vishnu-77/openreflex

Overview

OpenReflex is a Python-based developer tool that gives AI coding agents muscle memory. It learns from every task, advises the next one, and flags failure loops live. It supports Claude Code, Codex, Cursor, and OpenCode.

Best for

Best for
Developers using Claude Code, Codex, Cursor, or OpenCode who want task memory and failure-loop warnings.

Use cases

• Track recurring patterns across coding tasks
• Get live warnings when an agent enters a failure loop
• Advise next steps based on prior task history

How to use

Install

pip install -e ".[dev]"

Tools exposed

• get_execution_context
• check_progress
• choose_path
• record_outcome
• explain_decision
• get_execution_trace
• get_reflex_score
• search_experience
• explain_node
• get_project_insights
• approve_project
• forget_experience

Tested with

Claude Code, Cursor, Continue

Notes

OpenReflex is a Python-based developer tool that gives AI coding agents muscle memory. It learns from every task, advises the next one, and flags failure loops live. It supports Claude Code, Codex, Cursor, and OpenCode.

2 stars on GitHub. Last updated 2026-09-16. Licensed MIT.

Use cases

• Track recurring patterns across coding tasks
• Get live warnings when an agent enters a failure loop
• Advise next steps based on prior task history

Pros

• Learns from task history to improve future suggestions
• Live failure-loop detection
• Works across multiple coding agents

Cons

• Very early stage with only 2 GitHub stars
• Python-only, requiring a Python environment
• Limited evidence of active maintenance or community

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.