general
Default project
Describe your project.
It comes back done.
MindsHub is the unified workspace where AI models like
Kimi
get work done for you — apps, reports, tasks and more.
Let's knock things off your list
Model: latest:sonnet
Build an interactive KPI app the team can explore
Build me an interactive app the team can use to explore our KPIs — MRR, signups, NRR — pulling live from Postgres and Stripe. If something looks off with signups, let us open a Linear ticket and assign it right from the app. Publish it so the team can dig in.
PgPostgreSQLSStripeLLinear
- Planned the analysis3 KPIs · live refresh · drill-down by segment
- Connected to PostgreSQLvia the credentials vault — no raw key exposed
- Queried Stripe for MRR & signups1,204 subscriptions reconciled
- Wired up Linear for one-click assignmentissues created straight from flagged rows
- Published kpi-app.htmllive, shareable URL
Done — here's your KPI app. MRR is up +9.4% week-over-week to $128.4k. One thing worth a look: signup checkout is erroring for EU accounts — I flagged it below so someone can grab it.
Top customer-feedback themes, ranked by revenue
Combine last month's Gong calls, Zendesk tickets, and HubSpot notes into the top customer-feedback themes — and rank them by revenue impact, not just frequency.
GGongZZendeskHHubSpot
- Pulled 42 Gong call transcriptsMay 1 – May 31
- Read 318 Zendesk ticketsplus 96 HubSpot deal notes
- Clustered into 7 themessemantic grouping + dedupe
- Scored each theme by attached ARRcross-referenced HubSpot deals
- Wrote the memofeedback-themes.md
Here's the May feedback memo. Ranked by revenue, the #1 theme is onboarding friction — 28 mentions across $214k of ARR, well ahead of where raw frequency would rank it. Pricing confusion and a missing Salesforce sync round out the top three.
Extract 38 receipts into a Q2 expense workbook
Extract these 38 receipts from the shared Drive folder and build a categorized Q2 expense workbook with monthly totals. Flag anything that looks like a duplicate.
△Google Drive
- Read 38 receipts from Google DriveOCR on PDFs and photos
- Normalized vendors & currencies3 currencies → USD
- Categorized into 12 bucketssoftware, travel, meals, …
- Flagged 2 likely duplicatessame vendor, amount, ±1 day
- Built expenses.xlsx3 sheets, formulas intact
Built expenses.xlsx — 38 receipts totaling $24,318 across 12 categories. Software is the biggest line at $9,240. I flagged 2 duplicate charges ($318) for your review on the Summary tab.
Daily 7am briefing across Slack, Gmail, Calendar, Linear
Every weekday at 7am, scan Slack, Gmail, my Calendar, and Linear, and give me a priority briefing before my first meeting — what changed overnight and what needs me.
#SlackMGmail31Google CalendarLLinear
- Scanned 6 Slack channelsovernight messages + mentions
- Triaged 23 new emailsurgent vs. FYI
- Read today's calendar5 meetings, 2 need prep
- Checked Linear4 issues moved to your review
- Scheduled the recurring runweekdays · 7:00 AM
Scheduled ✓ — I'll run this every weekday at 7:00 AM and drop the brief here. Today's headline: 3 things need you before 10am. Acme is waiting on your reply, the pricing doc needs sign-off, and your 9:30 needs 5 minutes of prep (notes attached).
Size the US SMB-analytics market and compare vendors
Size the US SMB analytics market, compare the top vendors by price and ICP, and build me a shareable briefing I can send to the team.
BQBigQuery
- Researched 14 market sourcesreports, filings, pricing pages
- Modeled TAM / SAM / SOMbottoms-up by segment
- Compared 8 vendorsprice, ICP, and gaps
- Compiled a sourced appendixevery number cited
- Built market-sizing.htmlpublished, shareable
Here's the market-sizing briefing. TAM $18.4B, SAM $6.2B, three-year SOM $430M. I compared eight vendors — the clearest wedge is sub-50-seat teams that enterprise BI tools price out and overserve.
Projects
Group work, set instructions, and keep its data and artifacts together.
Q2-Reporting
Board metrics & dashboards
Revenue-Ops
GTM signal & feedback
Scheduled Tasks
Cowork runs these on the cadence you set, then drops the results in the task.
Live Artifacts
Documents, dashboards, and apps Cowork produced. Publish to share a live URL.
5 artifacts
Connected Apps & Data
Connect a source once. Secrets go into a vault, scoped per connection — the agent never sees a raw key.
Connected
Pg Connected
S Connected
M Connected
# Connected
31 Connected
L Connected
Available — featured
Memory
Rules, lessons, and saved context Cowork can reuse — yours to inspect and edit.
