privacy

A Java library for adding privacy and security guardrails to Spring AI apps, including PII tokenization, tool authorization, and content inspection.

Hob is an open-source desktop AI assistant that runs locally on Mac, Windows, and Linux. It positions itself as a private, offline alternative to ChatGPT and Claude, with support for open-weight models like Gemma and gpt-oss.

A local transcription studio for Windows and Linux that turns recordings into editable text, with speaker labels, translation, searchable transcripts, export formats, and optional AI research prompts.

A native Mac app that lets you type @@ in any editable field to talk to your AI agent, with screen, clipboard, and Finder context. It also includes TabTab autocomplete, clipboard history, screenshots, and screen recording.

A browser extension that lets users move AI chat threads between ChatGPT, Claude, and Gemini without retyping. It supports exporting/importing local .chatbridge files and emphasizes browser-only, local-first handling.

TokenMaxxer is a CLI-based AI usage tracker for developers that reads token counts from tools like Claude Code, Codex, Cursor, and others, then shows spend, model usage, and a public leaderboard. It emphasizes local-only reads and opt-in sharing.

SKI is a Mac and Windows voice assistant for AI coding agents. It lets developers talk to tools like Claude Code, Cursor, Codex, Gemini CLI, and OpenClaw, and hear replies spoken back locally on-device.

A local-first browser extension that captures a ChatGPT or Claude conversation, summarizes it into a portable handoff, and helps continue the chat in another AI in one click.

An iOS productivity app for offline speech-to-text, AI-assisted dictation, meeting transcription, and summaries. It runs on-device, supports multiple languages, and includes keyboard-based writing tools plus exports and integrations.

Open-source agent skill and Python service for stripping AI provenance marks from text and files. It supports multiple hosts, includes install scripts, hooks, and a service-backed workflow for cleaning watermarks across many file types.

PrivateRedact is a local-first PII redaction app that uses regex plus a local LLM to detect sensitive information in documents, then lets you review and export redacted files without sending data to the cloud.

Chrome extension that saves AI chat answers locally, adds tags, and lets users search and reopen them later.

A Mac menu bar app that tracks Claude Code activity locally, including prompts, lines of code, active time, breaks, tokens, and costs.

A browser-based FPS aim trainer that uses coaching, telemetry, and replays to help improve mouse control and tracking.

A local CLI for replaying what AI coding agents accessed on your machine, including file reads, secrets that entered context, and possible read-then-network-call exposure paths. It also scans exported ChatGPT, Claude, and Gemini histories for sensitive data.

UnderstandDocs is a document analysis tool that summarizes pasted text or uploaded files, flags risks, extracts important dates, and simplifies dense language. The page shows a working analysis form, supported file types, a privacy/no-storage claim, and an example output for a tenancy agreement.

SnapName is a macOS app that watches a screenshot or image folder and uses bundled local AI to suggest better filenames without uploading images.

Cockpit is a free local macOS app for managing Claude Code and Codex sessions in one window. It shows which sessions need attention, lets you start new runs, organize many sessions, review transcripts, and inspect file/version history without sending data off your Mac.

A macOS menu bar app that shows remaining Claude 5-hour and weekly usage limits locally, without reading tokens or calling an API.

Local Windows app that converts, sanitizes, and indexes documents before they reach an LLM. It removes sensitive data on-device, creates searchable Markdown/CSV outputs, and supports both personal and business editions.

A Mac-native menu bar app that tracks AI token usage, shows spend by model, and pops up break reminders when usage crosses configurable thresholds.

wavecat is a fully local personal agent that watches your screen and runs entirely on-device. The page explains its privacy focus, hardware requirements, local model setup, and supported platforms.

Local-first encrypted memory engine for AI agents, built in Rust with MCP support and persistent cross-session memory for Claude and other MCP clients.

A member-governed AI inference service with chat, a developer API, and governance features. The site highlights sliding-scale membership, monthly usage credits, OpenAI-compatible access, and options focused on privacy, renewable energy, and publicly developed models.