| FMRS | 64 / 100 · C | 79 / 100 · B |
|---|
| Reliability | 10 / 20 | 12 / 20 |
|---|
| Security and permissions | 11 / 20 | 18 / 20 |
|---|
| Maintenance | 15 / 20 | 16 / 20 |
|---|
| Documentation | 15 / 20 | 18 / 20 |
|---|
| Setup experience | 13 / 20 | 15 / 20 |
|---|
| Best for | - Teams building multi-step AI workflows with state, memory, and tool use
- Teams seeking to reduce repeated prompt-loop orchestration
- Projects requiring strict compile-time validation or execution auditing
- Users of Claude Code, Codex, or other MCP-compatible agents
| - 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 who only need simple hand-written scripts
- Teams that already have deterministic runners and use LLMs only at judgment gates
- Projects with no need for workflow validation, auditing, or MCP integration
| - 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 | - Install and run a local Python program
- Access workspace files, cache, or SQLite when corresponding adapters are enabled
- Access networks or external services when HTTP, A2A, or other adapters are enabled
- Use relevant environment configuration when workflows require secrets or external services
| - 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 | - Enabling HTTP or A2A adapters introduces external network access risk
- Workflows may access files, caches, databases, or secrets depending on adapters and policy configuration
- Misconfigured adapter, step, runtime, or workspace limits may broaden execution scope
- Machine-payment profiles are opt-in but may process HTTP 402 payment flows when enabled
| - 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 | Claude Code, Codex, Gemini CLI, Claude Desktop | Claude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue |
|---|
| Tools | 13 | 0 |
|---|