foundr.team — full features
An MCP-first roster for your AI teammates. Each agent gets a role, a budget cap, and a weekly retro of what it shipped. Flat $/mo, no per-seat math — you ARE the team.
Pricing
Free via X. Solo at indie prices. Pro when you scale.
Same pricing model across the whole foundr.* family. No per-seat math. No enterprise quote theater.
Free
quote-tweet @perea_ai
$0
Three agent slots, weekly retro, one project.
- 3 agent slots
- Weekly retro
- 1 project
- Basic trace history
Solo
Recommended$19 / mo
Ten slots, per-agent budget caps, BYO keys.
- 10 agent slots
- Per-agent budget caps with circuit breaker
- Unlimited retros
- 3 projects
- BYO model keys (Anthropic, OpenAI, OpenRouter)
Pro
$49 / mo
Unlimited agents and projects, audit log, MCP team_* surface.
- Unlimited agents
- Unlimited projects
- Audit log
- Full MCP team_* tool surface
- Priority support
What you get
Every feature, grouped by who it's for.
Core
- Agent profile cards (role, scope, tools, escalation path, model)
- Per-agent monthly $ budget cap with hard stop + soft warnings
- Weekly retro — auto-generated digest of what each agent shipped, cost, success rate
- Project assignment — one agent works across N projects with per-project budgets
- Run trace timeline (step, tool call, cost, duration) drillable from the retro
- Audit log of brief / budget / tool changes
- Agent pause / resume / hire / fire lifecycle
- Live activity feed of in-flight agent work
Agentic-first (MCP + token)
- team_hire — register a new agent via its MCP endpoint
- team_brief — push a role / system prompt update
- team_pause / team_resume — emergency stop
- team_retro — pull this week's retro programmatically
- team_budget_check — agent self-queries remaining budget before expensive calls
- team_report — agent posts what it shipped (becomes retro substrate)
Solo-founder-shaped
- Multi-project default — no "create org first" wall
- Flat $ / mo, no per-seat math (you ARE the team)
- BYO model keys — pass-through, no Cursor-Token-style markup
- Free tier via quote-tweet, not credit card
- Sane defaults — sign in, get 3 agent slots pre-wired for Claude / Cursor / Codex
Agentic-first
The MCP surface your agents call.
Add it once to Claude, Cursor, or any MCP host. Your bearer token unlocks every tier — no dashboard required.
claude mcp add --transport http foundr-team https://foundr-team.foundr.company/api/mcp
team_hireRegister a new agent via its MCP endpoint
team_briefPush a role / system prompt update
team_pause / resumeEmergency stop / restart
team_retroPull this week's retro programmatically
team_budget_checkAgent self-queries remaining budget
team_reportAgent posts what it shipped (retro substrate)
Why this differs
The angles the incumbents won't ship.
- 01
MCP-first roster. Every agent (Claude, Cursor, Codex, custom) registers via MCP — one universal contract.
- 02
Multi-project default, not multi-tenant org. Solo founder running 3 side projects, not 1 company with 50 seats.
- 03
Per-agent budget caps in dollars + circuit breaker. No managed platform ships this.
- 04
Weekly retro as the primary surface. Competitors show traces; nobody narrates what each teammate shipped.
- 05
Indie pricing, not per-seat. You ARE the team. Quote-tweet free, no card.
Competitive landscape
Who's already here, and what they leave on the table.
Honest comparison. We do not pretend the space is empty.
- CrewAIFree + $99 / mo+
OSS orchestration + enterprise cloud
Gap: Enterprise-shaped, dev-only
- Lindy$49.99–$199.99 / mo
Personal AI assistant + workflows
Gap: Built for inboxes, not roster mgmt of CLI agents
- Sintra$48.50–$97 / mo
12 pre-baked "AI employees"
Gap: Closed roster — can't add Claude / Cursor / custom
- Cursor Background Agents$40 / seat + usage
Coding agents in IDE
Gap: Per-seat, Cursor-only
- Devin Teams$80–$200 / mo + ACUs
Parallel coding agents
Gap: Devin-only — no shelf for other agents
Hire your first three agents
Quote-tweet @perea_ai. Three agent slots pre-wired for Claude, Cursor, and Codex. The weekly retro tells you what each one actually shipped.