Cherry is the self-hosted alternative to You.com.
You.com layered chat modes (Smart, Genius, Research and Agent) on top of a search engine, then kept reshaping the surface every product cycle. Cherry is an operator-first workspace built for teams that need stability, reproducibility and cost attribution across dozens of concurrent projects. Same multi-provider routing (OpenAI + Anthropic shipping, more on roadmap), plus infinite nested folders, the Pins/Clipboard/Snippets three-tier reuse system, per-message UsageEvent logging and private MinIO storage. Self-hosted end to end. You own the whole stack.
Three places the mode-switching search box breaks down.
You.com is a consumer search product with AI modes stapled on. Fine for a curious query. Not built for a professional running two dozen concurrent client threads.
Mode switching is the interface
You.com asks the user to pick Smart, Genius, Research or Agent before every query. Cherry inverts it. Cherry ships one workspace, one input, a first-class Agent Library of Presets and a Compare modal that fires one prompt at multiple models side by side. The model choice is a Preset, not a mode-select modal.
Search-first, workspace-last
You.com organizes around a search page. Cherry organizes around a workspace with infinite nested folders, Pins on individual messages, a drag-reorderable per-chat Clipboard and project-wide Snippets with tags. Global search runs in parallel across every chat, snippet, file, folder, pinned message and clipboard item, ranked.
No per-prompt cost visibility
You Pro bills flat. There's no per-prompt attribution. Cherry logs a UsageEvent on every message with tokens in, tokens out, dollar cost and latency attributed to user, workspace, chat and model. The Recharts dashboard filters by today, 7 days, 30 days or billing cycle. Consultants can attribute AI spend per client engagement in a single query.
An operator's workspace, not a search bar wearing chat modes.
Cherry inverts the You.com pattern. Instead of picking Smart, Genius, Research or Agent before every query, you pick a Preset once from the Agent Library and reuse it across chats. Instead of aggregating models opaquely, Cherry names the exact model on every response. Instead of billing flat and hiding per-prompt cost, Cherry logs tokens, dollars and latency on every message. And instead of a search page with chat stapled on, Cherry ships folders, Pins, Clipboard, Snippets and a Compare modal built for a real working day.
You.com vs Cherry.
A stable operator workspace versus a mode-switching consumer search product.
| Feature | You.com | Cherry |
|---|---|---|
| Model providers | Multi-provider (opaque routing per mode) | OpenAI + Anthropic shipping, named on every response |
| Interface pattern | Mode select before every query | One workspace, Presets in the Agent Library |
| Product surface | Search-first, chat modes stapled on | Workspace-first with a data model behind it |
| Organization | Flat chat list | Infinite nested folder tree, self-referential parents |
| Per-message bookmarks | No | Pins with scroll-to-highlight animation |
| Per-chat clipboard | No | Drag-reorderable saved passages, promote to Snippet |
| Cross-chat snippets | No first-class equivalent | Project-scoped, tagged, one-click injection to any chat |
| Model presets | Custom Agents | Agent Library. Presets with model + temp + system prompt + tier |
| Model comparison | Not first-class | Fire one prompt at multiple models side by side |
| Cost per prompt | Not shown | Tokens in, tokens out, dollar cost, latency on every message |
| Cost attribution | Flat subscription | Per user, per workspace, per chat, per model |
| Usage dashboard | None for end users | Recharts. Today / 7d / 30d / billing cycle |
| Bulk folder upload | No | Replicates an entire OS folder tree transactionally |
| File storage | You.com infrastructure | Self-hosted MinIO with local-disk fallback, presigned URLs |
| Conversation history | Vendor-owned | Your Postgres. Exportable, portable |
| Streaming transport | Proprietary | Server-Sent Events with cancel-mid-stream |
| Team workspaces | You Business | Multi-workspace with Owner / Admin / Member roles |
| SSO | Enterprise only | Available in Enterprise, configurable on your infrastructure |
| Keyboard shortcuts | Limited | 18 mapped across Navigation / Chat / Editor / Files |
| Connectors | Limited catalog | GitHub + Google Drive shipping, Notion / Slack / Jira on roadmap |
| Apps | Agents | Canvas, Code Interpreter (beta), Image Generation, modular |
| Outbound API | Search API only | Cherry outbound API for third-party integration |
| Deployment | SaaS only | Self-hosted. On-prem, cloud, run as your own SaaS. You decide |
| Ownership | Vendor-owned | You own the code, the data, the deployment |
Frequently asked questions.
Does Cherry do search grounding like You.com?
Cherry treats search as a pluggable capability, not the whole product surface. The provider abstraction is a typed interface, so wiring a search-grounded provider (You.com's own search API, Perplexity Sonar, Brave, Kagi, others) is a single-file adapter addition. Meanwhile the workspace primitives (folders, Pins, Clipboard, Snippets, UsageEvents) stay stable across whichever search provider you choose.
What replaces You.com's mode selector?
The Agent Library. A Preset captures the model, temperature and system prompt, and any Preset can be filtered to a specific tier requirement. Pick a Preset once, use it across chats. Model choice is a first-class configuration, not a modal to click through before every prompt.
How granular is cost tracking?
Every message generates a UsageEvent record with tokens in, tokens out, dollar cost, latency in ms, model, preset, chat, user and workspace. The Recharts dashboard filters by today, 7 days, 30 days or billing cycle and shows a daily cost bar chart, breakdown by user / model / chat and storage growth in GB.
Where do uploaded files live?
Files live in MinIO on your infrastructure, with a local-disk fallback if MinIO isn't wired. The storageKey is stored in the File record. The raw bucket path is never exposed. Every file access goes through a short-TTL presigned URL generated per request. Filenames are sanitized. If you shut Cherry down tomorrow, the files stay in your bucket.
How does Cherry stream responses?
Cherry streams via Server-Sent Events over HTTP. Every provider adapter implements the streaming interface, so tokens appear the moment the model emits them. The Stop button cancels mid-stream. SSE is a standard browser API. There's no proprietary transport.
How is Cherry deployed?
Cherry is self-hosted. Docker Compose orchestrates nginx, the Next.js frontend, the Express backend, Postgres, Redis and MinIO. Deploy it on your own hardware for internal use, run it in your cloud or spin it up as your own SaaS product. You own the code, the data and the deployment.
What does Cherry cost?
Contact sales for pricing. Every engagement is scoped to how you plan to deploy, who your users are, which provider adapters you need lit up and what support terms fit your organization.
Ready to work in a workspace instead of a search box?
Tell us how your team uses You.com today, which modes you actually rely on and where the mode-switching starts costing you. We'll respond within one business day with an honest read on whether Cherry fits.