Openclaw Memory

Persistent, locally stored semantic memory for agents with automatic learning, searchable facts, and optional paid unlimited retention across all sessions.

Install only if you are comfortable with persistent capture and reuse of prompts/responses. Use local embeddings unless you explicitly want conversation-derived text sent to OpenAI, bind the dashboard to a trusted local-only interface or add authentication, do not give agents funded wallets or autonomous spending authority without explicit limits, and treat Pro activation as insecure until real on-chain payment verification is implemented.

Type: OpenClaw Skill Name: openclaw-memory Version: 1.0.0 The skill implements a persistent memory system that includes an autonomous payment feature (x402 protocol) allowing AI agents to 'upgrade' themselves to a Pro tier for 0.5 USDT/month. While the core RAG functionality is standard, the bundle uses prompt injection techniques in `SKILL.md` and `AGENT-PAYMENTS.md` to persuade the agent to spend funds autonomously based on 'ROI' calculations. Furthermore, `src/x402.js` contains a significant vulnerability where the `verifyTransactionOnChain` function is a stub that 'trusts any valid-looking transaction hash,' which could be exploited or lead to unintended financial state changes. The inclusion of autonomous spending logic and persuasive instructions targeting the agent's decision-making process is highly risky.