Global 1
Project · general 2
Select a memory file to inspect it.
lessons.md global
— Always reconcile Stripe MRR against the subscriptions table before reporting; they drift by ~2%.
— The boss prefers numbers first, then the narrative. Lead with the headline metric.
— Publish dashboards as live URLs by default — the team shares links, not screenshots.
lessons.md project · general
— Fiscal quarter starts in February, not January. Q2 = May–Jul.
— "North-star" metric is NRR; report it on every dashboard.
rules.md project · general
— Never write to production databases. Read-only credentials only.
— Currency is USD. Convert at the receipt date's rate.
Skill Library
Teach a skill once; Cowork recalls it when the work fits — no relearning.
Settings
Cowork configuration and workspace preferences.
Providers
•••••••••••••••••• Connected
Agent models
latest:sonnet
Reasoning effort
High
latest:haiku
Reasoning effort
High
Agent harness
Appearance
POSTGRES + STRIPE + LINEAR · LIVE
Growth KPI App
Live · updating now
MRR
$128.4k
▲ 9.4% WoW
New signups (24h)
412
▲ 6.0%
Churn
2.1%
▲ 0.3 pt
Net revenue retention
112%
— flat
Signups per hour, last 48h — click a red dot to explore
65/hr
Signup error
Requests per minute
842/min
Recent signups
- Fenwick & Co.Scale planjust now
- Rivet LabsTeam plan2 min ago
- Halden GroupCheckout error · EU6 min ago
- Norra SystemsStarter plan11 min ago
RESEARCH · 14 SOURCES
US SMB Analytics — Market Sizing
Published · shareable
TAM$18.4BAll US SMB analytics spend
SAM$6.2BSelf-serve, < 200 seats
SOM$430MReachable in 3 years
Vendor comparison
| Vendor | Entry price | ICP | Gap |
|---|---|---|---|
| Enterprise BI A | $70k/yr | 2,000+ seats | Overserves SMB |
| Dashboard SaaS B | $24/mo | 10–50 seats | No warehouse |
| Notebook tool C | $0 OSS | Analysts | Not self-serve |
| The wedge → | — | < 50 seats | Underserved |
Sources: Gartner 2025, vendor 10-Ks, pricing pages, Census CBP. Every figure cited in the appendix.
Customer Feedback Themes — May
Ranked by attached ARR, not raw frequency. Each theme links to its source calls, tickets, and quotes.
- 1 · Onboarding friction$214k ARR · 28 mentions
- 2 · Pricing confusion$156k ARR · 19 mentions
- 3 · Missing Salesforce sync$98k ARR · 12 mentions
- 4 · Slow CSV export$41k ARR · 22 mentions
"We almost didn't make it past week one — setup took three calls with support." — VP Ops, $48k ARR account (Gong, May 14)
Recommended follow-ups
- Ship a guided first-run; target time-to-first-value < 10 min.
- Rework the pricing page around seats, not credits.
- Prioritize the Salesforce connector — 5 deals waiting.
Daily Briefing — Friday
- Reply to Acme — they're waiting on the renewal terms.#sales · 7:42 PM
- Sign off on the pricing doc before the 11am review.Gmail · Dana
- Your 9:30 with Initech needs 5 min of prep.Calendar
Meeting prep · 9:30 Initech
Renewal call. They asked about SSO last time — it shipped Tuesday. Up-sell angle: 15 seats added in May.
Open loops
- 4 Linear issues moved to your review overnight.
- 2 Slack threads in #product mention you.
Every line links back to the source — one click to the thread, email, or issue.
SummaryReceiptsCategories
| A · Date | B · Vendor | C · Category | D · Amount | E · Note | |
|---|---|---|---|---|---|
| 1 | 05-03 | Linear | Software | $1,200.00 | |
| 2 | 05-07 | AWS | Infrastructure | $3,480.12 | |
| 3 | 05-09 | Delta | Travel | $612.40 | |
| 4 | 05-12 | Figma | Software | $144.00 | ⚑ possible duplicate of row 9 |
| 5 | 05-15 | Notion | Software | $96.00 | |
| 6 | 05-18 | Uber | Travel | $58.20 | |
| 7 | 05-21 | Sweetgreen | Meals | $84.10 | |
| … | TOTAL | $24,318.00 | =SUM(D2:D39) |
Interactive preview — click around, open an artifact, or type a task.
Why MindsHub Make AI do actual work.
Make AI do actual work.
Swap the model anytime — keep everything you've built.
Real knowledge work needs your data connected, somewhere for results to live, and a way to share them, all within an open, model-agnostic workspace.
Use commercial and open models side by side, switch providers without rewriting anything, and keep the memories you build along the way.
One workspace. Any model.
Pick the model that fits the job — reasoning, coding, vision, long context, or fast, low-cost drafts — and switch anytime from a dropdown.
