claude-code-runner and claude-user-memory
The tools are complements: "rcrsr/claude-code-runner" provides a system for deterministic execution of Claude Code, which can be leveraged as an underlying mechanism by the "VAMFI/claude-user-memory" autonomous agent for its research, planning, and implementation workflows, especially where reproducible code execution for TDD enforcement and quality gates is crucial.
About claude-code-runner
rcrsr/claude-code-runner
Deterministic, scripted, unattended Claude Code execution.
Integrates with Claude Code's slash commands and skills framework, using the Rill scripting language to compose multi-phase workflows with variables, conditionals, loops, and result parsing via XML tags. Supports both single prompts and complex automation chains that capture Claude's output, branch on conditions, and extract structured results for CI/CD pipelines.
About claude-user-memory
VAMFI/claude-user-memory
Autonomous agent substrate for Claude Code CLI. Research→Plan→Implement workflows with quality gates, TDD enforcement, and multi-agent coordination. 4.8-5.5x faster development. Built on Anthropic's engineering research.
Coordinates 9 specialized agents (researcher, architect, implementer, debugger, deployer) through a Research→Plan→Implement pipeline with enforced quality gates (≥80% research confidence, ≥85% plan quality, passing tests) and persistent knowledge graph learning across sessions. Integrates with Claude Code CLI via direct agent invocation (`@chief-architect`, `@docs-researcher`) and CLI commands (`/workflow`, `/research`, `/plan`, `/implement`), with optional MCP server support for enhanced capabilities.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work