A project-memory add-on that searches your notes and decisions, records when claims have been withdrawn, and declines to answer when the stored evidence is insufficient.

Use it to retrieve project memory, check earlier decisions, identify superseded claims, and configure a PostgreSQL-backed memory store.

It helps keep agent answers grounded in project records rather than guesses or outdated information.

recall — Plugin by GiulioDER

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.

Claude Code

/plugin marketplace add GiulioDER/RE-call

agentmods

npx agentmods add plugins/giulioder/re-call/plugin

Clone the repo

git clone --depth 1 https://github.com/GiulioDER/RE-call

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

recall 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 yesterday.

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.

plugin/.claude-plugin/plugin.json · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "name": "recall",
  "displayName": "RE-call",
  "description": "Memory that abstains instead of guessing. Searches your project's own notes and decisions, marks a retracted claim as superseded, and refuses when nothing clears the threshold.",
  "version": "0.11.0",
  "author": {
    "name": "Giulio D'Erme",
    "url": "https://github.com/GiulioDER"
  },
  "homepage": "https://giulioder.github.io/RE-call/",
  "repository": "https://github.com/GiulioDER/RE-call",
  "license": "Apache-2.0",
  "keywords": [
    "memory",
    "rag",
    "retrieval",
    "agent-memory",
    "pgvector",
    "postgresql",
    "abstention"
  ],
  "mcpServers": {
    "memory": {
      "command": "recall-mcp",
      "env": {
        "RECALL_SERVING_DSN": "${user_config.serving_dsn}",
        "RECALL_TENANT": "${user_config.tenant}",
        "RECALL_TRUST_MODE": "${user_config.trust_mode}",
        "RECALL_TABLE": "${user_config.table}"
      }
    }
  },
  "userConfig": {
    "serving_dsn": {
      "type": "string",
      "title": "PostgreSQL DSN",
      "description": "The database RE-call reads. Run `recall quickstart` or `recall setup` first; both print the DSN when they finish. Looks like postgresql://recall:[email protected]:5497/recall",
      "sensitive": true,
      "required": true
    },
    "table": {
      "type": "string",
      "title": "Table",
      "description": "The chunk table inside that database. `recall quickstart` indexes into `quickstart_chunks` so its sample corpus can never be retrieved beside your real memory; `recall setup` uses `chunks`. Getting this wrong returns no hits and no error, so it is asked rather than assumed.",
      "default": "chunks"
    },
    "tenant": {
      "type": "string",
      "title": "Tenant",
      "description": "Which corpus in that database to search. `recall quickstart` writes to the `quickstart` tenant; `recall setup` writes to `default`.",
      "default": "default"
    },
    "trust_mode": {
      "type": "string",
      "title

Read the full file on GitHub · 61 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.

yesterday First seen · 61 lines scan A c69835ab55c7

Subscribe to this mod's changes

recall is a plugin published in the GitHub repository GiulioDER/RE-call (3 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-08-31.

Data and AI Databases LLM Memory and context embeddings hybrid-search information-retrieval llm-agents mcp

recall

Getting it into your agent

Grade A, and why

Nothing flagged

How it starts

What this file has done since we first saw it

Other plugins, from other repositories

cocosearch

cocosearch

subcog

kb-workflow

knowledge-base

melchizedek