Take control of agent work
Superloopy runs agent work in a loop until proof exists: plan, act, evidence, gate.
Crew
Superloopy keeps agents moving inside a bounded loop, then lets evidence decide when the work is done.
Evidence
Every run writes artifacts under .superloopy/evidence, so results can be checked after the chat.
Skill lanes
Use loopy for focused work, research, frontend, and clone flows without changing the proof rule.
VISIBLE PROGRESS
Plans, commands, screenshots, and reports stay linked to the goal instead of disappearing into chat.
FINAL GATE
Completion requires a named artifact and a clear pass, blocker, or next action.
superloopy®
Agent Work Loops
proof
Bounded task loops
Evidence that survives the chat
A final report with blockers named
Agents move fast. Superloopy makes done mean proven.
Proof
Built for Codex and Claude Code workflows that need receipts
Focus on the task. Let the loop demand proof.
Running agent work
been clearer
Step 01
Set the goal
Define the objective, success criteria, and evidence folder before the agent starts moving.
Step 02
Act in loops
The agent keeps taking the next visible action, with each pass tied back to the goal.
Step 03
Capture evidence
Commands, screenshots, reports, and audit files land where they can be opened and rerun.
Step 04
Pass the gate
The final report separates finished work from blockers, with artifacts named in the open.
Install
Install once. Then type loopy.
Install SuperloopyInstall SuperloopyInstall
Choose your agent lane
Questions
(01)
What makes Superloopy different from a prompt?
(02)
Where does the evidence live?
(03)
Does it work with Codex and Claude Code?
(04)