Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

AgentDB Performance Optimization

A tuning playbook for AgentDB vector databases: quantization, HNSW parameters, caching, batching and pruning.

Dev & CodingIntermediate★ 371⑂ 36AI score 7/10Last updated: Jul 28, 2026

What it does

  • Configures the AgentDB adapter (agentic-flow/reasoningbank) for your performance goal.
  • Compares four quantization modes — binary (32x smaller), scalar (4x), product (8–16x), none — with explicit accuracy trade-offs.
  • Recommends HNSW parameters (M, efConstruction, efSearch) by dataset size, from <10K to >1M vectors.
  • Covers cache sizing and LRU hit-rate monitoring, batch inserts, parallel retrieval, pattern consolidation and pruning.
  • Ships four ready-to-paste recipes: max speed, balanced, max accuracy, and memory-constrained (mobile/edge), plus a troubleshooting section.

Who it's for

  • Developers running agent memory on AgentDB / agentic-flow.
  • Teams whose vector count grew into the hundreds of thousands or millions and are hitting latency or RAM limits.
  • Anyone shipping vector search to edge or mobile targets.

Example uses

  1. "1M vectors are using 3GB" → get binary quantization + cacheSize 2000 + hnswM 32 to bring it near 96MB.
  2. "Search takes 150ms" → tune efSearch and k, grow the cache, and verify with npx agentdb@latest stats.
  3. "Inserting 100 docs takes a second" → replace per-item inserts with the batch pattern shown.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/spencermarx/open-code-review/HEAD/.claude/skills/agentdb-optimization/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the .claude/skills/agentdb-optimization folder from the GitHub repo spencermarx/open-code-review into my ~/.claude/skills/agentdb-performance-optimization/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/spencermarx/open-code-review.git && mkdir -p ~/.claude/skills && cp -r open-code-review/.claude/skills/agentdb-optimization ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/spencermarx/open-code-review.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r open-code-review/.claude/skills/agentdb-optimization ~/.claude/skills/
  5. Prerequisites: Node.js 18+ and AgentDB v1.0.7+ (via agentic-flow).
  6. Restart Claude Code and ask something like "reduce my AgentDB memory usage" to trigger the skill.
  7. Before applying changes in production, measure your own numbers with npx agentdb@latest benchmark and stats rather than trusting the documented benchmark table.
View source on GitHub ↗License: Apache-2.0