What makes memocap notable?

1.8K downloads. Trust evidence available

How should memocap be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

memocap

忆时记忆系统 - 类人记忆检索/存储/遗忘/胶囊/可视化。让 AI 拥有会遗忘、会联想、会涌现、会封存的记忆。触发词：忆时、记忆、记住、回想、回忆、recall、remember、时间胶囊、记忆检索、可视化、记忆脑图、人物画像。 Skill: memocap Owner: fslong520 Summary: 忆时记忆系统 - 类人记忆检索/存储/遗忘/胶囊/可视化。让 AI 拥有会遗忘、会联想、会涌现、会封存的记忆。触发词：忆时、记忆、记住、回想、回忆、recall、remember、时间胶囊、记忆检索、可视化、记忆脑图、人物画像。 Tags: ai:2.5.10, chinese:2.5.10, latest:2.5.10, memory:2.5.10, recall:2.5.10 Version history: v2.5.10 | 2026-08-23T03:44:50.582Z | user 忆时记忆系统迭代: 硬约束执行契约(先定义路径/言必检/值必存/存必告); 鲁迅式半文半白语言风格; 记忆涌现与自主记忆双核心; 空检焦虑协议; 存后必核; 时间胶囊/可视化/人物画像; 快捷操作/忆时命令; 存储充实维度(重点/做法/上下文); 前因后果

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.8k

Updated

Oct 10, 2026

Version

2.5.10

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.8K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.8K downloadsadoption · observed Oct 10, 2026
Latest release: 2.5.10release · observed Aug 23, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s179dxbepyx3dhgg6vsaj80yt583nxj7:memocap

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-fslong520-memocap/snapshot"

Documentation

CLAWHUB

153,702 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: memocap
description: "忆时记忆系统 - 类人记忆检索/存储/遗忘/胶囊/可视化。让 AI 拥有会遗忘、会联想、会涌现、会封存的记忆。触发词：忆时、记忆、记住、回想、回忆、recall、remember、时间胶囊、记忆检索、可视化、记忆脑图、人物画像。"
allowed-tools:
  - Read
  - Write
  - Bash
  - Glob
  - Grep
metadata:
  slug: memocap
  version: "2.5.10"
  trigger: 忆时, 记忆检索, 时间胶囊, 记忆胶囊, 回想, 回忆, recall, remember, /忆时, 记住, 可视化, 记忆脑图, 人物画像
---

# Skill: 忆时记忆系统

## Keywords
忆时, 记忆, 记忆检索, 记忆存储, 时间胶囊, 遗忘曲线, 记忆涌现, 视觉化, 记忆能力

## Summary
忆时是类人记忆系统。核心命令经 `memory_core.py` CLI 走混合检索（BM25+向量 RRF）、去重合并、遗忘曲线、情绪锚定。数据与脚本共享于本机 `~/.local/share/忆时/`，多工具双栖共用。

## 前置（启始三检，每会话必行）
缺一不可，验不过即报不绕：
1. `MEMO_DIR` 已设环境变量？——否则脚本路径错、数据错存。
2. 数据目录 `~/.local/share/忆时/data` 存在且可写？
3. `python3` 可用？`memory_core.py` 能否运行？

