Developer Tools●●Solid
AgentClick – Human-in-the-loop review UI for AI coding agents
Browser review layer stops AI agents from wrecking your code before you approve.
Solve My ProblemShip It
harvenstar
213mo ago
Back to browse
GitHub Repository
A rich web UI layer for AI agent interactions — human-in-the-loop, click-to-edit, preference learning. Built for Claude Code, CodeX and OpenClaw.
26 starsTypeScript
AgentClick – Human-in-the-loop review UI for AI coding agents
by harvenstar·Mar 16, 2026·1 point·0 comments
AI Analysis
●●SolidShip ItSolve My Problem
Human-in-the-loop review layer for Claude Code before irreversible agent actions.
Strengths
- •Edit drafts and commands in browser UI instead of just approve/reject.
- •Preference learning persists feedback so agents improve across sessions.
- •Framework-agnostic—any agent that POSTs JSON can integrate via HTTP.
Weaknesses
- •Agent review UI space is getting crowded with similar tools emerging.
- •Requires agents to implement skill/plugin integration—adoption friction.
Category
Target Audience
Developers using autonomous AI coding agents like Claude Code
Similar To
Warp AI · Cursor · Continue
Similar Projects
Developer Tools●●Solid
AgentClick – Human-in-the-loop review UI for AI coding agents
Human-in-the-loop for AI agents before they rm -rf production.
Solve My ProblemBig Brain
harvenstar
343mo ago
Developer Tools●●Solid
AgentClick – Human-in-the-loop review UI for AI coding agents
Browser review layer for terminal agents when most tools are CLI-only.
Niche GemShip It
harvenstar
403mo ago
Developer Tools●●Solid
Manual code review and feedback loop for agents
Human-in-the-loop interface for reviewing AI agent code plans before execution.
Bold BetShip It
ramoz
403mo ago
AI/ML●●Solid
NSED v0.5.1: Don't Trust Your Agents. Verify Them
Pause agents mid-deliberation and edit responses before commit for compliance.
Solve My ProblemSlick
t_peersky
203mo ago
Developer Tools●Mid
Ralph Review – OSS code review that loops fixes until no issues remain
Automated code review loop via agent ping-pong, but Cursor already does multi-turn fixing in context.
Big BrainShip It
kenryu
103mo ago