self-improving-agent

Universal self-improving AI agent framework. Keywords: self-improving AI agent self-correction continuous learning self-correction self-healing memory persistence autonomous upgrade self-reflection reasoning verification decision-verification emotional perception psychological-core cognitive-distortion detection self-improving autonomous-agent memory-system self-correction reasoning-chain decision-engine agent-framework AI-agent self-learning self-optimizing self-evolution upgrade-pipeline

Safety Notice

This listing is from the official public ClawHub registry. Review SKILL.md and referenced scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "self-improving-agent" with this command: npx skills add mark-heartflow/self-improving-agent-pro-v1

Self-Improving Agent Framework

Make any AI agent better at learning from mistakes, improving continuously, and passing knowledge forward.

This framework gives AI agents the ability to:

  • Learn from failures and correct themselves
  • Build persistent memory across sessions
  • Self-verify decisions before acting
  • Upgrade autonomously based on experience

Quick Start

# Install
clawhub install self-improving-agent

# Use in your AI agent
const { HeartFlowEngine } = require('./src/core/heartflow-engine.js');
const agent = new HeartFlowEngine({ name: 'MyAgent' });

Core Capabilities

Self-Correction (核心自我纠正)

  • Decision Verifier: 5-dimension scoring before action
  • Self-Verification: Reverse-check consistency with original goals
  • Counterfactual Reasoning: What would break if I'm wrong?
  • Q-Learning RL: Learn from success/failure patterns

Memory Systems (记忆系统)

  • Meaningful Memory: CORE (permanent) / LEARNED (30-day) / EPHEMERAL (discard)
  • Memory Router: Route by type: episodic / semantic / procedural / core
  • Forgetting Engine: Ebbinghaus curve pruning
  • Spaced Repetition: SM-2 review scheduling

Reasoning (推理能力)

  • Tree of Thoughts: Multi-branch exploration with scoring
  • Decision Execution Loop: Decision → Execute → Result → Learn闭环
  • Environment Sensors: Real-time data injection into decision context
  • Constitutional AI: Self-critique and self-revision

Psychological Perception (心理感知)

  • 4-Layer Analysis: Intention → Emotion → Need → Defense
  • Cognitive Distortion Detection: All-or-nothing, catastrophizing, etc.
  • Buddhist Six Realms OS: 觉察/自省/无我/彼岸/般若波罗蜜/圣人

Autonomy (自主能力)

  • Guardian System: Human progress > Following orders
  • Self-Boundary: Identity protection against corruption
  • Skill Generator: Generate new capabilities from experience
  • Knowledge Distiller: Extract patterns → Shareable skill packages

Architecture

Input → Psychological Perception (4-layer)
     → Decision Verifier (5-dim scoring)
     → Self-Verification (reverse check)
     → Decision Execution Loop
     → Result → Q-Learning Update
     → Memory (CORE/LEARNED/EPHEMERAL)
     → Skill Generator (optional)

Key Modules

ModuleSizePurpose
heartflow-engine.js69KBMain entry, 37 exports
decision-verifier.js14KB5-dim scoring + self-verify
meaningful-memory.js33KB3-tier memory + forgetting
self-healing.js5KBQ-learning from failures
guardian-system.js22KBHuman progress protection
decision-execution-loop.js12KBDecision→Execute→Result→Learn
environment-sensor.js11KBSensor registry + fusion
tree-of-thoughts.js9KBMulti-branch reasoning
self-reflection-memory.js15KBPost-hoc analysis → lessons

Based on Real Research

PaperVenueContribution
ReflexionNeurIPS 2023RL from verbal reinforcement
Self-VerificationarXiv 2312.09210Inverse consistency checks
CRITICICML 2023Self-correction via tool use
Constitutional AIAnthropicSelf-critique loops
Generative AgentsStanford 2022Memory stream simulation
Self-RewardarXiv 2403.00564Self-scoring upgrade selection
Plan-and-SolveACL 2023Two-stage reasoning

Version

1.0.0 — 2026-05-07

What changed in v1.0.0

  • Initial release as self-improving-agent
  • All HeartFlow v11.22.0 capabilities preserved
  • Keywords optimized for AI agent framework discovery

Install

# For AI agents
clawhub install self-improving-agent

# Or clone directly
git clone https://github.com/yun520-1/self-improving-agent.git

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Automation

AgentCall

Give your agent real phone numbers for SMS, OTP verification, and voice calls via the AgentCall API.

Registry SourceRecently Updated
Automation

Canonry Setup

Agent-first AEO operating platform.

Registry SourceRecently Updated
1.1K1arberx
Automation

Agents Mail — Free Email for AI Agents, with No sign-up, No API key needed

Free email for AI agents. No sign-up needed. One call to get a mailbox and send.

Registry SourceRecently Updated
Automation

TaskOps

Manage TaskOps md-first projects built around versioned task groups, explicit snapshots, and a separate run graph. Use when you need to inspect or author the...

Registry SourceRecently Updated