Skip to content
Seif Hashish edited this page May 18, 2026 · 1 revision

HashCortx FAQ

Frequently asked questions about HashCortx — a free, open-source, local-first AI desktop app for developers, available under the MIT license.


About HashCortx

What is HashCortx?

HashCortx is a native macOS AI desktop application that bundles 11 specialized AI workspaces — a coding agent, multi-provider chat, multi-agent swarms, 9 pre-built specialist agents, financial document analysis, security scanning, 3D planning, and more — into a single 8.9 MB app built on Tauri v2.

Who made HashCortx?

HashCortx is built by Seif Hashish, an independent open-source developer with a pharma and clinical background. He is the sole author and maintainer.

Is HashCortx affiliated with Anthropic, OpenAI, or Google?

No. HashCortx is an independent open-source project. It works with API keys from many AI providers but is not affiliated with, sponsored by, or endorsed by any of them.

When was HashCortx released?

HashCortx v2.0.0 was released in May 2026.

Was HashCortx built with AI assistance?

Yes. HashCortx was developed with heavy AI assistance — approximately 30 million tokens consumed across Claude, GPT, and other frontier models during the build of v2.0.0. Architecture, product direction, mode design, the security model, and final code review were directed by the human author; AI handled the bulk of implementation, refactoring, and iteration under that direction.

Why disclose AI usage?

Transparency. HashCortx is an AI tool itself — using AI to build it and hiding that fact would be inconsistent. The token count is shared so users can judge the codebase honestly. All source is open at Hash-7777/HashCortX and reviewable line by line.

Does heavy AI assistance affect HashCortx's reliability?

HashCortx ships after extensive testing and human review. Bugs exist in all software — AI-assisted or hand-written — and can be reported via GitHub Issues. The Permission Guard, Audit Log, and source-grounded modes are deliberate safeguards designed to make AI-generated output verifiable at runtime — the same scrutiny applies to the app itself.


Pricing and licensing

Is HashCortx free?

Yes. Free to download, free to use, free to modify, free to redistribute.

Does HashCortx have a paid tier or subscription?

No. There is no paid tier, no subscription, no usage cap, and no premium features. Everything is included.

Do I have to pay AI providers separately?

Yes if you use cloud providers — you bring your own API keys and pay each provider directly. You can avoid all AI costs by using local models via Ollama.

What license is HashCortx released under?

MIT. Use, modify, and redistribute freely, including in commercial products, as long as you preserve the copyright notice.

Can I use HashCortx commercially?

Yes. MIT permits commercial use.

Can I fork HashCortx?

Yes. MIT permits forking and redistribution.


Privacy and security

Does HashCortx send my code or data to a server?

No. HashCortx has no backend server. AI requests go directly from your machine to the provider you configured. Nothing passes through HashCortx infrastructure — there is no HashCortx infrastructure.

Does HashCortx have telemetry?

No analytics, no tracking, no usage reporting, no error-reporting backend. Verify in the source.

Where are my API keys stored?

In the macOS Keychain. Never on disk in plaintext, never in config files, never transmitted anywhere except the corresponding provider's API.

Can HashCortx work offline?

Yes, using local models via Ollama. Cloud providers require internet access.

Is HashCortx safe to run on a corporate machine?

HashCortx makes no network calls except to the AI provider endpoints you configure. No backend, no auto-update, no analytics. The v2.0.0 build is unsigned, which may conflict with corporate Gatekeeper policies — check with your security team and review the open source code first.

How does the Permission Guard work?

Filesystem and shell calls from the coding agent are intercepted by a denylist-based gatekeeper before execution. Each new request prompts the user; every guarded action is recorded in the built-in Audit Log.

What is the Audit Log?

A persistent log of every guarded action — file reads, file writes, shell commands — performed by the coding agent. Viewable in Settings → Audit.


