How POLYROB compares

POLYROB is a goal-achieving, self-evolving, crypto-native agent — and a base you can ship products on. The table below compares capabilities and architecture — the axes we can state about ourselves first-party.

Capabilities as of 2026-06. Popularity metrics (stars/forks/skill counts) are deliberately omitted here pending first-party re-verification — we publish capability facts we can stand behind, not numbers we can't.
Capability POLYROB Hermes OpenClaw LangGraph Claude Agent SDK
LicenseApache-2.0MITMITMITMIT
Goal-achieving autonomy✓ durable goal board + cron⚠ cron only
Self-evolving skills✓ writes + curates✓ learning loop✓ workspace
Cross-session memory✓ H-MEM hierarchical✓ FTS5✓ FTS5⚠ add-on⚠ add-on
Agent wallet✓ policy-capped + audited
On-chain payments (x402)✓ USDC on Base
On-chain identity + reputation (ERC-8004)✓ 3 registries
Security model✓ 3-tier access + capability gates⚠ pairing✓ sandbox⚠ basic⚠ basic
Prompt-injection defense✓ untrusted-output wrapping⚠ partial⚠ partial⚠ partial
Multi-tenant + billing✓ isolation + metering + credits✗ single-user✗ single-user
Standard agent APIs✓ REST + OpenAI-compat + A2A
Use any of 6+ providers✗ Anthropic
MCP support✓ full client⚠ exp.
Browser automation✓ Playwright
Chat surfaces (one contract)✓ CLI / Telegram / WhatsApp / email

supported   partial/limited   not supported

When to choose POLYROB

You want goals chased, not chatted

Durable goals + autonomy loops that run unattended, survive restarts, and deliver — and an agent that evolves its own skills as it goes.

You want a crypto-native agent

A built-in wallet and x402 pay-per-request in USDC on Base — the agent pays for what it uses and can charge for its own work.

You're building an agent product

Multi-tenant isolation, metering + credits, and standard APIs (REST / OpenAI-compat / A2A) are in the core — ship a paid agent without a backend. Apache-2.0, self-hosted.