Get This Tool
Afair
Summary
Every new AI chat starts with the same blank slate — no memory of your preferences, your projects, your team, or the context you explained three days ago in a different tool.
afair is an open-source memory layer that sits between you and every AI tool you connect, reading context you have shared and writing it back as structured, queryable memory — so Claude, ChatGPT, Cursor, and whatever ships next all start informed. It speaks MCP, so any MCP-compatible client can read and write without custom integration work. The vault is single-tenant by design: one machine, one user, encrypted at rest with SQLCipher and AES-256-GCM. The tool is self-hostable under AGPLv3; hosted managed infrastructure is listed as coming soon but is not yet available. Teams that need cross-user shared memory, org-level context, or a REST API will find none of those here.
Bottom line: Pick afair if you switch between three or more AI tools daily and want your personal context to follow you without re-explaining it — but plan elsewhere if your use case is team-shared memory or any environment that lacks MCP client support.
Hosted & API Pricing
The model is free to self-host. These are the creator's hosted/API options.Hosted
Managed single-tenant machine in Germany with backups and export handled
- Claude.ai and ChatGPT integration
- No setup
- Cancel anytime
Pricing may have changed since last verified. Check the official site for current plans.
Pricing Plans
Subscription- Price
- €10/month (hosted, coming soon)
Self-host
Run AGPLv3 open-source code on your hardware
- Full vault control
- No vendor involvement
Hosted
Managed single-tenant in Germany, backups and export handled
- No setup required
- Cancel anytime
View full pricing on afair.ai →
Pricing may have changed since last verified. Check the official site for current plans.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- MCP-native design means any MCP-compatible AI tool can read and write to the same vault without custom glue code, so adding a new AI client does not require rebuilding your context setup.
- Single-tenant architecture with per-user dedicated storage, so your memory data is never co-mingled with another user's in a shared database — which matters when what you are storing includes personal and professional context.
- Human-readable, correctable vault structure, so when afair extracts something wrong you open the data, fix it, and move on rather than chasing a black-box embedding you cannot inspect.
- Full vault export to a single file at any time, which means switching off afair or migrating to a different setup does not strand your accumulated context behind a proprietary format.
- AGPLv3 open-source core with self-host support, so teams with strict data residency requirements can run the full stack on their own hardware without waiting for a managed offering.
Cons
Sign in to edit- No API surface exists: any application that needs to read or write memory programmatically outside an MCP client is blocked entirely, and teams building custom integrations will need to wait for or fork toward an API layer that does not exist.
- The self-hosted version calls external APIs from Anthropic, OpenAI, and Google for extraction and ranking — teams expecting a fully local or air-gapped deployment will find the tool does not meet that requirement without significant modification.
- There is no team or org-level memory model; the single-tenant design is a hard architectural constraint, so any team that needs shared context across multiple users will abandon this for a solution that supports multi-user memory from the start.
- The managed hosted service the vendor describes is not yet available, so users who cannot self-host have no path to onboard until that infrastructure launches — and no timeline is stated on the vendor page.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- Self-hosted on user machine; MCP clients
- API Available
- No
- Self-Hosted
- Yes
- Last Updated
- 2026-07-03T03:18:29.553Z
Best For
Who it's for
- Users switching between Claude, ChatGPT, Cursor, and similar tools
- Individuals wanting full control over personal AI memory data
- Developers seeking an open-source MCP-compatible memory layer
What it does well
- Maintaining consistent personal and work context across multiple AI chat tools
- Avoiding repeated explanations of preferences, family, or projects to different AIs
- Self-hosting a private memory store for AI interactions
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare Afair
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is Afair free?
- Afair has a permanent free tier alongside paid upgrades (paid plans from €10/month (hosted, coming soon)). You can keep using a baseline version indefinitely without paying.
- Is Afair open source?
- Yes. Afair is open source.
- Can I self-host Afair?
- Yes. Afair supports self-hosting on your own infrastructure.
- What platforms does Afair support?
- Afair is available on: Self-hosted on user machine; MCP clients.
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
You re-explain yourself to every AI you open. Your working style, your project names, your family — every tool starts fresh, and you pay the tax in repeated context-setting. afair addresses this by acting as a passive memory store that connects to your AI tools over MCP. As you have conversations, afair extracts relevant facts, ranks them, resolves entities across sessions, and keeps a structured vault. The next tool you open reads from that vault automatically. You never manually file anything.
The vault’s architecture is the differentiating design choice. It is single-tenant by definition — one machine per user, never a shared database. Encryption runs at the database layer via SQLCipher and at the file layer via AES-256-GCM, and decryption requires your key. The vendor states the structure afair builds is human-readable data you can open, inspect, and correct yourself. Nothing is hidden in model weights. When the extraction logic gets something wrong, you fix it. The full vault exports to a single file at any time.
This fits one profile well: an individual switching between Claude, ChatGPT, Cursor, Codex, or Perplexity who wants personal context to persist without vendor lock-in. It breaks down quickly outside that profile. There is no API, so any application that needs to read your memory programmatically rather than through an MCP client is blocked. There is no multi-user or team memory model — the architecture is explicitly single-tenant. The managed hosted option the vendor describes is not yet live.
On the integration side, the vendor states afair connects to Claude.ai, ChatGPT, Perplexity, Claude Code, Cursor, Codex, and Warp through MCP. Three models from Anthropic, OpenAI, and Google are used internally for extraction and ranking — meaning the self-hosted version still calls external model APIs rather than running inference locally. Teams expecting a fully air-gapped deployment need to account for that dependency.