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#

bash

# 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#

text

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#

ModuleSizePurposeheartflow-engine.js69KBMain entry, 37 exportsdecision-verifier.js14KB5-dim scoring + self-verifymeaningful-memory.js33KB3-tier memory + forgettingself-healing.js5KBQ-learning from failuresguardian-system.js22KBHuman progress protectiondecision-execution-loop.js12KBDecision→Execute→Result→Learnenvironment-sensor.js11KBSensor registry + fusiontree-of-thoughts.js9KBMulti-branch reasoningself-reflection-memory.js15KBPost-hoc analysis → lessons

---

Based on Real Research#

PaperVenueContributionReflexionNeurIPS 2023RL from verbal reinforcementSelf-VerificationarXiv 2312.09210Inverse consistency checksCRITICICML 2023Self-correction via tool useConstitutional AIAnthropicSelf-critique loopsGenerative AgentsStanford 2022Memory stream simulationSelf-RewardarXiv 2403.00564Self-scoring upgrade selectionPlan-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#

bash

# For AI agents
clawhub install self-improving-agent

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