| FMRS | 58 / 100 · C | 79 / 100 · B |
|---|
| Reliability | 7 / 20 | 12 / 20 |
|---|
| Security and permissions | 10 / 20 | 18 / 20 |
|---|
| Maintenance | 11 / 20 | 16 / 20 |
|---|
| Documentation | 17 / 20 | 18 / 20 |
|---|
| Setup experience | 13 / 20 | 15 / 20 |
|---|
| Best for | - Retrocomputing enthusiasts who own Ultimate-family hardware or run VICE and want AI-assisted C64 development
- Developers working with BASIC / 6502 assembly, SID music, or PETSCII graphics
- Teams automating C64 program testing across real hardware and emulators with an AI agent
| - Engineering teams scaling AI coding agents while controlling spend
- Platform teams that need auditable, rollback-aware agent execution records
- Organizations using multiple agents (Claude, Codex, Gemini) under one governed flow
|
|---|
| Not for | - Users without any C64 hardware or the VICE emulator (no backend is available)
- Beginners seeking a fully hosted cloud service with no local setup
- Retro platforms other than the Commodore 64 (this server is C64-specific)
| - Developers who just want a simple code-completion helper without run governance
- Teams unwilling to accept local JSONL run records with HMAC signing
- Environments without a supported adapter (Claude/Codex/Gemini CLIs, direct provider, or verifier-only)
|
|---|
| Required permissions | - Network access to C64 Ultimate / Ultimate 64 / U2 cartridges via REST (default port 80), with an optional network password sent as an X-Password header
- Ability to launch and manage a local VICE emulator process and its Binary Monitor (default 127.0.0.1:6502)
- Local file access for config files, memory/screen dumps, diagnostics, and output artifacts
- Optional: GITHUB_TOKEN for RAG discovery against GitHub; optional use of sidplayfp for audio generation
| - Read/write access to the configured repo root (writable scope restrictable via --allow-path/--deny-path)
- Ability to invoke the chosen agent CLI (Claude/Codex/Gemini, etc.) and its underlying model account
- Local disk writes for run records, receipts, and share outputs (share/run-receipt., etc.)
- Execution of user-configured verifier commands (e.g. npm test)
|
|---|
| Risks and side effects | - The server can write memory, control power/reset, and manage drives; misuse may disrupt running C64 programs or firmware state
- Network passwords and GitHub tokens are passed in plaintext via environment variables, so credential handling matters
- The optional HTTP bridge is disabled by default; if enabled without protection, local clients could invoke tools
- U2-family cartridges have reduced capability (no machine input, debug registers, power-off, or streaming), and some operations require recent firmware (e.g., U64 3.15+), so older firmware makes certain tools unavailable
| - Verifier commands are executed; poorly chosen verifier commands carry security risk despite preflight policy checks
- Cost and token figures may be estimates (labeled with provenance) and should not be treated as settled accounting
- Receipt integrity must be verified before use as trustworthy evidence; missing rollback evidence is flagged as EVIDENCE_BOUNDARY
- Policy defaults come from martin.config.yaml and can be overridden by CLI flags; misconfiguration can loosen safety boundaries
|
|---|
| Supported clients | GitHub Copilot, Claude Code, Cursor, Visual Studio, VS Code Insiders | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 17 | 0 |
|---|