MCP Servers · Memory

CodeAbra/iai-mcp

Name: CodeAbra/iai-mcp
Author: Various

The best-benchmarked open-source memory system for AI coding assistants

Visit site ↗

Our verdict

Not reviewed yet

We have not reviewed CodeAbra/iai-mcp yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About CodeAbra/iai-mcp

An open-source memory system designed to provide persistent context for AI coding assistants. It is benchmarked as the top performer among similar tools and implemented in Python.

Best for

Developers using AI coding assistants who need reliable, persistent memory across sessions

Use cases

Give coding assistants long-term memory across multiple sessions
Store project-specific context for AI code generation
Integrate with MCP-compatible development tools and editors

Notes

133 stars on GitHub. Last updated 2026-05-15. Licensed MIT.

Pros

Top benchmarked performance among open-source memory systems
Lightweight Python implementation with clear codebase
Actively developed with 133 GitHub stars

Cons

Relatively small community compared to larger tools
Requires manual setup and integration into existing workflows
Primarily focused on AI coding assistants, not general-purpose memory

Key facts

What we have checked

Not checked yet. Dated facts such as prices, releases and repository activity appear here once we have confirmed them from a source.

How to use

How to set it up

As the listing publishes it. We have not run this install.

Install

python3.12 -m pip install -U iai-pme

Tools exposed

memory_recall
memory_temporal_recall
memory_recall_structural
memory_search
memory_capture
memory_contradict
memory_reinforce
memory_consolidate
profile_ge

Clients the listing names (not checked here)

Claude Desktop, Claude Code, Cursor

Install

Add CodeAbra/iai-mcp to your client

Not verified yet

No install recipe yet. We write one for Claude Code, Claude Desktop, Cursor, VS Code, Codex and ChatGPT when the server is in the official MCP registry with a package or remote address we can use.

Until then, follow the project's own README, or the setup the listing publishes under How to set it up.

Works with

What CodeAbra/iai-mcp connects to

No confirmed connections yet. A product appears here when the server's registry name, repo, homepage or name ties it to that product, and a client appears when we have an install recipe for it.

Health and security

Is CodeAbra/iai-mcp looked after, and what do its setup files show

Security check static checks

97 out of 100

Reads what is published about the server: package advisories, licence, secrets in the documented setup and tool permissions. Nothing is installed or run, so this is not a security assessment. Checked 26 Oct 2026 by edna-static-v1. What it checks

Licence: MIT

Low The documented install uses iai-pme, whose published metadata names no source repository. Check it is the right package before installing.
Note No published npm or PyPI package of this repository was found, so package advisories were not checked.
Note The lab has not recorded this server's tool list yet, so tool permissions were not checked.

Alternatives

Alternatives to CodeAbra/iai-mcp

Record	Type	How we know	Checked
oraios/serenaThis is an alternative to it	MCP server	Named in the listing	Not dated
topoteretes/cogneeThis is an alternative to it	MCP server	Named in the listing	Not dated
vectorize-io/hindsightThis is an alternative to it	MCP server	Named in the listing	Not dated