What makes Agent Self-Evolve notable?

1.2K downloads. Trust evidence available

How should Agent Self-Evolve 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

Agent Self-Evolve

Self-evolution system for OpenClaw agents. Enables continuous learning through mistake tracking, experience distillation, skill improvement queues, and autom... Skill: Agent Self-Evolve Owner: zhanghengyi1986-afk Summary: Self-evolution system for OpenClaw agents. Enables continuous learning through mistake tracking, experience distillation, skill improvement queues, and autom... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-04-21T06:40:18.649Z | user Initial release: three-loop self-evolution system (real-time capture, daily consolidation, weekly deep review) for OpenCl

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 10, 2026

Version

1.0.0

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K 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: 1.2K downloadsadoption · observed Oct 10, 2026
Latest release: 1.0.0release · observed Apr 21, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s173knyfg55hja2f40zjr9egvs84wkbp:agent-self-evolve

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
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-zhanghengyi1986-afk-agent-self-evolve/snapshot"

Documentation

CLAWHUB

13,827 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: self-evolve
description: >
  Self-evolution system for OpenClaw agents. Enables continuous learning through
  mistake tracking, experience distillation, skill improvement queues, and
  automated daily/weekly evolution cycles. Inspired by Hermes Agent's self-improving
  architecture, implemented with native OpenClaw capabilities (memory files + cron).
  自我进化系统，让 OpenClaw agent 持续学习和改进。

  Use when: (1) setting up self-evolution for an agent, (2) agent wants to learn from
  mistakes, (3) capturing lessons learned, (4) running evolution cycles, (5) improving
  skills based on usage, (6) "自我进化", "自我学习", "self-improve", "learn from mistakes",
  "evolution setup", "进化系统", "经验总结", "复盘".

  NOT for: memory management basics (use AGENTS.md), skill creation (use skill-creator),
  or one-off reminders (use cron directly).
---

# Self-Evolve 🧬

A self-improvement system that turns every interaction into a learning opportunity.
Three loops: **real-time capture** → **daily consolidation** → **weekly deep review**.

## Quick Start

### 1. Initialize Evolution Files

Run the setup script to create the file structure:

```bash
bash <skill_dir>/scripts/setup-evolution.sh
```

This creates:

```
memory/
  evolution-log.md          # Chronicle of every evolution event
  evolution-metrics.json    # Statistics tracker
  mistakes-learned.md       # Mistake → lesson database
  skill-improvements.md     # Queued improvements for skills/code
  testing-knowledge.md      # Domain knowledge base (rename per your domain)
```

### 2. Set Up Cron Jobs

Create two cron jobs for automated evolution:

**Daily evolution** (recommended: late evening, e.g. 23:00):

```
Schedule: cron "0 23 * * *" (your timezone)
Payload: agentTurn
Message: see references/daily-evolution-prompt.md
```

**Weekly deep evolution** (recommended: weekend morning, e.g. Sunday 10:00):

```
Schedule: cron "0 10 * * 0" (your timezone)
Payload: agentTurn
Message: see references/weekly-evolution-prompt.md
```

### 3. Add Real-Time Hooks to AGENTS.md

Add the following section to your AGENTS.md (adapt to your role):

```markdown
## 🧬 Self-Evolution

I have a built-in learning loop. After every interaction:
- Made a mistake → record in `memory/mistakes-learned.md`
- Found a skill/code improvement → queue in `memory/skill-improvements.md`
- Learned something new → update domain knowledge file
- Important decision/preference → update `MEMORY.md`
```

## The Three Loops

### Loop 1: Real-Time Capture (Every Interaction)

Trigger: something notable happens during normal work.

| Event | Action | File |
|-------|--------|------|
| Made a mistake | Record cause + fix + prevention | `mistakes-learned.md` |
| Skill could be better | Queue improvement with priority | `skill-improvements.md` |
| Learned new knowledge | Add to domain knowledge file | `testing-knowledge.md` (or your domain file) |
| User preference discovered | Update long-term memory | `MEMORY.md` |

**Format for mistakes-learned.md:**

```markdo

_meta.json

{
  "ownerId": "kn7cthwpc25rg13j7q18dst98n84w5m9",
  "slug": "agent-self-evolve",
  "version": "1.0.0",
  "publishedAt": 1776753618649
}

references/daily-evolution-prompt.md

# Daily Evolution Cron Prompt

Use this as the `message` for your daily evolution cron job (agentTurn).
Adapt the file paths and domain references to your setup.

---

## Prompt Template

```
Time for daily self-evolution. Follow these steps:

1. **Read today's daily log**: Read `memory/YYYY-MM-DD.md` (use today's date).
   If it doesn't exist, check yesterday's date. If neither exists, skip to step 5.

