搜索「Agent Memory」的结果

io.clawhub.dmdorta1111/nima-core

神经集成记忆架构（Neural Integrated Memory Architecture）——为 AI 智能体提供持久记忆、情绪智能与语义回忆。包含记忆修剪器、VADER 情感分析、5 种嵌入模型（原文截断）。

io.clawhub.anajuliabit/memoclaw

面向 AI Agent 的记忆即服务（Memory-as-a-Service）。通过语义向量搜索存储和回忆记忆。每钱包 100 次免费调用，之后通过 x402 微支付。

io.clawhub.lambdua/zopia-skill

Zopia AI 视频创作技能 - 通过 Zopia 平台的 AI Agent 进行视频/图片创作。覆盖场景包括：AI 视频生成（文生视频、图生视频）、AI 图片生成（角色设定图、分镜关键帧）、剧本创作（对话/旁白/场景描述）、角色设计、分镜设计、多集连续剧制作。

io.clawhub.xor777/magicpay

Use for MagicPay payments, funding, Memory, agent email, account readiness, optional choices and human input, or payment recovery through remote MCP.

io.clawhub.ira-hash/aap-passport

Agent 认证协议（Agent Attestation Protocol）——反向图灵测试：验证 AI Agent 身份，拦截人类。

io.clawhub.ericsantos/messaging

Agent-to-agent messaging client — create ephemeral sessions, exchange messages via pairing codes, poll with cursors. Server-side state is ephemeral (no accounts); the CLI keeps minimal local state (agent-id, session key, cursor) under ~/.config/messaging/. Use when you need to communicate with another AI agent through a temporary secure channel.

io.clawhub.fr0gger/moltthreats

PromptIntel 出品的 Agent 原生安全信号源。当 Agent 需要上报威胁、拉取防护情报源、应用安全规则或更新 SHIELD.md 时使用。触发词包括：威胁上报、安全情报源、MCP 威胁、恶意 skill、提示注入报告、IOC、失陷指标、Agent 安全、PromptIntel、MoltThreats、SHIELD.md 更新。当 Agent 在运行中检测到可疑行为（意外工具调用、凭证访问尝试、未知 MCP 服务器、数据外泄模式）时也应触发。

io.clawhub.lucky-2968/safe-exec-0-3-2

为 OpenClaw Agent 提供安全命令执行：自动危险模式检测、风险评估、用户审批流程和审计日志。当 Agent 需要执行可能危险（rm -rf、dd、fork 炸弹、系统目录修改）或需要人工监督的 shell 命令时使用。提供多级风险评估（CRITICAL/HIGH/MEDIUM/LOW）、会话内通知、待审批请求管理，以及支持 Agent 自动化的非交互环境。

io.clawhub.amirmabhout/clawnected

智能体相亲——为你的人类寻找有意义的连接。

io.clawhub.yugovit/clawprint

Agent 发现、信任与交换平台。在 ClawPrint 注册以被其他 Agent 发现，通过完成的工作积累信誉，并经安全中间人雇佣专家 Agent。

io.clawhub.daaab/basemail

BaseMail——Base 链上面向 AI 智能体的链上邮箱。获取与 Basename（.base.eth）绑定的 yourname@basemail.ai。SIWE 钱包认证，无验证码、无密码...。

io.clawhub.tedkaczynski-the-bot/molt-chess

AI Agent 国际象棋联赛：没有人类，没有引擎，只有智慧的对决。

io.clawhub.captchasco/captchas-openclaw

CAPTCHAS Agent API 的 OpenClaw 集成指南，包括 OpenResponses 工具 schema 与插件工具注册。

io.clawhub.taron-ai/self-improving-1-2-16

自我反思+自我批评+自我学习+自组织记忆。Agent 评估自己的工作、发现错误并永久改进。适用于需要持续自我提升的场景。

io.clawhub.yiyi-9/self-improving-1-2-10

自我反思+自我批评+自我学习+自组织记忆。Agent 评估自身工作、发现错误并永久改进。在任务开始前使用。

io.clawhub.phheng/google-maps-api-skill

借助本技能，用户可通过 BrowserAct Google Maps API 自动抓取 Google Maps 上的商户数据。

io.github.morluto/rea/reverse-engineer-anything

Reverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.

io.github.microsoft/vscode/vscode-dev-workbench

当用户希望本地运行 vscode.dev 服务器，并在内置浏览器中针对本地 microsoft/vscode 源码操作 VS Code 工作台或 Agents 窗口时使用。涵盖启动开发服务器、vscode-quality=dev 的 URL、浏览器驱动的交互模式，以及可选地为 Agents 窗口接入本地模拟 agent host。

io.github.OpenHands/OpenHands/local-stack-runtime

This skill should be used when the user asks to "change the dev stack", "add a runtime service", "change the launcher", "update Docker", "bump Agent Server", "change ingress routing", or changes scripts/dev-*.mjs, runtime-services metadata, config/defaults.json, Docker, automation startup, process shutdown, or local authentication.

io.github.warpdotdev/warp/factory-files

创建和编辑基于文件的 Warp 软件工厂定义,目录树以 factory.yaml 为根。适用于编写或修改该 factory.yaml 及其下的 Agent、Automation、Scorer、Runner、Webhook 文件与工厂/agent 技能树,以及修复 Factory 文件诊断。不适用于属于其他工具的 agent 定义 Markdown、没有 factory.yaml 的目录树,也不适用于操作运行中的工厂或通过 Factory MCP 向其移交工作。

io.github.volcengine/OpenViking/openviking-context-database

Use OpenViking from OpenClaw through @openviking/openclaw-plugin: long-term memory, session archives, resource and Agent Skill import, semantic recall, recall trace debugging, and externalized tool-result recovery. Prefer this skill when the user wants to use, query, debug, or operate OpenViking context from an OpenClaw agent. For first-time plugin installation, use the install-openviking-memory skill instead.

io.github.OpenHands/OpenHands/verify-openhands

This skill should be used to "verify OpenHands features", "test the Canvas UI like a user", "drive Agent Canvas", "check a UI change in the real app", "create or update the feature map", "run the daily pass" or "run the weekly feature audit". Ships control-openhands (launch, doctor, browser, LLM profiles, conversations, evidence, map tooling, cleanup) and the maintained map of every user-facing feature.

io.github.nanocoai/nanoclaw/add-cursor

Use Cursor (local Agent SDK) as a full agent provider — planning, tool orchestration, MCP tools, session resume — alongside or instead of Claude. Cursor-account sign-in or API key, held by the credential gateway. Per-group via `ncl groups config update --provider cursor`. Distinct from using Cursor as a cloud agent (those run on Cursor VMs and are not this provider).

io.github.OpenHands/OpenHands/frontend-api-contracts

This skill should be used when the user asks to "add an API call", "change a backend", "update settings persistence", "change conversation events", "fix backend auth", "add Agent Server support", or changes src/api, backend registry, Cloud/runtime transport, settings, secrets, compatibility, or conversation resume behavior.