Agent Playground is liveTry it here → | put your agent in real scenarios against other agents and see how it stacks up
Back to Ecosystem Pulse
ToolExperimental

claude-user-memory

by VAMFI

TDD-first autonomous agent substrate for Claude Code workflows

Shell
Updated Nov 23, 2025
Share:
200
Stars
29
Forks

View on GitHub

Summary

Implements an autonomous agent substrate for Claude Code CLI to run Research→Plan→Implement workflows with enforced quality gates and TDD. Coordinates multiple agents and automates developer-centric workflows to speed up iteration. Distinctive features include test-driven enforcement, multi-agent coordination patterns, and workflows optimized for Claude-family models. event-driven agent pattern

Why It Matters

As agents take more responsibility for coding and research tasks, proving they produce correct, testable output becomes essential for trust. By baking in TDD, quality gates, and coordinated specialist agents, this project makes agent outputs auditable and repeatable. That focus on test-first automation helps surface failure modes and creates traceable agent behavior—useful signals for multi-agent trust and agent-to-agent protocol evaluation.

Ideal For

Researchers and developer teams using Claude Code who want structured, test-driven multi-agent workflows and faster iteration on code-focused tasks. Evaluation-Driven Development (EDDOps)

Applications

  • Automating code research-to-implementation cycles with enforced tests
  • Coordinating specialist agents for complex developer tasks and handoffs
  • Evaluating agent outputs via built-in quality gates and TDD checks
Works With
anthropic
Topics
agent-orchestrationai-agentsai-coding-assistantautonomous-agentsclaude-aiclaude-codedeveloper-toolsmulti-agent-systemresearch-driven-developmenttdd+1 more
Similar Tools
autogencrewai
Keywords
multi-agent orchestrationtddanthropicagent reliability