← 返回 Skills 市场
500
总下载
2
收藏
1
当前安装
7
版本数
在 OpenClaw 中安装
/install openclaw-memory-pensieve-algorand
功能描述
Long-term episodic memory for OpenClaw with append-only hash-chained local layers, daily dream-cycle consolidation, AES-GCM encrypted Algorand anchoring, and...
安全使用建议
This skill appears to do what it says: it will read a wallet mnemonic and an AES key (from env vars or local .secrets files) to encrypt and anchor your local memory to the Algorand blockchain. Before installing: (1) review server.py yourself or run it in an isolated environment; (2) use a dedicated low-balance anchoring wallet (do not reuse your main ops wallet) and rotate/delete that wallet if you stop using the skill; (3) prefer env vars over local fallback files and secure them (chmod 700/.secrets); (4) run pensieve_anchor in dry-run mode and pensieve_validate to confirm expected behavior; (5) confirm logs never contain mnemonic/key (the project states this, but verify). If you cannot review the code, treat the mnemonic as highly sensitive and consider running only in a sandbox or using a temporary wallet.
功能分析
Type: OpenClaw Skill
Name: openclaw-memory-pensieve-algorand
Version: 3.0.0
The skill bundle implements a sophisticated long-term memory system that anchors encrypted data to the Algorand blockchain. While the code in 'server.py' appears functionally aligned with its stated purpose and includes robust integrity checks (AES-GCM, zlib compression, and hash-chaining), it requires high-sensitivity credentials—specifically a 25-word Algorand mnemonic—to be stored in environment variables or local files. Although the script uses these credentials only to sign self-transactions for data anchoring and does not show evidence of intentional exfiltration, the management of private keys within an AI agent's execution environment is a high-risk capability that warrants caution.
能力评估
Purpose & Capability
Name/description (encrypted Algorand anchoring of local memory) match the requested capabilities: algosdk and cryptography are required, and the server requires an Algorand wallet + AES key. There are no unrelated credentials or unexpected binaries requested.
Instruction Scope
SKILL.md instructs running server.py as an MCP server and to provide ALGORAND_WALLET_MNEMONIC and ALGORAND_NOTE_KEY_HEX in env vars. It documents append-only paths, encrypt-before-anchor rules, and validation steps. The server reads workspace paths and optional local .secrets fallbacks (explicitly documented as local-dev only). This is in-scope for the stated functionality, but you must be aware the runtime will read secret env vars or fallback files and will sign/send transactions to the Algorand network.
Install Mechanism
No opaque download/install is embedded. The repo lists standard Python packages (mcp, algosdk, cryptography) and SKILL.md instructs pip install of those packages — a normal, traceable install mechanism for a Python MCP server.
Credentials
Required secrets (mnemonic, AES key) are proportional to the functionality (blockchain anchoring + encryption). The skill does not request unrelated tokens or extra credentials. It also allows (documented) local file fallbacks; those are reasonable for development but increase risk if misused.
Persistence & Privilege
always is false and the skill is user-invocable; it does not request permanent platform-wide privileges or modify other skills. It exposes MCP tools as intended for this use case.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install openclaw-memory-pensieve-algorand - 安装完成后，直接呼叫该 Skill 的名称或使用
/openclaw-memory-pensieve-algorand触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v3.0.0
OpenClaw Pensieve v3.0.0 is a major update — all scripts replaced by a streamlined MCP server.
- Migrated from multiple standalone scripts to a single `server.py` providing all functionality.
- All tools (capture, dream-cycle, anchoring, validation, recovery, status) now exposed via MCP commands.
- Removed dependence on separate virtual environments and per-script invocations.
- Secrets are now read from environment variables (with file-based fallback for dev only).
- Simplified installation and deployment: just install `mcp`, `algosdk`, and `cryptography`.
- Usage and operational rules updated for single-server operation.
v2.1.1
- Added explicit prerequisites section outlining Python dependencies, required secret files, and relevant environment variables.
- Introduced a new preflight requirements script (`scripts/preflight_requirements.py`) for environment validation.
- Added reference documentation (`references/security-prereqs.md`) specifying required security and operational dependencies.
- Updated runtime instructions and reference list to include new scripts and mandatory preflight check.
v2.1.0
Version 2.1.0 introduces disaster recovery hardening, new scripts, and improved anchor handling.
- Added v2.1 hardening scripts for post-anchor recoverability checks and validation.
- Replaced daily capture, consolidation, and anchoring scripts with new streamlined versions for event collection, dream cycle, and Algorand integration.
- All operational references updated or consolidated; new runbook and hardening documentation added.
- Prior scripts for payload construction, encryption, event capture, and key rotation removed in favor of the new approach.
- Recovery from blockchain is now directly supported with a dedicated script for memory reconstruction.
v2.0.0
Version 2.0.0 — Major overhaul with a focus on high-performance, predictable memory and streamlined daily operations
- Introduces a dual-lane architecture: fast append-only capture and bounded daily consolidation.
- Adds new scripts for event capture and budgeted dream cycles; removes legacy consolidation flow.
- Updates all references to reflect current architecture, operations, and Algorand anchoring process.
- Consolidates and simplifies rules for append-only storage and anchoring.
- Emphasizes external transaction signing and encrypted anchoring for enhanced security and compliance.
v1.0.2
- Added dream_cycle_daily.py script to scripts/, enabling a high-performance daily memory consolidation and anchoring workflow.
- Updated SKILL.md: recommends running dream_cycle_daily.py for daily memory operations; provides a streamlined, step-by-step daily pipeline section.
- Clarified usage instructions for both basic and high-performance (dream cycle) consolidation, and improved performance tips for anchoring and retrieval.
- No breaking changes to existing APIs or scripts.
v1.0.1
- Algorand anchor workflow updated to require external wallet/HSM for transaction signing.
- Added script: scripts/build_unsigned_anchor_tx.py for generating unsigned Algorand anchor transactions.
- Removed script: scripts/create_algorand_wallet.py; wallet creation is now out of scope.
- Revised documentation to reflect the new external signing and submission flow.
v1.0.0
openclaw-memory-pensieve-algorand v1.0.0
- Initial release of a local-first, append-only memory system for OpenClaw agents.
- Features integrity hash-chains, daily consolidation, and contradiction logging.
- Optional Algorand blockchain anchoring using encrypted transaction notes for integrity verification.
- Provides scripts for memory layer management, anchoring workflows, and data retrieval/verification.
- Includes detailed documentation and schema references.
元数据
常见问题
pensieve-algorand 是什么？
Long-term episodic memory for OpenClaw with append-only hash-chained local layers, daily dream-cycle consolidation, AES-GCM encrypted Algorand anchoring, and... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 500 次。
如何安装 pensieve-algorand？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openclaw-memory-pensieve-algorand」即可一键安装，无需额外配置。
pensieve-algorand 是免费的吗？
是的，pensieve-algorand 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
pensieve-algorand 支持哪些平台？
pensieve-algorand 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 pensieve-algorand？
由 pitertxus（@pitertxus）开发并维护，当前版本 v3.0.0。
推荐 Skills