inAiinAi
Products / Open Source

Open Source

Useful AI tools, released in the open.

View projectsRead our Open Source approach

Open work for the intelligence era.

inAi releases selected tools, experiments, developer utilities, and local-first applications when they can be useful beyond our own work.

Some projects support agent-era development. Some explore new interfaces, media workflows, speech, conversation, or local productivity. Some are reference projects from earlier experiments that remain useful for builders who want to inspect, adapt, or learn from them.

Open Source is one of inAi's four product categories. It is not the whole company, and it is not a promise that every internal system will be public. It is a practical way to share useful work with developers, researchers, builders, and the wider AI ecosystem.

AI-native software is moving quickly. Useful tools often start as experiments, internal utilities, local workflows, prototypes, or developer infrastructure before they become polished products.

When a tool can help other builders, we prefer to release it openly rather than leave it hidden in a private folder. That does not mean every project has the same maturity. Some are active tools. Some are experimental prototypes. Some are reference utilities or legacy projects preserved because they still contain useful ideas.

Project portfolio

The portfolio is grouped by maturity so each project is easy to understand. Active tools can be used or inspected now. Experimental prototypes show directions we are exploring. Reference and legacy projects remain public because they may still be useful to developers, researchers, or builders working on similar problems.

These projects are the strongest current or current-adjacent parts of the Open Source portfolio. They are not all equally mature, but each shows a public direction in inAi’s work: agent-era developer infrastructure, wearable AI interfaces, creative workflow tooling, and speech or conversation assistance.

Active and experimental tools

These projects are the strongest current or current-adjacent parts of the Open Source portfolio. They are not all equally mature, but each shows a public direction in inAi's work: agent-era developer infrastructure, wearable AI interfaces, creative workflow tooling, and speech or conversation assistance.

Reference utilities

Some Open Source work is not meant to be a flagship product. It is still useful because it captures practical local workflows, utilities, and small tools that developers or operators may want to inspect, adapt, or reuse.

Legacy and reference projects

Legacy projects are kept public because they preserve useful ideas, implementation patterns, or earlier experiments. They should not be read as current flagship products. They remain part of the portfolio because public reference work can still help builders understand how ideas evolved.

  1. Active

    A local MCP control plane that routes ChatGPT context into local Codex workers. PatchBay lets ChatGPT open approved repositories, brief durable named workers, pass generated files and reports into local work, inspect worker diffs and integration previews, and apply accepted work without turning the user into a copy-paste bridge. It supports Streamable HTTP and stdio MCP transports, worker-first tool modes, workspace context, artifact inboxes, isolated writing worktrees, repo mutation locks, token-gated tunnel setup, and explicit power boundaries. This is the strongest public bridge between inAi's Open Source portfolio and Products for Agents: software that makes AI-assisted workflows more local, inspectable, coordinated, and reviewable.

    View on GitHub

  2. Experimental Prototype

    A host-first operating-surface prototype for wearable AI. PrismOS is an experimental operating-surface project for Brilliant Labs Monocle hardware. The host device owns app state, layout, provider calls, persistence, diagnostics, recovery, and bounded display output, while the Monocle stays closer to a thin display, input, and media endpoint. It explores compact AI-assisted apps and interface patterns for hardware-adjacent workflows, including concepts such as Oracle, Vision, Signal, Chronos, Teleprompter, Babel, and Gallery-style experiences. PrismOS shows that AI-native products do not have to live only in web dashboards or chat windows.

    View on GitHub

  3. Active

    A desktop workspace for large image-generation runs. ImageAI Batch Generator is a desktop workspace for managing larger image-generation workflows. It supports prompt imports, shared settings, per-row overrides, queueing, throttling, retries, cancellation, autosave, export metadata, and offline mock generation. It is designed for the moment when image generation moves beyond one prompt at a time and becomes a repeatable workflow that needs structure, tracking, retries, and operational control.

    View on GitHub

  4. Experimental

    A local tool for live transcription, translation, and conversation assistance. WhisperMind is an experimental local app for live microphone transcription, translation, and conversation assistance. It includes desktop and web-interface variants around speech, translation, and realtime conversation workflows. The project explores how AI can support live communication: not only by answering prompts, but by helping people understand, translate, and respond in the flow of conversation.

    View on GitHub

  5. Reference Utility

    A local toolbox for documents, files, OCR, tokens, and small AI workflows. AdditionalApps is a local desktop toolbox made from older practical utilities. It includes document, PDF, OCR, table, file-management, filename, video-organization, token-counting, and small AI-assisted text or code workflows behind a local launcher. It is a reference utility suite rather than a flagship product, but it preserves useful local tooling for builders working with files, documents, and small workflow problems.

    View on GitHub

  6. Legacy Prototype

    An older prototype for building and running multi-step AI workflows. ChainerAI is an older prototype for composing multi-step AI pipelines. It includes a backend, frontend, saved chains, ordered prompt/model steps, persistence, login, containerized setup, and provider-adapter-style workflow ideas. It is not presented as a current flagship product. It remains public as a legacy prototype and reference point for AI workflow composition.

    View on GitHub

  7. Legacy

    A lightweight local browser UI for one configured assistant. ChatGPT Assistants UI is a small local Flask interface for chatting with one configured Assistants API assistant. It stores local chat metadata and provides a simple browser-based interface for creating, renaming, selecting, and deleting chats. It is preserved as a legacy reference project: simple, focused, and useful mainly as an example of an earlier local assistant interface.

    View on GitHub

Use, inspect, contribute, or collaborate.

Open Source work is useful when people can read it, run it, learn from it, and improve it. If a project is useful to you, start with the repository: read the README, inspect the code, open an issue where appropriate, or contribute through the normal GitHub workflow.

For broader collaboration, research, product, or partnership conversations around Open Source work, contact inAi through the relevant collaboration route.

Each repository includes its own license and usage details on GitHub.

View GitHubContribute on GitHubContact about collaboration

How Open Source connects to inAi

Open Source is one part of inAi's broader product architecture. Business products focus on companies and industries. Consumer products focus on personal workflows. Products for Agents focus on software that agents can discover, call, and use. Open Source lets inAi release selected tools and experiments that may help the wider ecosystem.

AGI as a System

Read inAi's stance on general intelligence as systems of models, agents, tools, memory, execution, coordination, feedback, and environment.

Read the stance

AI for Everybody

AI should be understandable beyond technical circles. AI for Everybody explains AI, agents, risk, work, and public questions in accessible language.

Read AI for Everybody

Trust

Open work is one part of trust. It does not mean every internal system is public, but it shows selected tools, experiments, and utilities in the open.

How we build