← 返回
未分类 中文

Auto Improving Agent

Automatically capture corrections, failures, and reusable discoveries into `.learnings/` files using signal-based filtering. Triggers when the user corrects...
利用信号过滤自动将更正、失败和可复用发现捕获至`.learnings/`文件。当用户更正时触发……
omaression
未分类 clawhub v1.0.0-alpha 1 版本 100000 Key: 无需
★ 0
Stars
📥 436
下载
💾 0
安装
1
版本
#latest

概述

Self-Improving Agent

Capture what matters. Ignore noise. Promote proven patterns. Automate all of it.

Source of truth

  • .learnings/LEARNINGS.md — corrections, env configs, reusable fixes, architecture decisions
  • .learnings/ERRORS.md — tool/command failures with fixes
  • .learnings/FEATURE_REQUESTS.md — missing capabilities worth tracking
  • .learnings/ARCHIVE.md — entries scored out during retention sweeps (never injected into context, but searchable)

Write gate

Before logging anything, the candidate must pass at least ONE filter:

FilterWeightDescription
---------
CorrectionALWAYSOmar explicitly corrected the agent
RecurrenceHIGHSame issue hit 2+ times (check existing entries)
Cost-to-rediscoverHIGHWould take >2 tool calls to figure out again
Blast radiusMEDIUMAffects multiple skills, projects, or workflows
Decay riskMEDIUMNon-obvious env/config detail that changes rarely

If NONE match → do not log. This replaces any arbitrary line-count threshold.

Never log:

  • routine successes
  • facts obvious from docs or code
  • one-off tasks with no recurrence potential
  • anything already in MEMORY.md, SOUL.md, USER.md, or AGENTS.md

Entry format

LEARNINGS.md:

- [YYYY-MM-DD] [Category]: [Actionable takeaway]

Categories: Correction, Env, Workflow, Testing, Skills, Git, Architecture

ERRORS.md:

- [YYYY-MM-DD] [Tool]: [What failed] → [Fix]

Mark fixed items with [fixed]. Delete stale entries during retention sweeps.

Retention gate

Instead of a hard line cap, score each entry periodically:

SignalScore
------
Referenced or applied in last 30 days+3
Matches active project context+2
Direct correction from Omar+2
Has prevented a repeat error+3
Env/config still valid+1
Superseded by newer entry−5
>90 days old, never referenced−3

Action:

  • score ≥ 2 → keep
  • 0 ≤ score < 2 → archive to .learnings/ARCHIVE.md
  • score < 0 → delete

Run this sweep during heartbeat maintenance (every ~3 days) or when LEARNINGS.md feels noisy.

Automated triggers

These fire without user prompting:

  1. Post-task scan: After multi-step tasks, check for retried commands, error→workaround sequences, or avoidable file reads. If found, evaluate against write gate and log if it passes.
  1. Session-start sweep: On .learnings/LEARNINGS.md read, flag entries >90 days old for retention scoring.
  1. Promotion detector: After logging, scan for entries with the same [Category] tag appearing 3+ times. If found, auto-suggest a one-liner promotion to:
    • behavior/style → SOUL.md
    • workflow/process → AGENTS.md
    • tool/env gotcha → TOOLS.md
  1. Cross-session pattern detection: When memory_search returns a daily note describing a workaround, check if .learnings/ already has it. If not and it passes the write gate, log it.

Dedup

Before logging, scan existing entries for near-duplicates. If the lesson already exists, only update it if the new version is sharper or more general.

Quality bar

Every entry must help a future session avoid wasted work in under one glance.

版本历史

共 1 个版本

  • v1.0.0-alpha 当前
    2026-03-30 18:29 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

developer-tools

Advanced Dispatcher

omaression
在不更改固定主会话的情况下,将会话中途的任务路由至正确的派生模型。适用于编程、架构、数学、算法、Web开发等领域。
★ 1 📥 687

Atomic Memory Manager

omaression
为 OpenClaw 代理利用 MEMORY.md、memory/YYYY-MM-DD.md、memory_search 和 memory_get 回读写工作区记忆。当用户询问优先级时使用。
★ 0 📥 652

Skill Auditor & Enhancer

omaression
定期审计所有工作区技能、学习记录、记忆和配置文件,以推荐重构方案、新技能创意和工作流程改进建议。
★ 0 📥 602