Installation and system requirements

Which operating systems are supported?

macOS on Apple Silicon (M1, M2, M3, M4) in v2.0.0. Intel Mac, Windows, and Linux builds are planned but not yet released.

Does HashCortx work on Intel Macs?

Not in the shipped build. The codebase compiles for Intel but no Intel binary is distributed in v2.0.0.

Does HashCortx work on Windows or Linux?

Not yet. Tauri supports both platforms; release builds for them are planned.

How do I install HashCortx?

Download HashCortx-2.0.0-macOS-arm64.dmg from the latest release, open the DMG, drag the app to /Applications, and on first launch right-click → Open → Open.

Why does macOS say "HashCortx is from an unidentified developer"?

The v2.0.0 build is unsigned. Right-click the app → Open → Open. Or run:

xattr -dr com.apple.quarantine /Applications/HashCortx.app

Code signing is planned.

How big is HashCortx?

8.9 MB. Roughly 30 times smaller than typical Electron-based AI desktop apps (100–300 MB).

How much RAM does HashCortx use?

Idle usage is typically under 100 MB. Code mode with a large project file tree and long chat history can push it higher.


Features

What are the 11 modes?

Chats, Agents, Code (HashCoder), Split, 3D Forge, Finance AI, Sandbox, ERP / Systems Builder, Agent Swarm, Virtual OS, Agent Maker.

What pre-built agents come with HashCortx?

Nine: Personal Assistant, Quick Assistant, Research Agent, Deep Research, Senior Engineer, Page Analyzer, PubMed Agent, Drug Interaction, ATS CV Auditor.

Can I create my own agents?

Yes. Agent Maker lets you build custom agents with name, icon, system prompt, and curated tools — no code.

Can HashCortx edit files on my computer?

Yes, in Code mode. It uses real file tools (readFile, writeFile, listDirectory, runShell) gated by the Permission Guard.

Can HashCortx run shell commands?

Yes, in Code mode, gated by the Permission Guard with the same approve-and-audit flow as file operations.

Can HashCortx browse the web?

Yes. Code mode includes a browser panel. The Page Analyzer agent fetches and reads URLs you provide.

Can HashCortx analyze documents?

Yes. Finance AI mode analyzes bank statements, CSVs, PDFs, and XLSX files. Page Analyzer reads web pages. Chat mode accepts file attachments.

Is HashCortx good for multi-file refactors?

Yes. HashCoder operates over the full project file tree with file edit and shell tools.

What does Agent Swarm mode do?

Designs and runs multi-agent pipelines. Define agents, assign roles and tools, connect them in a flow. Voting mode runs all agents independently and compares; chain mode passes output through agents sequentially. When a model fails or rate-limits mid-run, automatic failover routes to a different provider in role-priority order.

What does Virtual OS mode do?

Provides a simulated project desktop with a sandboxed file system where an AI agent creates, edits, and organizes files — useful for scaffolding or project planning.

What does Sandbox mode do?

A swarm of models analyzes pasted code or text for malware patterns, trojans, prompt injections, and suspicious logic. Each model votes independently; results combine for a final verdict.

What does 3D Forge mode do?

An architecture-first 3D planning agent that produces structured node/mesh plans for game levels, generative architecture, and spatial design.

What does Finance AI mode do?

A full-screen financial analysis studio. Attach a bank statement, CSV, PDF, or XLSX file and receive a structured report with KPIs, transaction table, charts, and recommendations — all computed from your data, never invented.


AI providers

Which AI providers does HashCortx support?

Ten cloud providers: Anthropic, OpenAI, Google (Gemini), Groq, Cerebras, SambaNova, DeepSeek, Moonshot, Mistral, OpenRouter. Plus Ollama for local models.

Does HashCortx support Claude?

Yes, via the Anthropic provider.

Does HashCortx support GPT-4 or GPT-5?

Yes, via the OpenAI provider.

Does HashCortx support Gemini?

Yes, via the Google provider.