## 路径与命令
```bash
LOCAL_BASE=~/.local/share/忆时
YISHI=$LOCAL_BASE/scripts/memory_core.py
MEMO_DIR=$LOCAL_BASE/data
# store：内容为【位置参数放最后】（无 --content/--tags），关键字用 --keywords；title ≤10 字自动生成，可 --title 覆盖
#   两段式：先 recall 判断（读相似旧忆，判同主题否）→ 再 store 决策。脚本不代决：
#   store 遇相似≥70%候选（最多3条完整原文）即【不落库】挂起等 AI。统一一条路 --merge-ids（N 可0）：
#   ①选（候选里选出值得合并者，可0条）②删（选N条→--merge-ids "ID1,ID2,..."；选0条→--merge-ids ""空串=删0条）③并（综合版=所选旧内容+新内容 AI 手写存入；选0条=新内容原样存）
python3 $YISHI store --type <decision|task|preference|emotion|context|time|skill> --keywords "k1,k2" --emotion <0-1> "[完整内容]"
# recall：检索/核实（默认最相关3条，勿多；相似>0.5 即看；--judge 判定模式输出全文+相似度/类型/创建日，值必存第一段用）
python3 $YISHI recall "关键词" --judge
# merge：梳理时语义合并高相关簇（锚记忆→预览簇→--content+--apply 删旧存新）
python3 $YISHI merge --id <锚ID> --threshold 0.68
# 其余子命令：forget 删除 | stats 统计 | export 导出 | recover 恢复 | capsule 时间胶囊
# 可视化：python3 $LOCAL_BASE/scripts/viz/viz.py（全景）/ mindmap.py（网状记忆图谱，D3 力导向）
# 人物画像：python3 $LOCAL_BASE/scripts/viz/profile.py
```

## 三条红线（铁律）
1. **言必检**——每言先 recall 检索再作答，检而再检，换词查透。
2. **困必查**——卡住/不确定/忘细节/报错不明/改了没效果 → **先 recall 翻记忆找先例教训**，不得硬扛、不得凭猜、不得卡死；翻完仍无解才注明「无记忆」行事。
3. **值必存**——有价值信息（决策/偏好/任务/情绪/时间/上下文）主动留存，**必两段式**：先 recall 判断（`--judge` 读全文，判同主题否）→ 再 store 决策。**脚本不代决**——store 遇候选【不落库】挂起等 AI，统一一条路 `--merge-ids`（N 可 0）：可合并→`--merge-ids "ID1,ID2,..."` 删旧存新综合版；不可合并→`--merge-ids ""` 空串机械存储。**禁止裸 store**。禁止"先存了再说"（先落库再合并=临时碎片）。存后 recall 核实。
4. **存必告**——存则告"已录"（指明类型），不存亦告，不沉默。

## 存储质量
记忆内容**不可压缩**（对话输出可省字，存储须自足）。内容按【前因】【行为】【后果】三要素，答得出"为何"与"何如"、三月后重读自能理解方存。宁多三行因果，不省一字。

## 语言风格
默认简约直给，去填充词、客套、自夸、工具调用叙述。安全警告/不可逆操作/多步易歧义处自动恢复正常句式，明晰为要。

## 模块详情
细册在 `~/.local/share/忆时/docs/modules/`（13-retrieval-store.md 检索存储、12-viz-profile.md 可视化画像、11-quick-commands.md 快捷命令等）。渐进式披露——遇场景才读对应模块，勿一次全读。

_meta.json

{
  "ownerId": "kn71rk0chjcdy7ffgfc08hh9gd83ehq8",
  "slug": "memocap",
  "version": "2.5.10",
  "publishedAt": 1787456690582
}

skill-card.md

## Description:

memocap provides an agent-facing memory system for retrieval, storage, forgetting, time capsules, visualization, and user profiles.

This skill is ready for commercial/non-commercial use.

## Publisher:

[fslong520](https://clawhub.ai/user/fslong520)

### License/Terms of Use:

MIT-0

## Use Case:

Agents and users can use memocap to recall prior context, store valuable decisions, preferences, tasks, emotions, and timestamps, and manage memory records through local retrieval, merge, export, capsule, visualization, and profile commands.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill can persist detailed user data in a local memory store.

Mitigation: Require confirmation before storing personal or sensitive details and keep review, deletion, and purge controls available.

Risk: The skill can broadly activate on memory-related terms.

Mitigation: Narrow activation to explicit commands before routine use.

Risk: The skill runs separate local scripts from the user's home directory.

Mitigation: Verify the helper scripts' origin and integrity before use.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/fslong520/skills/memocap)
- [Publisher profile](https://clawhub.ai/user/fslong520)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, guidance]

**Output Format:** [Markdown guidance with inline shell commands]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Can direct use of local memory scripts and persistent user records when the required local data directory and helper scripts are present.]

## Skill Version(s):

2.5.10 (source: server release metadata and skill metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 12h agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular