Is the Agentdb Memory Patterns skill free?

Yes. The skill itself is free from spencermarx/open-code-review. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Agentdb Memory Patterns SkillProof Score?

7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.

How do I install Agentdb Memory Patterns?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Agentdb Memory Patterns with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Agentdb Memory Patterns

Persistent agent memory patterns and CLI workflow built on the AgentDB vector store

by spencermarx · spencermarx/open-code-review

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.6/10
Tested: Jul 31, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 84a3f10

Fetched SKILL.md; frontmatter parses with valid name+description and no bundled scripts (external CLI/npm deps only). Confirmed `agentdb` and `agentic-flow` exist on npm, then actually ran `npx agentdb@latest init ./agents.db` (created a 384-dim sql.js WASM DB) and `npx agentdb@latest stats ./agents.db` (printed Episodes/Embeddings/Skills counts) in a temp HOME — both match the documented commands. Could not do a real output-vs-baseline comparison: the TypeScript SessionMemory/storeFact/storePattern examples use an illustrative `db` pseudo-API, not the real `createAgentDBAdapter` API, so producing a verified working artifact needs the agentic-flow adapter plus an embeddings/training pipeline I did not run. The "Learn More" GitHub link 404s; performance multipliers (150x-12,500x) are unverified.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 5/10
Docs & honesty 4/5

What Agentdb Memory Patterns does

A reference skill for adding persistent memory to AI agents using the AgentDB vector database and its ReasoningBank adapter, covering session memory, long-term facts, pattern learning, and the agentdb CLI (init/query/stats/migrate). Triggers when building stateful agents, chat systems, or assistants that must remember context across sessions. The CLI commands work as documented, but the TypeScript memory-pattern examples target the agentic-flow adapter API rather than being drop-in runnable.

How to install Agentdb Memory Patterns

git clone --depth 1 https://github.com/spencermarx/open-code-review.git /tmp/agentdb-memory-patterns-src
mkdir -p ~/.claude/skills
cp -R /tmp/agentdb-memory-patterns-src/.claude/skills/agentdb-memory-patterns ~/.claude/skills/agentdb-memory-patterns
# Requires Node.js 18+. CLI is real: `npx -y agentdb@latest init ./agents.db` then `npx -y agentdb@latest stats ./agents.db` (verified working).
# API patterns need the package: `npm i agentic-flow` -> import { createAgentDBAdapter } from 'agentic-flow/reasoningbank'
# Optional MCP for Claude Code: `claude mcp add agentdb npx agentdb@latest mcp`
# Note: the "Learn More" GitHub link in the body (ruvnet/agentic-flow/tree/main/packages/agentdb) is 404.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Agentdb Memory Patterns

/agentdb-memory-patterns Persistent agent memory patterns and CLI workflow built on the AgentDB vector store

It also activates on plain-language prompts like these:

Add long-term memory to this chat agent
Store session context using AgentDB
Implement pattern learning for this assistant

Frequently asked questions

Is the Agentdb Memory Patterns skill free?: Yes. The skill itself is free from spencermarx/open-code-review. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agentdb Memory Patterns work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Works with setup. Fetched SKILL.md; frontmatter parses with valid name+description and no bundled scripts (external CLI/npm deps only). Confirmed `agentdb` and `agentic-flow` exist on npm, then actually ran `npx agentdb@latest init ./agents.db` (created a 384-dim sql.js WASM DB) and `npx agentdb@latest stats ./agents.db` (printed Episodes/Embeddings/Skills counts) in a temp HOME — both match the documented commands. Could not do a real output-vs-baseline comparison: the TypeScript SessionMemory/storeFact/storePattern examples use an illustrative `db` pseudo-API, not the real `createAgentDBAdapter` API, so producing a verified working artifact needs the agentic-flow adapter plus an embeddings/training pipeline I did not run. The "Learn More" GitHub link 404s; performance multipliers (150x-12,500x) are unverified.
What is the Agentdb Memory Patterns SkillProof Score?: 7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install Agentdb Memory Patterns?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Agentdb Memory Patterns with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.