Log inSubmit server
Cognitive AI Memory logo

Cognitive AI Memory

Persistent local memory for MCP clients with fact extraction, Ebbinghaus decay, consolidation, and graph-assisted recall.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Cognitive AI Memory

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "cognitive-ai-memory": {
      "command": "uvx",
      "args": [
        "yourmemory"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

uvx yourmemory

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 9d ago.

Overview

The cognitive-ai-memory MCP server gives AI agents persistent local memory that extracts durable facts, recalls related information, and adapts memory strength over time. It uses an Ebbinghaus forgetting curve, consolidation, and hybrid retrieval combining vector search, BM25, and entity links. DuckDB provides the default zero-setup backend, while Postgres with pgvector supports shared or production deployments. Reach for it when agents need continuity across sessions, context resets, or team memory pools without sending memory data off the machine.

Use cases

  • Maintain user preferences across agent sessions
  • Recall project facts after context-window compaction
  • Share role-based institutional knowledge across team agents
  • Consolidate repeated conversation facts
  • Purge or export stored memory records

Key features

  • Ebbinghaus-based memory decay
  • Hybrid vector, BM25, and entity-graph retrieval
  • Automatic fact consolidation
  • Local DuckDB storage
  • Postgres with pgvector support
  • Hash-chained memory audit trail

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

8/8 checks healthy over the last 40d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 10d ago via OSV.dev · yourmemory (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars270Stargazers on the source repository.
Last commit1mo agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity3 viewsConfig copies, upvotes, and views on AllMCPs.

How Cognitive AI Memory works

What the cognitive-ai-memory MCP server does

The cognitive-ai-memory MCP server adds persistent memory to MCP-compatible AI clients. It extracts durable facts from conversations, stores them locally, and makes relevant information available in later sessions. The system is designed to avoid treating memory as an ever-growing collection of undifferentiated records.

Related facts can be consolidated into a shorter summary while the original records are archived. Memories also lose strength according to an Ebbinghaus-style forgetting curve. Frequently recalled or important information is more likely to remain available, while stale and unused facts can fade and be pruned.

Entity relationships connect memories through shared people, places, and concepts. This allows retrieval to follow related facts even when a second fact has weak direct similarity to the user’s query. The project also describes support for context resets, role-based team memory pools, export, right-to-forget operations, and a hash-chained audit record for reads, writes, and deletes.

How it works

The system extracts candidate facts, removes duplicates, creates embeddings, and links entities before saving the results in its memory store. Retrieval combines vector search, BM25 text search, and graph relationships. Related records may later be compressed into one summary, with source records retained in an archive rather than immediately deleted.

Memory strength changes with elapsed time and recall activity. This approach is intended for agents that need long-term continuity instead of only storing the current context window.

Setup and configuration

Install the Python package with Python 3.11 through 3.14, then register a token and run the setup command:

Terminal
pip install yourmemory
yourmemory-register <your-token>
yourmemory-setup

The token is obtained from the project’s website through email verification. Setup can detect and configure Claude Code, Claude Desktop, Cursor, Windsurf, and Cline. Memory is stored under ~/.yourmemory/.

DuckDB is the default backend and requires no separate database service. Postgres is available for shared or production use and requires a DATABASE_URL plus the pgvector extension. Built-in heuristics support local extraction by default. Ollama can provide higher-quality local extraction, while YOURMEMORY_EXTRACT_BACKEND=anthropic selects the documented cloud extraction option.

A standalone binary is also available for macOS Apple Silicon, macOS Intel, Linux x86-64, and Windows x86-64. The binary includes its Python runtime, dependencies, embedding model, and spaCy, but is approximately 2 GB.

Tools and capabilities

  • Extract and persist durable facts from agent interactions.
  • Recall memories using vector, BM25, and entity-graph retrieval.
  • Consolidate related memories into summaries.
  • Apply time-based decay and prune stale information.
  • Export stored data and purge memories.
  • Record memory reads, writes, and deletes in a hash-chained audit trail.

Limitations and notes

The default DuckDB configuration is local and suited to a single installation; shared use requires Postgres and pgvector. Cloud extraction is optional, while local extraction can use heuristics or Ollama. The standalone binary avoids first-run downloads but has a large download size. The project’s license is CC BY-NC 4.0, which should be reviewed before commercial use.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Cognitive AI Memory

cognitive-ai-memory is an MCP server that connects AI clients such as Claude Desktop, Cursor, Cline, Windsurf, and Claude Code to local persistent memory. Its main tools support extracting, storing, recalling, consolidating, decaying, and graph-linking memories across sessions.

Install it with pip, register a project token, and run `yourmemory-setup`. Python 3.11–3.14 is supported. Setup can configure Claude Code, Claude Desktop, Cursor, Windsurf, and Cline automatically.

Yes, cognitive-ai-memory supports Cursor. The setup command can detect Cursor and wire up the MCP configuration.

No, the default DuckDB backend requires no separate database setup. Postgres is an alternative for shared or production use and requires a `DATABASE_URL` and the pgvector extension.

Yes, memory is stored locally by default and built-in heuristics work without a cloud extraction service. Ollama can provide local model-based extraction; the documented Anthropic option is available when cloud extraction is preferred.

Related MCP servers

All in Knowledge & Memory All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewCognitive AI Memory AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/cognitive-ai-memory?style=directory)](https://allmcps.com/mcp/cognitive-ai-memory)
HTML Embed
<a href="https://allmcps.com/mcp/cognitive-ai-memory"><img src="https://allmcps.com/api/badge/cognitive-ai-memory?style=directory" alt="Cognitive AI Memory on AllMCPs" /></a>