LetRetro
5.6The retro tool that thinks with your team
LetRetro is a young, AI-forward retrospective platform built around retros wired into sprint data. Its headline differentiator is now shipped rather than promised: an official MCP server lets Claude, Cursor, VS Code and other AI clients read and drive boards directly. Real-time collaborative boards, AI-generated retro documentation, sentiment/trend analysis and a team health checker sit on flat (pooled-seat) pricing rather than per-user, with Jira, GitHub, GitLab and Linear card linking to close the loop.
Full review →
QRetro
5.8Manage team health, not sticky notes
QRetro is a completely free retrospective tool with no seat or team caps, built by solo developer Roman Ermilov and shipping continuously since January 2023. It runs a fixed seven-stage session — optional health check, optional icebreaker game, cards, grouping, voting, discussion, results — and closes with an auto-generated summary, ROTI score and action items. An official MCP server exposes 29 read/write tools so Claude, Cursor or VS Code can query boards, health trends and actions directly.
Full review →Summary
LetRetro scores 5.6 overall and is best for developer-leaning agile teams and startups that want AI-assisted retros wired into their sprint data and dev stack — Jira, GitHub, GitLab and Linear card linking, plus an official MCP server their AI clients can drive — with health and sentiment tracking and no enterprise overhead. It offers a free tier.
QRetro scores 5.8 overall and is best for small agile teams and independent squads that want a genuinely well-equipped retro — 52 templates, health checks, ROTI, timer, icebreaker games and MCP access — at zero cost, and can accept a solo-maintainer vendor with no SSO, no export files and no certifications. It offers a free tier.
LetRetro leads on AI & insights, integrations and enterprise-grade. QRetro leads on ease of use, fun factor and open platform.
Across our eight scoring dimensions, QRetro edges ahead with an overall score of 5.8. That said, the right pick depends on your team — see the dimension-by-dimension breakdown below.
Scores compared
| Detail | LetRetro | QRetro |
|---|---|---|
| Category | Retrospectives | Retrospectives |
| Team size | Small | Small |
| Free tier | Yes | Yes |
| Free limit | 3 boards, 1 team, 20 pooled seats, 2 AI docs/mo, 5 exports/mo, community support | Everything is free with no seat or team caps — 52 templates, unlimited public and team boards, planning poker, team games, health checks, ROTI, summaries and MCP access |
| Starting price | $15/mo (Pro, flat) | Free |
| Est. 3 teams × 8 people | $15/mo (Pro — flat plan covers unlimited teams within its 200 pooled-seat cap; 24 users fits) | Free (no paid tier) |
| Enterprise | Yes | No |
| Founded | 2025 | 2023 |
| HQ | Bengaluru, India | — |
| Data residency | — | — |
| Languages | English only | English only |
| Export formats | — | — |
| Features | 21 | 32 |
| Integrations | 6 | 3 |
Feature & integration comparison
Side-by-side checklist across features, integrations and security. Hover a note for details.
| Capability | LetRetro | QRetro |
|---|---|---|
| Features | ||
| AI Summaries | ✓ | ✓ |
| AI grouping/clustering | — | — |
| AI action items | ✓note | ✓note |
| Action tracking | ✓ | ✓ |
| Team Insights | ✓note | ✓note |
| Polling | ✓note | — |
| Action dashboard | ✓note | ✓note |
| Custom templates | ✓note | — |
| Anonymous input | ✓ | ✓note |
| Independent voting | ✓ | ✓ |
| Async mode | — | — |
| Agile Estimations | — | ✓note |
| Health Checks | ✓note | ✓note |
| Team Kudos | — | ✓note |
| Whiteboard | — | — |
| Integrations | ||
| Asana | — | — |
| Azure DevOps | — | — |
| Basecamp | — | — |
| ClickUp | — | — |
| Confluence | — | — |
| GitHub | ✓ | — |
| GitLab | ✓ | — |
| Jira | ✓ | ✓note |
| Linear | ✓ | ✓note |
| Microsoft Teams | — | — |
| Monday.com | — | — |
| Notion | ✓ | — |
| Shortcut | — | — |
| Slack | ✓note | ✓note |
| Trello | — | — |
| Security & Privacy | ||
| SOC 2 | — | — |
| GDPR | ✓note | ✓note |
| SSO / SAML | ✓note | — |
| SCIM provisioning | — | — |
| ISO 27001 | — | — |
| On-premises | ✓note | — |
| Public API | — | — |
| Webhooks | — | — |
| MCP server | ✓note | ✓ |
LetRetro — pros
- + Flat pricing — $15/mo Pro covers unlimited boards and teams within a 200 pooled-seat cap, so a growing org isn't billed per head
