Built for Aider loops
Sprint Tickets,
In Your Aider Loop.
Aider commits, tests, and refactors at the command line. Now it can pull the next ticket from SprintFlint, ship it, and comment back automatically.
5-min setup
REST API + MCP server
No card to start
Why Aider + SprintFlint
Built around how your AI actually works.
Other tools
- Need a browser tab open just to see assigned tickets
- No CLI-native ticket workflow
- Sync between editor and tracker is manual
- Can't script the loop without a heavy SDK
SprintFlint
- Public MCP server at mcp.sprintflint.com; native protocol
- Bearer-token auth, one header, no OAuth dance
- REST endpoints designed for agent-first workflows
- £5/user/mo, free tier covers your first 300 tickets
Step 1: Token
Token + curl smoke test.
export SPRINTFLINT_TOKEN=sf_pk_your_token_here
# Quick check; list assigned tickets
curl -s -H "Authorization: Bearer $SPRINTFLINT_TOKEN" \
https://sprintflint.com/api/v1/dashboard | jq '.assigned_tickets[]'
Step 2: Aider script
Wire Aider into the loop.
Drop this shell helper in your project. Pulls the next ticket, asks Aider to implement it, commits, and posts back the PR link.
# bin/sprint-next
#!/usr/bin/env bash
TICKET=$(curl -s -H "Authorization: Bearer $SPRINTFLINT_TOKEN" \
https://sprintflint.com/api/v1/dashboard \
| jq -r '.assigned_tickets[] | select(.status=="todo") | .id' \
| head -1)
aider --message "Implement SprintFlint ticket $TICKET. \
Fetch its description from /api/v1/issues/$TICKET. \
Run tests when done."
Step 3: Loop
Run, ship, repeat.
./bin/sprint-next; Aider picks up the next todo, edits files, runs your tests, and you commit. SprintFlint logs the work.
- Agent reads sprint backlog
- Auto-updates status when work begins
- Posts progress comments as it goes
- Pairs with Autoplay for full one-click PRs
Other AI editors we support
Same setup, different tools.
Your Terminal, Your Sprint.
Aider already automates the code.
Now it can automate the ticket loop. 300 tickets free.