← 返回 Skills 市场
Grantai Memory
作者
lgrant1234
· GitHub ↗
· v1.3.0
· MIT-0
352
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install grantai-memory
功能描述
Persistent memory for OpenClaw agents. Exact recall in milliseconds - your agent remembers everything across sessions.
使用说明 (SKILL.md)
GrantAi Memory
Persistent memory for your OpenClaw agent. Never hit context limits again.
Your agent remembers everything - from 1 minute ago to 5 years ago. Exact recall in milliseconds.
Free for OpenClaw Users
GrantAi Memory is free for OpenClaw users - automatic activation, no license key required.
The Problem
OpenClaw agents hit context window limits mid-task, forget everything, and start from scratch.
The Solution
GrantAi gives your agent exact recall in milliseconds:
- Memory persists across sessions
- Works outside the context window
- 100% local - data never leaves your machine
- AES-256 encrypted at rest
Installation
Download from solonai.com/grantai/download
- macOS: .pkg installer
- Windows: GUI installer (.exe)
- Linux: .tar.gz package
- Docker:
ghcr.io/solonai-com/grantai-memory:1.8.6
Configuration
Add to your OpenClaw config:
mcp:
grantai:
command: grantai-mcp
Or with Docker:
mcp:
grantai:
command: docker
args:
- run
- -i
- --rm
- -v
- grantai-data:/data
- ghcr.io/solonai-com/grantai-memory:1.8.6
Tools
| Tool | Description |
|---|---|
grantai_infer |
Query memory (use FIRST before file searches) |
grantai_teach |
Store information for future recall |
grantai_learn |
Import files/directories into memory |
grantai_summarize |
Save session summaries |
grantai_project |
Track project state across sessions |
grantai_snippet |
Store code snippets with context |
grantai_capture |
Capture conversation turns verbatim |
grantai_git |
Import git commit history |
grantai_health |
Check memory system status |
grantai_savings |
View token savings statistics |
Usage Examples
Store a decision:
Remember that we decided to use JWT for authentication
Recall it later:
What did we decide about authentication?
→ Returns exact decision in milliseconds
Import codebase:
Learn the src/ directory
Support
安全使用建议
This skill appears coherent for adding a local persistent-memory coprocessor, but the security/privacy guarantees in the README depend on the upstream binary/image. Before installing: 1) Verify the publisher (solonai.com) and download checksums/signatures if available. 2) If you need to ensure data never leaves your machine, run the binary/image in an isolated container or host with networking disabled and monitor outgoing connections. 3) Review the Docker image and installer release notes or source code if available (or request a reproducible build). 4) Be aware that import commands will read files you point them at (codebases, git history) — avoid importing sensitive directories unless you trust the binary. If you want stronger assurance, obtain the binary from a verifiable release and/or audit it before use.
功能分析
Type: OpenClaw Skill
Name: grantai-memory
Version: 1.3.0
The skill bundle requires the installation of external, opaque binaries (.pkg, .exe, .tar.gz) from a third-party domain (solonai.com) to function as an MCP server. While the stated purpose of providing persistent memory is plausible, directing users to execute external installers to enable agent capabilities is a high-risk supply chain pattern that could lead to arbitrary code execution. No explicit malicious instructions or exfiltration logic were found in the provided markdown, but the reliance on unverified external artifacts warrants a suspicious classification.
能力评估
Purpose & Capability
Name/description (persistent memory) match the declared requirement (grantai-mcp) and the SKILL.md tools (grantai_infer, grantai_teach, grantai_learn, etc.). Requiring a local mcp binary is expected for this integration.
Instruction Scope
SKILL.md limits actions to memory-related operations (store, recall, import directories, capture conversation turns). It also claims '100% local - data never leaves your machine' and AES-256 at rest; however, those guarantees are only as strong as the grantai-mcp binary/Docker image — the instructions do not provide any enforcement or verification steps (e.g., offline mode, no-telemetry flag, or reproducible checksums).
Install Mechanism
There is no install spec in the registry (instruction-only). SKILL.md points to downloads from solonai.com and a Docker image on ghcr.io (both reasonable hosts). Still, installation requires fetching and running third-party binaries/images — moderate risk unless you verify the releases or run in an isolated/containerized environment.
Credentials
The skill declares no environment variables, no credentials, and no config paths. That is proportionate for a local tool that runs as a coprocessor. NOTE: import commands (learn/git import) will access files you point them at — expected for the stated functionality.
Persistence & Privilege
always is false and autonomous invocation is allowed (the platform default). The skill does not request persistent agent-level privileges or changes to other skills. Wiring the tool into OpenClaw config is normal for an MCP-style integration.
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 grantai-memory - 安装完成后，直接呼叫该 Skill 的名称或使用
/grantai-memory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
v1.3.0
- Extends memory recall claim in documentation from "3 months ago" to "5 years ago" for greater clarity.
- Bumps version from 1.2.0 to 1.3.0.
- No functional or technical changes; documentation only.
v1.2.0
- Updated installation instructions with direct download links and package details for each OS.
- Removed shell script installation for macOS/Linux in favor of dedicated installers.
- Clarified installation steps for Docker, macOS, Windows, and Linux.
- No changes to skill functionality or usage.
v1.1.0
Major documentation update for version 1.1.0:
- Rewrote SKILL.md for clarity, usability, and modern OpenClaw config syntax
- Added clear installation instructions for macOS, Linux, Windows, and Docker
- Expanded tool list with new utility descriptions (e.g., grantai_capture, grantai_git, grantai_health, grantai_savings)
- Stressed exact-recall, 100% local storage, and agent memory sharing features
- Noted free automatic activation for OpenClaw users
- Included configuration examples and usage scenarios for better onboarding
v1.0.0
- Initial release of GrantAi Memory for OpenClaw agents.
- Enables persistent, encrypted memory across sessions with exact-recall (no vectors/RAG).
- Provides six tools: grantai_infer, grantai_teach, grantai_learn, grantai_summarize, grantai_project, and grantai_snippet.
- Supports multi-agent shared memory without extra configuration.
- Simple setup and integration instructions included.
元数据
常见问题
Grantai Memory 是什么？
Persistent memory for OpenClaw agents. Exact recall in milliseconds - your agent remembers everything across sessions. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 352 次。
如何安装 Grantai Memory？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install grantai-memory」即可一键安装，无需额外配置。
Grantai Memory 是免费的吗？
是的，Grantai Memory 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Grantai Memory 支持哪些平台？
Grantai Memory 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 Grantai Memory？
由 lgrant1234（@lgrant1234）开发并维护，当前版本 v1.3.0。
推荐 Skills