ForeverVM

Creates and manages long-lived Python execution environments (machines) that maintain state across multiple instruction invocations, with automatic memory-to-disk swapping for idle machines. Machines are created with optional memory limits and tags, execute Python code sequentially, and automatically transition between active (in-memory) and idle (disk-swapped) states based on usage patterns. The system preserves all local variables, imports, and execution context between calls without requiring explicit serialization.

Provides consistent client libraries in JavaScript, Python, and Rust that abstract the ForeverVM service API, exposing identical methods for machine creation, instruction execution, and machine management across all three languages. Each SDK implements the same core classes (ForeverVM client, Repl connection) and follows language-idiomatic patterns while maintaining API parity, enabling polyglot teams to use ForeverVM without language-specific learning curves.

Exposes ForeverVM machines as tools through the Model Context Protocol (MCP), enabling AI platforms and LLM agents to discover, create, and execute Python code on persistent machines via a standardized tool-calling interface. The MCP server translates LLM function calls into ForeverVM machine operations, handling schema validation, result formatting, and error propagation back to the AI system.

Enables organizing and querying machines using arbitrary key-value tags assigned at creation time, with filtering capabilities to retrieve machines matching specific tag criteria. Tags are stored as metadata on each machine and can be used to organize machines by project, user, environment, or any custom dimension without modifying the machine itself.

Allows specifying memory constraints when creating machines, enabling control over resource allocation and cost. Memory limits are enforced at the machine level, preventing runaway processes from consuming unlimited system resources and enabling predictable resource planning for multi-machine deployments.

Executes Python statements and expressions sequentially on a machine, streaming results (stdout, stderr, return values) back to the client as they become available. Instructions are processed one at a time in FIFO order, with each instruction's execution isolated from others while sharing the machine's persistent state. Output streaming enables real-time feedback without waiting for full execution completion.

Provides methods to enumerate all machines or filter machines by tags, returning machine objects with full metadata (id, creation timestamp, tags, memory configuration, current state). Machine discovery enables inventory management, monitoring, and lifecycle operations across multiple machines without requiring external state tracking.

Provides command-line interfaces in JavaScript, Python, and Rust for creating, listing, executing code on, and managing ForeverVM machines without requiring SDK integration. CLI tools expose the same core operations as SDKs (create, execute, list, delete) with shell-friendly output formats and argument parsing, enabling shell scripts and automation workflows.

Implements a client-server model where SDK clients communicate with a remote ForeverVM service over the network, with the service managing all machine lifecycle, state persistence, and Python code execution. Clients send instructions and receive results via API calls, enabling decoupling of client applications from execution infrastructure and enabling multi-client access to shared machines.

Organizes ForeverVM as a monorepo containing parallel implementations in JavaScript, Python, and Rust, each with SDK, CLI, and supporting tools. The monorepo structure enables code sharing of common patterns and documentation while maintaining language-specific idioms and build systems (npm, pip, cargo). This architecture supports consistent versioning and coordinated releases across all language implementations.