- + AI is a genuine focus, not a bolt-on: retro-doc generation, sentiment/trend analysis, key takeaways and improvement suggestions that cut the post-retro write-up burden
- + An <strong>official MCP server actually shipped</strong> in July 2026 — one-command install, 17 tools, 11 clients — so Claude, Cursor or VS Code can read boards and file cards without a bespoke script
- + Dev-stack card linking is real and reasonably deep: Jira, GitHub, GitLab and Linear, with inline issue editing, comments and one card linked across several providers at once
- + Built-in team health checker and sentiment-over-time trend dashboards — longitudinal signal many cheap retro tools skip
LetRetro — cons
- − Thin enterprise story: Google and Microsoft sign-in but no SAML SSO, SCIM only 'in progress', no audit-log access, no LetRetro-held SOC 2 or ISO 27001; on-premise and SLA sit behind a quote-only Enterprise tier
- − Solo-founder micro-SaaS — the team page lists one person (Dhanush Kandhan, Bengaluru) still recruiting, and independent coverage is almost nil (9 Product Hunt upvotes, 2 reviews) — a real durability risk for procurement
- − The vendor's own pages contradict each other on connectors: the homepage badges Jira, Confluence and Asana 'Coming Soon' while the integrations page and comparison FAQ list all three as live. Verify anything you're depending on
- − Retro toolkit lacks facilitator staples: no confirmed timer, recurring/scheduled retros, parking lot, team agreements or async-first mode — it's built around live, real-time sessions
- − No public REST API and no webhooks, and the export formats behind the metered '5 exports/mo' limit aren't documented anywhere — MCP is the only programmatic route in
QRetro — pros
- + Genuinely free with no seat caps, team caps or paywalled features — a 24-person org across three teams pays nothing, and there is no paid tier to be upsold to
- + Retro toolkit is deep for a free product: 52 templates, private-mode submission, timer, drag-and-drop grouping with auto-named groups, action items, team agreements, ROTI and a radar-charted health check stage
- + Unusually strong engagement layer for a product that charges nothing — four built-in games (Draw & Guess, Sprint in one GIF, Hangman, Decoded) usable as a switchable icebreaker stage, plus GIF cards, emoji reactions and live cursors. TeleRetro and the whiteboard tools still go further, mainly on music and ambient audio
- + Official MCP server at a single address (mcp.qretro.com) with 29 read, write and delete tools and OAuth sign-in, so Claude, Cursor or VS Code can pull board summaries, health trends and action items with nothing to paste
- + Guest access with no account or password, and guest contributions now persist permanently rather than expiring after a day
- + Visibly active despite being a solo project — 15+ dated changelog entries across 2026, including the v4 relaunch, MCP OAuth, poker over MCP and two new games in July–August 2026
QRetro — cons
- − Built and maintained by a single developer (Roman Ermilov) with no support team, SLA or published company entity — the enterprise-grade cap for founder-only vendors applies regardless of how good the product is
- − No enterprise controls at all: no SSO or SAML, no SCIM, no audit logs, no SOC 2 or ISO 27001; a DPA and sub-processor list are published but there is no explicit GDPR compliance claim
- − No file export — results share to Slack or Telegram as a recap message, but there is no documented PDF, CSV, Excel, Markdown or email export, so the retro record cannot be filed anywhere outside those two channels
- − Integration set is narrow: Jira, Linear, Slack and Telegram only — nothing for Teams, Confluence, GitHub, GitLab, Azure DevOps or any other tracker
- − No async or distributed-team support — the seven-stage flow assumes a live session, and there are no recurring or scheduled retros
- − Vote allowance is computed automatically (cards + 3, capped at 10) rather than set by the facilitator, and the stage order itself cannot be customised
- − AI is deliberately limited — summaries, recommended next steps and health trends, but no clustering, sentiment analysis or coaching; the vendor pitches this as avoiding 'intrusive chatbots'
- − No cross-team or org-level reporting, so health and action data stays inside a single team's boards
Keep comparing
Other LetRetro comparisons
Other QRetro comparisons
Not sure which to pick? Read our guide on how to choose a retrospective tool.