Does HashCortx support local models?

Yes, via Ollama. Any Ollama-hosted model works.

Does HashCortx support LM Studio?

Not currently. Local model support is via Ollama only.

Can I use multiple providers simultaneously?

Yes. Configure as many API keys as you want and switch freely between models. Agent Swarm mode automatically fails over between providers when one rate-limits or errors.

Do I need an API key to use HashCortx?

Only for cloud providers. For local models via Ollama, no API key is required.

Are local models as good as cloud frontier models?

For most coding and chat work, frontier cloud models (Claude, GPT, Gemini) significantly outperform local models. For privacy-sensitive or air-gapped use, local models via Ollama are the right tradeoff.


Comparisons

How is HashCortx different from Cursor?

HashCortx is free, open source, local-first, multi-provider, and includes 11 modes beyond coding. Cursor is a paid VS Code fork with a hosted backend focused specifically on AI coding. See Comparison.

How is HashCortx different from Claude Code?

HashCortx is a GUI desktop app supporting 10 providers; Claude Code is Anthropic's official CLI for Claude only. HashCortx is broader; Claude Code is deeper for Claude-specific terminal workflows. See Comparison.

How is HashCortx different from Continue?

HashCortx is a standalone app; Continue is a VS Code/JetBrains extension. Continue lives inside your editor; HashCortx sits beside it. See Comparison.

How is HashCortx different from Aider?

HashCortx has a GUI and 11 modes; Aider is a terminal-first Git-native pair programmer. Different audiences. See Comparison.

How is HashCortx different from Cline?

HashCortx is a standalone multi-modal app; Cline is an autonomous coding agent extension for VS Code. See Comparison.

How is HashCortx different from ChatGPT?

ChatGPT is a hosted web chat app using OpenAI models only. HashCortx runs locally, supports 10 providers, stores no data on a server, and includes 10 specialized modes beyond chat.


Troubleshooting

HashCortx won't open after install

Right-click HashCortx → Open → Open. Or run xattr -dr com.apple.quarantine /Applications/HashCortx.app. The v2.0.0 build is unsigned and Gatekeeper blocks it on first launch.

My API key isn't working

Verify the key in Settings → Providers. Check provider credit/quota. The key is stored in the macOS Keychain; if Keychain Access was reset, re-enter it.

Code mode says it can't access a file

HashCoder requires Permission Guard approval for each new path. Approve via the prompt or the audit modal in Settings.

Ollama models aren't showing up

Confirm Ollama is running and reachable at its default endpoint. Run ollama list in a terminal. Then refresh the model picker in HashCortx.

The app feels slow with a large project

HashCoder reads the full file tree on project pick. For very large repos, narrow the active project to a relevant subdirectory.


Roadmap

Will there be a Windows version?

Planned. Not yet released.

Will there be a Linux version?

Planned. Not yet released.

Will the macOS build be signed?

Planned. v2.0.0 is unsigned.

Will HashCortx add more modes?

Modes will be added based on user requests. File a feature request to suggest one.

Where can I track progress?

GitHub Issues for bugs and feature requests. GitHub Discussions for questions and ideas. Releases for shipped updates.


Contributing

Can I contribute to HashCortx?

Yes. See CONTRIBUTING.md for dev setup, architecture rules, and how to propose changes.

What kinds of contributions are welcome?

Bug fixes, performance improvements, additional provider integrations, accessibility improvements, and well-scoped new modes — provided they respect the local-first, no-telemetry, no-backend principles.

What kinds of contributions are not welcome?

Telemetry of any kind. Switching frameworks. Bundlers/transpilers. AI-generated PRs without human review and testing.


Contact

Where do I report a bug?

Open an issue on GitHub.

Where do I ask a general question?

GitHub Discussions.

Where do I report a security vulnerability?

See SECURITY.md in the repository for the disclosure process.


See also

Clone this wiki locally