Results for "accessibility"

Accessibility-aware PDF parser and conversion pipeline for AI-ready markdown and structured data workflows.

Safe and private runtime for autonomous AI agents with policy-driven execution boundaries and CLI integration.

Native macOS control panel for the Android Emulator and real devices with a built-in stdio MCP server (18 tools) that lets Claude Code, Codex, Cursor and VS Code see and drive the emulator. MIT licensed.

MCP server that lets AI agents automate and inspect iOS and Android simulators, emulators, and real devices through accessibility trees, screenshots, and structured device tools. Apache-2.0 licensed.

Portable sandbox execution environment for AI agents with constrained filesystem and network boundaries, designed to reduce blast radius in tool-use and LLM autonomy tests.

Open-source agent workspace for building and running AI-created apps, documents, and agents in sandboxed Cloudflare Workers with capability-based integrations and reviewable actions. Apache-2.0 licensed.

Most popular self-hosted ChatGPT-style interface.

Self-repairing CLI catalog that exposes web, desktop, Electron, and bridge tools as deterministic commands for AI agents.

Run, manage, and scale AI workloads on any AI infrastructure. Unified interface to access and manage compute across Kubernetes, Slurm, and 20+ cloud providers. Used by Shopify and research institutions for training and inference. Apache 2.0 licensed.

Git-backed platform for managing and sharing skills, tools, and context across AI agents through a remote MCP server. Apache 2.0 licensed.

Self-improving framework that orchestrates meta, target, and feedback agents to autonomously optimize the performance of AI models and agents on benchmark tasks. MIT licensed.

Agent framework for fintech and banking with built-in MCP support, guardrails, and tool server architecture.

macOS CLI & MCP server enabling AI agents to capture screenshots and automate UI interactions. Visual question answering through local or remote AI models. MIT licensed.

GNOME/Linux desktop virtual assistant with integrated file editor, global hotkeys, and profile manager.

Self-hosted ML experiment tracker designed to handle 10,000s of training runs with performant UI and SDK for programmatic access. Apache 2.0 licensed.

The most advanced embedded vector search engine for Java. DiskANN-based algorithm for billion-scale vector search with efficient memory mapping. Apache 2.0 licensed.

AI code editor built on VS Code (Code - OSS) that runs Claude Code, Codex, OpenCode and Kimi over ACP, with hunk-level keep/undo of agent edits and a Git checkpoint every turn. MIT licensed.

Open-source AI engine running LLMs, vision, voice, image, and video models on any hardware. Self-hosted OpenAI-compatible API. MIT licensed.

The de facto standard library for pretrained NLP models. 1M+ models, 250,000+ downloads/day. BERT, GPT, Llama, Qwen, and hundreds more.

NumPy and SciPy-compatible array library for GPU-accelerated computing in Python.

Unified metadata platform for data discovery, observability, and governance. Column-level lineage, semantic search, and team collaboration with 70+ data service connectors. Apache 2.0 licensed.

Semantic layer for AI-powered data analytics. Allows AI agents to describe data models and query the data using an expressive format with measures, dimensions, and filters, without writing raw SQL. MCP, CLI, API, and Python clients. Embeddable as a Python library. MIT licensed.

Large-scale language model training codebase from EleutherAI with distributed training support and historical open-model importance.

GraphQL-native vector search engine.