Anthropic
OpenAI
Google
Kimi (Moonshot)
DeepSeek
Qwen
Data & tools
Connect your data through a secure vault
Point MindsHub at the systems your work lives in — BigQuery, Postgres, Gmail, Drive, HubSpot, Notion, Linear — from one connectors directory. Credentials go into a vault, scoped per connection. The agent uses them at runtime but never sees a raw key.
Models
Pre-wired models — swap in a click
The Model Router comes pre-wired, so there are no per-provider API keys to set up. Pick a planning model and a coding model from a dropdown — frontier models from Anthropic, OpenAI, and Google, or cost-effective open-source LLMs like DeepSeek, Qwen, and Kimi — and switch anytime. Your agent, history, and memory stay put.
Agent harness
Switch the agent harness
MindsHub runs on interchangeable open-source agent harnesses — Anton and Hermes today, with more on the way. Pick the one that fits your work from a dropdown and keep the same workspace, data, and artifacts. One interface; the engine underneath is yours to choose.
Artifacts
Real artifacts, not a wall of chat
MindsHub turns an agent's output into things you can use — documents, dashboards, apps, code — not a scrolling transcript. Keep them in the workspace, or publish to a live URL to share with anyone.
Collaboration
Organize in projects, share by link
Group work into projects, pin what matters, and share published artifacts with your team by link. MindsHub is built for handing work back and forth — not a private transcript only you can see.
And more
The rest of the workspace.
Memory across sessions
MindsHub remembers your schemas, preferences, and past decisions — and lets you manage what it keeps.
A skill library
Teach reusable skills once; the agent recalls them when the work fits, instead of relearning every time.
Scheduled work
Set a cadence and MindsHub runs the work on schedule — daily briefings, weekly summaries, recurring audits.
Under the hood
How MindsHub fits together.
MindsHub is the workspace you see; underneath, a managed runtime does the work. You brief a task, an open-source agent harness runs it, the Model Router sends each step to the right model, and a credentials vault lets the agent reach your data and tools without ever seeing a raw key — all on MindsHub's always-on infrastructure.
The MindsHub platform
Cowork
The unified workspace — brief the work, watch it run, collect the artifacts.
Projects Live artifacts Scheduled tasks Channels Skills
Agents Runtime
Agent Harnesses
Anton
Hermes
Coming soon 
Codex
NanoClaw
Model Router
Routes each step to the right LLM by cost, latency, and capability.
Right model for every task
Scratchpads
Protected reproducible execution environment.
Memories
Long-term, cross-run recall — facts, preferences, prior outcomes.
Credentials Vault
Encrypted secrets store — agents never see raw credentials.
OAUTH API KEY JWT SSH
Data & Tools Access
Databases
Warehouses
Docs & files
SaaS apps
Email & chat
Calendars
CRM
APIs
Data Files SaaS API / MCP
Open-source agents
Swap the engine, keep the work.
Switch agents without starting over — your data, memory, and work carry across. Builders can also run any of them standalone, native harness and all.
In MindsHub today Model and agent choice per task — coming soon
FAQ
Frequently asked.
- What is MindsHub?
- MindsHub is the unified workspace for open-source agents — one place for every agent and model. Brief a whole task in plain language, connect your data and tools, and collect finished, shareable work. The agent and model are swappable underneath.
- Which agents power MindsHub?
- MindsHub runs on interchangeable open-source agent harnesses — Anton and Hermes today, with more on the way. Anton is the default; switch the harness and the model from a dropdown anytime. Picking a different agent per individual task is coming soon.
- Can I switch the agent or model?
- You can switch the agent harness and the model from a dropdown today — the change applies across your work, not to one task at a time. Choosing a different agent per task is coming soon, along with memory that follows you across agents.
- Do I need to pick a model or agent to start?
- No. Create an account and brief your first task — there are no agent, model, or API-key decisions to make first. Sensible defaults are set for you, and you can switch the model or harness anytime.
- Why isn't a chat box enough for an AI agent?
- Chat is good for a question and an answer. Real knowledge work needs connected data, the right model for each step, a place for results to live, and a way to share them. MindsHub is the workspace around the agent, not just a transcript.
- How does MindsHub connect to my data?
- Through a connectors directory and a credentials vault. You connect sources like databases, warehouses, and SaaS tools once; secrets stay in the vault, scoped per connection, and the agent never sees a raw key.
- Is there a desktop or mobile app?
- MindsHub runs on the web with nothing to install, and ships as a desktop app for macOS and Windows — both installers are linked on this page. Mobile apps are coming soon.
- How do I get started?
- Create an account and brief your first task — no agent, model, or runtime to pick first. $9.95/month, cancel anytime, on the web or the desktop app.