AgentDB Performance Optimization

A guide for improving AgentDB, a database that stores and searches numerical representations of data called vectors. It covers memory reduction, search indexing, caching, and grouped database operations.

In plain words
What is it for?
Use it to tune vector search, configure quantization, add HNSW indexes, use caching, batch operations, and run performance benchmarks.
Why use it?
It helps reduce memory use and improve search and insert speed when an AgentDB database becomes large or slow.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/aegntic/cldcde/agentdb-optimization
Any agent
npx skills add aegntic/cldcde --skill agentdb-optimization
Clone the repo
git clone --depth 1 https://github.com/aegntic/cldcde

Made for: Claude Code, Codex.

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,268 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.03268
Opus 5 $0.00026 $0.01634
Sonnet 5 $0.00011 $0.00654
Haiku 4.5 $0.00005 $0.00327

Measured 2d ago against content hash 0438ee74207a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

AgentDB Performance Optimization scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/agentdb-optimization/SKILL.md · 510 lines

How it starts

The opening of the file, as written. The whole thing — 510 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentDB Performance Optimization

What This Skill Does

Provides comprehensive performance optimization techniques for AgentDB vector databases. Achieve 150x-12,500x performance improvements through quantization, HNSW indexing, caching strategies, and batch operations. Reduce memory usage by 4-32x while maintaining accuracy.

Performance: <100µs vector search, <1ms pattern retrieval, 2ms batch insert for 100 vectors.

Prerequisites

  • Node.js 18+
  • AgentDB v1.0.7+ (via agentic-flow)
  • Existing AgentDB database or application

Quick Start

Run Performance Benchmarks

# Comprehensive performance benchmarking
npx agentdb@latest benchmark

# Results show:
# ✅ Pattern Search: 150x faster (100µs vs 15ms)
# ✅ Batch Insert: 500x faster (2ms vs 1s for 100 vectors)
# ✅ Large-scale Query: 12,500x faster (8ms vs 100s at 1M vectors)
# ✅ Memory Efficiency: 4-32x reduction with quantization

Enable Optimizations

import { createAgentDBAdapter } from 'agentic-flow/reasoningbank';

// Optimized configuration
const adapter = await createAgentDBAdapter({
  dbPath: '.agentdb/optimized.db',
  quantizationType: 'binary',   // 32x memory reduction
  cacheSize: 1000,               // In-memory cache
  enableLearning: true,
  enableReasoning: true,
});

Quantization Strategies

1. Binary Quantization (32x Reduction)

Best For: Large-scale deployments (1M+ vectors), memory-constrained environments Trade-off: ~2-5% accuracy loss, 32x memory reduction, 10x faster

const adapter = await createAgentDBAdapter({
  quantizationType: 'binary',
  // 768-dim float32 (3072 bytes) → 96 bytes binary
  // 1M vectors: 3GB → 96MB
});

Use Cases:

  • Mobile/edge deployment
  • Large-scale vector storage (millions of vectors)
  • Real-time search with memory constraints

Performance:

  • Memory: 32x smaller
  • Search Speed: 10x faster (bit operations)
  • Accuracy: 95-98% of original

2. Scalar Quantization (4x Reduction)

Read the full file on GitHub · 510 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 510 lines · 53 tokens per session scan A 0438ee74207a

Subscribe to this mod's changes

AgentDB Performance Optimization is a skill published in the GitHub repository aegntic/cldcde (11 stars, last pushed 6d ago), licensed MIT. It adds 53 tokens to every session and 3,268 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

hono-core

Hono ultrafast web framework fundamentals - routing, context, handlers, and response patterns for multi-runtime deployment.

bobmatnyc/claude-mpm-skills · 26 tokens

tauri-django-react

Agents should invoke this skill for Tauri + Django + React desktop apps, especially backend lifecycle, CORS/auth, frontend integration, mandatory light/dark theming, German/English i18n, build packaging, dual desktop/web deployment, Rust commands, and platform-specific gotchas.

Firstp1ck/pi-coding-agent-forge · 63 tokens

project-readme

Use when creating, updating, reviewing, restructuring, or harmonizing a repository's project README from verified local evidence for user-oriented or developer/library-oriented readers.

Firstp1ck/pi-coding-agent-forge · 35 tokens

subagent-governance

Delegation admissibility governance for a parent orchestrator. Use when deciding whether to launch, sequence, replace, or accept one or more delegated child runs while preserving role fit, plan-backed worker contracts, one-writer isolation, bounded retry safety, and reviewer finding disposition. Covers admissibility…

Firstp1ck/pi-coding-agent-forge · 74 tokens

html-report

Creates polished self-contained HTML explanation reports for complex, multi-step topics using overview tables, evidence cards, adaptive graphs or diagrams, meaningful SVG/media, and accessible tabs for long pages. Use when the user requests a browser-readable diagnostic report, technical guide, decision analysis…

Firstp1ck/pi-coding-agent-forge · 67 tokens

repo-explorer

Agents should invoke this skill before modifying unfamiliar codebases, answering where/how something is implemented, tracing dependencies, mapping repo structure, or planning changes. Explores a repository and returns a strict JSON handoff with key files, symbols, risks, and evidence.

Firstp1ck/pi-coding-agent-forge · 55 tokens