vvm
CommunityRun LLM-powered agent workflows with memory.
Software Engineering#parallel-execution#agent-workflow#module-imports#vvm#llm-runtime#memory-patch#semantic-predicate
Authorkaranchawla
Version1.0.0
Installs0
System Documentation
What problem does it solve?
VVM enables orchestrating complex AI workflows by letting the LLM act as the runtime, coordinating multiple agents with semantic control flow and memory persistence.
Core Features & Use Cases
- Actor-aware orchestration: semantic predicates, pattern matching, and explicit memory patches to guide decisions.
- Memory-backed execution: digest and ledger memory with patch channels, providing continuity across runs while keeping prompts bounded.
- Portability: runtime-agnostic design that works across in-context and filesystem state modes for debugging and auditing.
Quick Start
Run a minimal VVM program to observe memory patches emitted and the resulting outputs.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: vvm Download link: https://github.com/karanchawla/vvm/archive/main.zip#vvm Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.