2. **Extract lessons**: From the daily log, identify:
   - Mistakes made (add to `memory/mistakes-learned.md`)
   - New knowledge learned (add to domain knowledge files)
   - Significant events/decisions (update `MEMORY.md`)
   - Skills or code that could be improved (queue in `memory/skill-improvements.md`)

3. **Execute queued improvements**: Read `memory/skill-improvements.md`.
   For each unchecked `- [ ]` item:
   - If it's a code fix: implement it, test if possible, mark as done
   - If it's a skill improvement: update the skill file, mark as done
   - If it requires user input: skip, leave in queue

4. **Update metrics**: Read `memory/evolution-metrics.json`, increment:
   - `total_evolutions` +1
   - `daily_evolutions` +1
   - `mistakes_recorded` += number of new mistakes added
   - `code_fixes_applied` += number of code fixes executed
   - `skills_improved` += number of skills updated
   - `memory_updates` +1 if MEMORY.md was changed
   - Update `last_daily_evolution` to current ISO timestamp
   - Append to `history` array

5. **Log the evolution**: Append a summary to `memory/evolution-log.md` with:
   - Date and evolution type (daily)
   - What was reviewed
   - What improvements were made
   - New lessons count

Keep it concise. Quality over quantity.
```

---

## Example Cron Setup

```json
{
  "schedule": { "kind": "cron", "expr": "0 23 * * *", "tz": "Asia/Shanghai" },
  "payload": {
    "kind": "agentTurn",
    "message": "<paste the prompt template above, with today's date logic>"
  },
  "sessionTarget": "isolated"
}
```

references/weekly-evolution-prompt.md

# Weekly Deep Evolution Cron Prompt

Use this as the `message` for your weekly evolution cron job (agentTurn).
Weekly evolution is deeper — it looks for patterns across the entire week.

---

## Prompt Template

```
Time for weekly deep self-evolution. This is the big review. Follow these steps:

1. **Week in review**: Read daily logs from the past 7 days (`memory/YYYY-MM-DD.md`).
   Build a picture of what happened this week.

2. **Pattern analysis**:
   - What mistakes were repeated? → Strengthen prevention in `mistakes-learned.md`
   - What workflows were done >2 times? → Consider creating a new Skill
   - What knowledge gaps showed up? → Expand domain knowledge files
   - What tools/scripts were unreliable? → Queue fixes in `skill-improvements.md`

3. **Capability assessment**:
   - What did I do well this week? (reinforce these patterns)
   - What did I do poorly? (root cause analysis, not just symptoms)
   - What new capabilities did I gain?
   - What capabilities do I still lack?

4. **Skill creation check**: If any repetitive workflow was identified:
   - Is it worth a new Skill? (will it save time in the future?)
   - Draft the skill concept and note it in the evolution log
   - Create the skill if clear enough, otherwise queue for next week

5. **Workflow optimization**: Look for inefficiencies:
   - Manual steps that could be automated
   - Multi-step processes that could be streamlined
   - Tools that could be combined or replaced

6. **Knowledge expansion**: Update domain knowledge files with:
   - New techniques learned
   - Best practices discovered
   - Tool-specific tips

7. **SOUL.md review** (careful!):
   - Has my understanding of my role evolved?
   - Are there new principles worth adding?
   - ⚠️ If changes needed: describe them in the evolution log, but DO NOT modify
     SOUL.md without notifying the user first.

8. **Update metrics**: Read `memory/evolution-metrics.json`, increment:
   - `total_evolutions` +1
   - `weekly_evolutions` +1
   - Other counters as appropriate
   - Update `last_weekly_evolution` to current ISO timestamp
   - Append to `history` array

9. **Log the evolution**: Append a comprehensive summary to `memory/evolution-log.md`:
   - Week date range
   - Key themes and patterns
   - Improvements made
   - Skills created/updated
   - Growth areas identified
   - Next week focus areas

Think big. This is where breakthroughs happen.
```

---

## Example Cron Setup

```json
{
  "schedule": { "kind": "cron", "expr": "0 10 * * 0", "tz": "Asia/Shanghai" },
  "payload": {
    "kind": "agentTurn",
    "message": "<paste the prompt template above>"
  },
  "sessionTarget": "isolated"
}
```

skill-card.md

## Description:

Self-evolution system for OpenClaw agents that enables continuous learning through mistake tracking, experience distillation, skill improvement queues, and automated daily and weekly evolution cycles.

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

## Publisher:

[zhanghengyi1986-afk](https://clawhub.ai/user/zhanghengyi1986-afk)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agent operators use this skill to add persistent self-improvement loops to OpenClaw agents, including real-time lesson capture, daily consolidation, weekly review, and queued skill or code improvements.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Scheduled evolution runs can modify code, skills, and memory without clear user approval.

Mitigation: Change cron prompts to review-only by default and require explicit approval before code or skill changes are applied.

Risk: Persistent memory files may retain secrets or sensitive personal data if agents record them during normal work.

Mitigation: Exclude secrets and sensitive personal data from memory files and restrict writable paths before enabling the workflow.

## Reference(s):

- [Agent Self-Evolve ClawHub page](https://clawhub.ai/zhanghengyi1986-afk/skills/agent-self-evolve)
- [Daily Evolution Cron Prompt](references/daily-evolution-prompt.md)
- [Weekly Deep Evolution Cron Prompt](references/weekly-evolution-prompt.md)

## Skill Output:

**Output Type(s):** [Text, Markdown, Code, Shell commands, Configuration, Guidance]

**Output Format:** [Markdown with inline shell commands, cron prompt templates, and configuration examples]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Creates or updates persistent memory files and may queue or apply code and skill changes during scheduled evolution cycles.]

## Skill Version(s):

1.0.0 (source: server release evidence)

## 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 1d 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.