Skill centered on the public views of Zheng Xi, a fund manager at E Fund. It is built to reduce unsupported AI answers by grounding responses in original public statements, fund reports, interviews, and documented methodology. The project organizes a corpus of Zheng Xi’s views from 2012 to 2026, then connects those materials to an extracted investment framework. It also includes real fund data snapshots for managed funds and broader fund... -
7
DeepSpec
A full-stack codebase for training and evaluating speculative decoding
DeepSpec is a full-stack codebase for training and evaluating draft models used in speculative decoding. It provides the components needed to prepare data, train draft models, and measure acceptance behavior against target models. The workflow starts with data preparation, including prompt download, target answer regeneration, and target cache construction. It then trains a draft model using configuration files for different algorithms and target model setups. The evaluation pipeline... -
8
Hy-MT2 is a family of fast-thinking multilingual translation models built for complex real-world translation scenarios. It includes 1.8B, 7B, and 30B-A3B model sizes, giving users options for lightweight deployment, stronger general performance, or MoE-based capacity. The models support translation across 33 languages and are designed to follow detailed translation instructions in multiple languages. They can handle tasks involving terminology, style, personalization, delimiters, structured...
-
9
git-remote-dropbox
A transparent bridge between Git and Dropbox
git-remote-dropbox is a Git remote helper that lets Dropbox act like a real Git remote. It provides a transparent bridge between Git and a Dropbox folder or shared Dropbox folder. After installation and login, users can clone from or push to remote URLs that use the dropbox scheme. The helper preserves traditional Git remote guarantees, including atomic behavior even when multiple people operate on the repository. It can automatically create the repository directory the first time a user... -
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
huey
A little task queue for python
huey is a lightweight task queue for Python applications. It gives developers a clean API for running background jobs outside the main request or execution flow. The project supports several storage backends, including Redis, Valkey, Redict, SQLite, the file system, and in-memory storage. It can execute tasks with processes, threads, or greenlets, which makes it adaptable to different workloads. Huey also supports scheduled tasks, recurring tasks, retries, task priorities, result storage,... -
11
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... -
12
Claude Engineer v3
Claude Engineer is an interactive command-line interface (CLI)
Claude Engineer v3 is a self-improving AI software development assistant built around Claude 3.5 Sonnet. It provides both a command-line interface and a modern web interface for coding-related workflows. 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... -
13
Hiring Agent
AI agent to evaluate and score resumes
Hiring Agent is an AI-powered resume evaluation pipeline for screening technical candidates. It reads a resume PDF and converts the content into Markdown-like text. It then uses a local or hosted language model to extract structured candidate information into sectioned JSON. The system can enrich that resume data with GitHub profile and repository signals when a profile is available. After the data is collected, it produces an explainable evaluation with category scores, supporting evidence,... -
14
ZaneOps
A self-hosted PaaS for deploying and managing web apps
ZaneOps is a self-hosted, open-source PaaS for deploying and managing applications, services, databases, workers, and static sites. It is designed as an alternative to platforms like Heroku, Railway, Render, Vercel, and Netlify while keeping ownership of infrastructure in the user’s hands. The platform uses Docker Swarm for scalable container orchestration and Caddy for flexible routing and web serving. It gives developers a polished dashboard for managing projects, deployments, logs, URLs,... -
15
PixelRAG
The beginning of scalable pixel-native search
PixelRAG is a visual retrieval-augmented generation system that searches documents by how they look, not only by the text they contain. It renders web pages, PDFs, and images into screenshot tiles, then performs retrieval over those visual representations. This approach preserves layout, tables, charts, diagrams, infographics, and other visual structure that traditional HTML or text parsing can miss. The project includes tools for rendering, chunking, embedding, indexing, and serving visual... -
16
Pycorrector
Pycorrector is a toolkit for text error correction
Pycorrector is a Python toolkit for Chinese text error correction. It focuses on common error types such as similar-sounding characters, visually similar characters, grammar issues, proper noun errors, missing words, extra words, wrong words, and word-order problems. The project implements multiple correction approaches, including KenLM, ConvSeq2Seq, BERT, MacBERT, ELECTRA, ERNIE, GPT-style models, and newer Qwen-based correction models. It is designed for use cases such as input method... -
17
HRM-Text
1B text generation model based on the HRM architecture
HRM-Text is a one-billion-parameter text generation model and pretraining framework based on the Hierarchical Reasoning Model architecture. It is designed to make foundation model pretraining more accessible by reducing compute and data requirements compared with traditional scaling-heavy approaches. The system combines hierarchical recurrent design, task-completion strengthening, and latent-space reasoning. Its training stack includes PrefixLM sequence packing, FlashAttention 3 kernels,... -
18
Dia2
TTS model capable of streaming conversational audio in realtime
Dia2 is a streaming dialogue text-to-speech model created by Nari Labs for generating conversational audio in real time. It is designed to begin producing speech before receiving the entire input text, which makes it useful for interactive voice applications. The model supports audio conditioning, allowing generated speech to follow a reference voice or conversational style more naturally. Dia2 provides 1B and 2B model checkpoints along with inference code for research and experimentation.... -
19
invisible_playwright
Anti-Detect Browser that passes every bot detection test
invisible_playwright is a stealth browser automation project that presents itself as a drop-in Playwright replacement built around a patched Firefox browser. It is designed to preserve Playwright-style automation while reducing the browser fingerprints that automated sessions often expose. The project targets advanced browser testing, AI browser workflows, and automation scenarios where normal headless browsers may be blocked or classified as bots. It includes claims about passing common... -
20
GoPay Workflow Orchestrator
Lightweight process orchestration framework for regional payment
GoPay Workflow Orchestrator is a lightweight workflow orchestration framework for studying and debugging regional payment-chain flows. 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.... -
21
SkillOpt
Text-space optimizer that trains reusable natural-language skills
SkillOpt is a Microsoft research project for improving frozen LLM agents by optimizing reusable natural-language skill documents. Instead of changing model weights, it treats a compact skill file as the trainable state of the agent. The system learns from agent rollouts, reflection, bounded edits, and validation gates to produce better instructions over time. Its output is a deployable best_skill.md artifact that can be reused across agent tasks. The project is focused on making agents more... -
22
Train LLM From Scratch
A straightforward method for training your LLM
Train LLM From Scratch is an educational PyTorch project that shows how to build and train a transformer-based language model from the ground up. It is based on the architecture described in Attention Is All You Need and is designed to make the training pipeline understandable rather than hidden behind a large framework. The repository walks through the process from downloading data to generating text with a trained model. It supports training smaller or larger models, including million- and... -
23
SmartNode
Visual simulation platform for space-based data backhaul scenarios
smartNode is a visual simulation platform for space-based intelligent relay and satellite data-return scenarios. It models the relationship between satellites, ground stations, relay links, and content-driven task scheduling. The project includes a Python backend and a browser-based frontend, making it suitable for local simulation, teaching, and secondary development. Users can view a three-dimensional space situation, submit data return tasks, and monitor resource states in real time. The... -
24
MathCode
A Frontier Mathematical Coding Agent
MathCode is a terminal-based AI coding assistant focused on mathematical formalization and theorem proving. It is designed to transform plain-language mathematical reasoning into verified Lean 4 code and formal proofs. The project combines AI agents with Lean Language Server Protocol integration, allowing it to inspect compiler feedback, search for lemmas, and iteratively repair failed proof attempts. It supports an agentic proving workflow where the system behaves more like an interactive... -
25
Meli-Action
Download files from direct links, YouTube, Telegram, Google Play
Meli-Action is a GitHub Actions-based downloading and web archiving project designed for heavily restricted internet environments. 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...
