Verified:GitHub

ReasoningBank with AgentDB

Implements adaptive agent learning with trajectory tracking, verdict judgment, and memory distillation on AgentDB.

Updated May 11, 2026

Search Tags:#vector database #reasoningbank #agentdb #memory distillation #experience replay #agent learning #trajectory tracking

Ready to run

npx skills add https://github.com/Turgunoff/mebellar_app --skill reasoningbank-with-agentdb-turgunoff

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ReasoningBank with AgentDB
Source: https://github.com/Turgunoff/mebellar_app/tree/main/.agents/skills/reasoningbank-agentdb
Command: npx skills add https://github.com/Turgunoff/mebellar_app --skill reasoningbank-with-agentdb-turgunoff

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires agentdb, agentic-flow.

What problem does it solve? Agents that cannot retain and reuse past experiences repeat mistakes and recompute solutions. This Skill provides a ReasoningBank implementation backed by AgentDB's vector database so agents can store experiences, judge outcomes, and retrieve relevant patterns for better decisions. ## Core Features & Use Cases - Trajectory Tracking & Verdict Judgment: Record sequences of agent actions with outcomes and judge whether new trajectories are likely to succeed based on similar past patterns. - Memory Distillation & Pattern Recognition: Consolidate similar experiences into distilled patterns using reasoning modules like PatternMatcher, ContextSynthesizer, MemoryOptimizer, and ExperienceCurator. - Use Case: A coding agent stores successful API optimization trajectories; when facing a new N+1 query problem, it retrieves similar past solutions with similarity scores and applies the proven approach. ## Quick Start Initialize an AgentDB database with npx agentdb init, then use the createAgentDBAdapter API to store and retrieve experience patterns for my agent.

Frequently Asked Questions about ReasoningBank with AgentDB

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I implement ReasoningBank adaptive learning with AgentDB?▼

Initialize a database with npx agentdb init, then use createAgentDBAdapter from agentic-flow/reasoningbank to insert experience patterns and retrieve them with retrieveWithReasoning. Enable learning and reasoning flags for the built-in reasoning modules.

How to migrate from legacy ReasoningBank to AgentDB?▼

Run npx agentdb migrate --source .swarm/memory.db to transfer existing data automatically. Verify the migration with npx agentdb stats on the new database file.

Is AgentDB compatible with the legacy ReasoningBank API?▼

Yes, AgentDB maintains 100% backward compatibility. Legacy functions like retrieveMemories, judgeTrajectory, and distillMemories work unchanged and automatically use the AgentDB backend.

What are the performance characteristics of AgentDB pattern retrieval?▼

AgentDB provides 150x faster pattern search (around 100µs), sub-millisecond memory retrieval with caching, and 500x faster batch inserts compared to the legacy backend.

Why are my ReasoningBank confidence scores low?▼

Low confidence often results from sparse or low-quality stored experiences. Enable context synthesis and MMR diversity in retrieveWithReasoning, and filter with minConfidence to surface only high-quality memories.