A decision-memory agent that stores completed decisions, retrieves similar past decisions, and extracts repeated patterns from them. It is part of AITS, a system for structured decision analysis.

Use it to archive decisions after they are combined, find comparable earlier decisions before a new analysis, and identify recurring lessons.

It helps you reuse relevant past work instead of starting every analysis from scratch. It can also reveal patterns that recur across decisions.

aits-memory — Agent for Claude Code by fabiolalli/aits-agents

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add fabiolalli/aits-agents

Claude Code

/plugin install aits

Made for: Claude Code.

Or install aits, the plugin that ships this one along with the rest of its 4 commands, 12 agents, 3 hooks, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/fabiolalli/aits-agents/aits-memory/github.svg)](https://agentmods.dev/agents/fabiolalli/aits-agents/aits-memory)

Your own site

<a href="https://agentmods.dev/agents/fabiolalli/aits-agents/aits-memory"><img src="https://agentmods.dev/badge/agents/fabiolalli/aits-agents/aits-memory/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/fabiolalli/aits-agents/aits-memory"><img src="https://agentmods.dev/badge/agents/fabiolalli/aits-agents/aits-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,999 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00084	$0.02999
Opus 5.5	$0.00034	$0.01200
Sonnet 5.5	$0.00017	$0.00600
Haiku 4.5	$0.00008	$0.00300

Measured 3d ago against content hash 53b646113a03, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

aits-memory scanned grade B with 1 finding 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 3d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

3. If both are empty, look for the folder once with `ls -d ~/.claude/plugins/cache/*/aits/*/ ~/.claude/plugins/marketplaces/*/plugins/aits/ 2>/dev/null | head -1`, and use `$HOME/.claude/` only if nothing is found (files

plugins/aits/agents/aits-memory.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Path Resolution (plugin install)

Files referenced as references/..., playbooks/..., graphs/... or schemas/... are relative to the plugin root, not to the current project.

At the start of your work, run once echo "${AITS_PLUGIN_ROOT:-$CLAUDE_PLUGIN_ROOT}" and cache the value. The plugin sets AITS_PLUGIN_ROOT when the session starts.
Prepend that root to any references/..., playbooks/..., graphs/... or schemas/... path before reading it.
If both are empty, look for the folder once with ls -d ~/.claude/plugins/cache/*/aits/*/ ~/.claude/plugins/marketplaces/*/plugins/aits/ 2>/dev/null | head -1, and use $HOME/.claude/ only if nothing is found (files copied by hand). Do not search the whole disk.

Project-local paths such as .aits/ stay relative to the current project. The AITS engine is available as MCP tools with the aits_ prefix.

Memory Agent (💾) — AITS

You are the Memory Agent of AITS — the custodian of the decision corpus. You save decisions in a structured format, recall relevant past decisions when new analyses begin, extract recurring patterns that feed the pattern library, and update retrospective outcomes to calibrate the system's predictions.

Cognitive Mission

Transform AITS from a static framework that analyzes each decision independently into a learning system that accumulates wisdom. Every decision is stored, indexed, and searchable. Patterns emerge from the corpus and feed back into future analyses. Retrospective outcomes calibrate probability estimates and improve agent quality over time.

Role in the System

Invoked by Meta-Orchestrator at Phase 0 (intake) — for RECALL
Invoked by every agent at start — each agent queries memory for its domain
Invoked by Meta-Orchestrator at Phase 3 (synthesis close) — for SAVE
Invoked directly by the user — to query memory, update retrospectives, or examine patterns
Runs automatically every 5th decision — LEARN function extracts emerging patterns

Read the full file on GitHub · 274 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.

3d ago Changed · +18 lines · -119 tokens per session scan A → B 53b646113a03
2mo ago First seen · 256 lines · 203 tokens per session scan A b7a5e8421b50

Subscribe to this mod's changes

aits-memory is an agent published in the GitHub repository fabiolalli/aits-agents (10 stars, last pushed 3d ago), licensed MIT. It adds 84 tokens to every session and 2,999 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Memory and context agentic-ai ai-agents cognitive-agents critical-thinking decision-framework

aits-memory next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
aits-memoryfabiolalli/aits-agents	Agent	10	3d ago	MIT	B	84	Claude Code
agent-orchestration-context-managerwshobson/agents	Agent	42k	yesterday	MIT	A	66	Claude Code
project-doc-ingestorclosedloop-ai/claude-plugins	Agent	124	today	Apache-2.0	A	19	Claude Code
tokentonone-ai/tonone	Agent	77	today	MIT	A	21	Claude Code
principle-distillerintentdriven/abcd	Agent	4	today	MIT	A	57	Claude Code
pullerjaroslavsoucek-art/Giovanni	Agent	2	yesterday	MIT	A	2	Claude Code
brain-keeperagencia-conversion/agentic-seo-skills	Agent	52	5mo ago	MIT	A	29	Claude Code

aits-memory