Comparison

Project Agent Memory vs Perenna

Project Agent Memory is no longer listed on any marketplace we read: these are its last known data, as of 2026‑10‑15.

Project Agent Memory is a plugin bundle for AI coding tools published by Balaji.G. No marketplace we read lists it any more. Perenna is an MCP server published by scarletkc. Marketplaces we read that list it: 2 (Official MCP Registry, Community GitHub marketplaces). As of our marketplace pass on 2026-10-23. A plugin in this pair is no longer listed on any marketplace we read, so search engines are asked not to index the page.

Where each is published

Where each is published
Marketplace	Project Agent Memory	Perenna
Community marketplace balaji-g42/project-agent-memory	Removed on 2026-10-15 Version: 3.1.0 Forks (GitHub): 0 Stars (GitHub): 1 Not marked · First seen 2026-10-14	Not listed
Official MCP Registry	Not listed	Listed Version: 0.4.1 Downloads/month (PyPI): 248 Downloads/week (PyPI): 39 Forks (GitHub): 3 Stars (GitHub): 61 Not marked · First seen 2026-10-11

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

Project Agent Memory vs Perenna
Fact	Project Agent Memoryno longer listed · 2026-10-15	Perenna
Marketplaces that list it (differs)	0	2
Stars (GitHub) (differs)	1	61
Forks (GitHub) (differs)	0	3
Last release	Not published	Not published
Where it runs (differs)	On your machine (project-agent-memory)	On your machine (perenna)
Transport (differs)	Not stated	stdio
Tools it declares	Not published	Not published
Environment variables it asks for (differs)	5, secrets among them: 2	4, secrets among them: 2
Hooks it runs (differs)	6	Not published
Parts of the bundle (differs)	8	2
Licence	MIT	MIT
Repository (differs)	github.com/balaji-g42/project-agent-memory	github.com/scarletkc/perenna
Changes in the last 7 days	0	0
First seen (differs)	2026-10-14	2026-10-11

Lines where the two differ have a tinted background and bold values. No value is marked better or worse: a plugin no marketplace lists any more is shown with its last known data, which we do not rank against current figures.

What to use instead of Project Agent Memory

Plugins still listed whose own names, descriptions, tools and skills are closest in meaning to it. Comparable, not endorsed.

claude-memory

A Claude Code plugin that adds structured, categorized memory to your projects.

by tars23364-bit · Plugin bundle

Listed on: Claude Code: claude-plugins-community · Describes nearly the same job
Total Agent Memory

Persistent local memory for coding agents: temporal knowledge graph, procedural and episodic recall

by vbcherepanov · MCP server

Listed on: Official MCP Registry, Community GitHub marketplaces · Describes nearly the same job
kagura-memory

Persistent AI project memory — restore session context, recall & save knowledge, setup, and an MCP smoke test

by Kagura AI, Inc. · Plugin bundle

Listed on: Community GitHub marketplaces · Describes nearly the same job
origin

AI work memory for Claude Code: brief, capture, recall, handoff, and distill, backed by a local daemon and MCP so decisions, lessons, project context, and wiki pages carry across…

by Qi-Xuan Lu · Plugin bundle

Listed on: Community GitHub marketplaces · Describes nearly the same job
context-vault

Persistent structured memory for Claude Code. SQLite JSONB vault with 7 MCP tools for entity CRUD, todos with dependencies, and context injection across compactions.

by hazyhaar · Plugin bundle

Listed on: Claude Code: claude-plugins-community · Describes nearly the same job
agent-recall

Persistent memory for AI coding agents. SQLite knowledge graph with scoped entities, MCP tools, and LLM-summarized briefings.

by mnardit · Plugin bundle

Listed on: Claude Code: claude-plugins-community · Describes nearly the same job

Its card, with similar plugins by marketplace

What each says it does

Project Agent Memory

In its own words, on Community GitHub marketplaces:

Persistent, semantically searchable agent memory backed by Qdrant or PostgreSQL/pgvector, with a code index graph and memory-first session hooks.

Perenna

In its own words, on Official MCP Registry:

A lightweight, Git-backed permanent memory for AI agents.

How to run each

Project Agent Memory

No data for an automatic command: what its marketplaces declare does not say unambiguously how to connect it.

Perenna As a local MCP server: PyPI package

Claude Code

claude mcp add --env "VEXOR_API_KEY=<YOUR_VEXOR_API_KEY>" --env "VEXOR_REMOTE_RERANK_API_KEY=<YOUR_VEXOR_REMOTE_RERANK_API_KEY>" --transport stdio perenna -- uvx perenna mcp

Requires: VEXOR_API_KEY (secret), VEXOR_REMOTE_RERANK_API_KEY (secret)

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Tools each declares

Neither one's marketplaces publish a list of tools, so there is nothing to compare.

Settings each asks for

Only Project Agent Memory asks for

MEMORY_BACKEND
POSTGRES_PASSWORD (secret)
POSTGRES_URL
QDRANT_API_KEY (secret)
QDRANT_URL

Only Perenna asks for

PERENNA_GIT_REMOTE
VEXOR_API_KEY (secret)
VEXOR_CONFIG_JSON
VEXOR_REMOTE_RERANK_API_KEY (secret)

Settings as each marketplace publishes them. Asking for fewer is not better in itself.

What it can do: Project Agent Memory · What it can do: Perenna · Compare two other plugins

Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on 2026-10-23. We publish no contact details for plugin publishers.