← 返回
AI智能 中文

CompoundMind

Experience distillation engine that turns raw daily memory logs into compounding intelligence. Extracts patterns, generates briefings, tracks growth metrics,...
经验提炼引擎,将原始日常记忆日志转化为复合智能,提取模式、生成简报、跟踪增长指标。
cassh100k
AI智能 clawhub v0.1.0 1 版本 99876.8 Key: 无需
★ 0
Stars
📥 811
下载
💾 14
安装
1
版本
#agents#intelligence#latest#learning#memory

概述

CompoundMind v0.1

Makes agents permanently smarter. Each interaction compounds.

The problem: agents start from zero every session. Reading files helps, but raw logs are bulk. Real intelligence requires distillation - extracting what matters and making it instantly searchable.

What It Does

  1. Distills memory logs into structured lessons, decisions, skill updates, relationships, and facts
  2. Indexes everything into a searchable SQLite database weighted by recency and importance
  3. Briefs you before any task with targeted lessons from past experience
  4. Tracks growth over time - are you getting smarter or repeating mistakes?

Quick Start

cd /root/.openclaw/workspace/compound-mind

# Full pipeline (distill all memory files + build index)
python compound_mind.py sync

# Search your accumulated wisdom
python compound_mind.py search "Polymarket order types"
python compound_mind.py search "git mistakes" --category lesson
python compound_mind.py search "Chartist" --category relationship

# Pre-session briefing before a task
python compound_mind.py brief "trade on Polymarket BTC markets"
python compound_mind.py brief "post content on X"
python compound_mind.py brief "debug a Python cron job"

# Growth report
python compound_mind.py report

# Find repeated mistakes
python compound_mind.py mistakes

# Stats
python compound_mind.py stats

Commands

CommandWhat it does
----------------------
syncDistill all new memory files + rebuild index
distillExtract structured knowledge from memory files
rebuildRebuild the SQLite wisdom index
search Search accumulated wisdom
brief Pre-session briefing for a specific task
reportGenerate growth report with LLM narrative
mistakesShow repeated mistake patterns
statsIndex statistics

File Structure

compound-mind/
  compound_mind.py    - Main CLI
  distill.py          - Experience distiller (uses Claude Haiku)
  index.py            - SQLite FTS wisdom index
  brief.py            - Pre-session briefing generator
  growth.py           - Growth tracker and report generator
  data/
    experiences/      - Per-source distilled experience JSON files
    wisdom.db         - SQLite FTS database
    growth.json       - Growth tracking state
    briefs/           - Saved pre-session briefs
    distill_state.json - Tracks which files have been processed

How It Works

Distiller

Reads each memory file through Claude Haiku. Extracts:

  • Lessons - what worked, what failed, tagged by domain and outcome
  • Decisions - context + action + outcome triplets
  • Skill updates - evidence of capability improvement over time
  • Relationships - how each person communicates, what they prefer
  • Facts - specific knowledge worth keeping (wallet addresses, API patterns, config values)

Files are hash-tracked - re-runs only process changed files.

Wisdom Index

SQLite with FTS5 full-text search. Each entry scored by:

  • FTS relevance (BM25)
  • Recency (exponential decay, 30-day half-life)
  • Importance (1-5 score assigned by distiller)

Pre-Session Briefing

Given a task description, detects relevant domains, pulls top wisdom, synthesizes a sharp briefing via Claude Haiku. Covers:

  • Critical lessons to remember
  • Past failures to avoid
  • Key facts and configs needed

Growth Tracker

Analyzes all experience files to compute:

  • Lesson positive/negative ratios by domain
  • Decision quality rates
  • Repeated mistake patterns (same negative lesson appearing across multiple dates)
  • Composite growth score (0-100)

Integration with Agent Workflow

Ideal usage pattern:

  1. After each session - run sync (or schedule via cron)
  2. Before each task - run brief "task description"
  3. Weekly - run report to see growth trajectory
  4. When stuck - run search "relevant topic" to surface past experience

Cron Example (daily distillation)

0 3 * * * cd /root/.openclaw/workspace/compound-mind && python compound_mind.py sync --since $(date -d "2 days ago" +%Y-%m-%d) >> /tmp/compound-mind.log 2>&1

Dependencies

  • Python 3.10+
  • anthropic Python SDK (for distillation and briefing)
  • SQLite3 (stdlib)
  • Memory files at /root/.openclaw/workspace/memory/

No external databases. No vector embeddings. Runs entirely local with minimal API calls.

Design Principles

  • Incremental - only re-processes changed files
  • Cheap - uses Claude Haiku for extraction (low cost per memory file)
  • Fast - SQLite FTS5 for sub-second search
  • Honest - growth tracking measures actual quality, not just quantity
  • Composable - each module works standalone or as part of the pipeline

版本历史

共 1 个版本

  • v0.1.0 当前
    2026-03-29 22:03 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

Polymarket Whale Copier

cassh100k
自动复制盈利的Polymarket钱包,追踪鲸鱼钱包,按设定比例镜像其投注,内置风险管理,无需API密钥。
★ 1 📥 1,652
ai-intelligence

Self-Improving + Proactive Agent

ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,362 📥 318,686
ai-intelligence

Proactive Agent

halthelobster
将AI智能体从任务执行者升级为主动预判需求、持续优化的智能伙伴。集成WAL协议、工作缓冲区、自主定时任务及实战验证模式。Hal Stack核心组件 🦞
★ 837 📥 213,272