MCP100 IndexMCP Server
WatchlistCommunity implementation

iai-memory

by CodeAbra

Reviewed October 5, 2026

MCP Server

Watchlist tracking

Reviewed for relevance and future tracking value.

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow memory storage, indexing, and tool behavior as coding integrations evolve

Reviewed · Documentation review; complete setup workflow not independently tested

Best fit

Persistent personal memory for AI coding and agent workflows

What we know

Personal memory engine that retains conversation/context and exposes recall, pin/fade/rescue and MCP integration.

Maintenance / activity evidence

  • Observed (UTC)Update README

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: medium.

Activity source · commits ↗Activity source · releases ↗

Verification gaps / watch-outs

  • Installation and comprehensive security have not been independently audited.
  • Memory-store access. Reported action classes: Store/update memory state. Complete write authority is not verified.
  • Authentication not yet verified.
  • Sensitive access: Conversation history, Project context
  • Long-lived agent memory is privacy-sensitive; local storage/auth boundaries should be confirmed before broad use.
Security source · repository notice ↗Security source · policy file ↗

Full authority, access and evidence limits are available in Review context and Access & risk.

Popularity

901 repository stars

Stars observed Oct 6, 2026.

30-day package downloads intentionally left null because the package-stats provider ran out of credits during Batch 3 QA.

30-day package downloads intentionally left null because the package-stats provider ran out of credits during Batch 3 QA.

30-day package downloads intentionally left null because the package-stats provider ran out of credits during Batch 3 QA.

All limitations / Review context

Which memory operations and client integrations does the current engine support?

The bounded assessment reviewed the official README, repository notices, security policy path, and security page for known material public-tracking blockers. No such blocker was identified. This is a public-tracking assessment, not an installation safety certification.

  • Long-lived agent memory is privacy-sensitive; local storage/auth boundaries should be confirmed before broad use.
  • Memory-store access.
  • Persists user/agent conversational context.
  • Reviewed write actions: Store/update memory state
  • Sensitive access: Conversation history, Project context
  • Complete write authority is not verified.
  • Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
  • No independent runtime, installation, or comprehensive security audit was performed.
  • No installation, runtime, client matrix, or complete tool-contract audit was performed in this review.
  • Authentication model
  • Detailed tool inventory
  • Retention controls
  • Detailed auth/tool inventory was not fully established in this audit.
  • Persistent memory may hold sensitive context.

Original activity observations

  • 2026-09-16T11:54:11Z: Update README
Technical identity
github.com/codeabra/iai-personal-memory-engine
Reviewed resource type
MCP Server
Repository identity
CodeAbra/iai-personal-memory-engine
Package identity
pypi:iai-pme

Evidence & Sources

Evidence basis
Recorded source evidence
Setup runtime verification
Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed · Latest source observation

  • GitHub repository ↗

    codeabra/iai-personal-memory-engine

    Recorded repository material and project history.

    Includes references whose attribution is not established.