Evaluation report

• Repository is reachable

  https://github.com/alibaizhanov/mengram @ 5a0c0e2 — ★ 178 · Python · Apache-2.0 · last push 3 days ago

• Manifest detected

  kind=mcp slug=mengram-ai · source=pyproject.toml

• Slug is URL-safe

  "mengram-ai" matches /^[a-z0-9][a-z0-9-]{0,62}$/

• Slug is unique within kind

  No collision found for mcp/mengram-ai

• Version is semver

  2.25.3

• Description quality

  25 words · 207 chars — "Human-like memory for AI agents — auto-save, auto-recall, cognitive profile. Cla…"

• README is present and substantial

  18,196 chars · 20 sections · 38 code blocks

• Tags / topics declared

  20 total — agent-memory, ai-agents, ai-memory, claude-desktop, cognitive-architecture, cohere (+14)

• README has usage / example sections

  no labeled section but 38 code blocks document usage

• Homepage / docs URL declared

  https://mengram.io

• LICENSE file at repo root

  LICENSE

• No sensitive files in the repo

  scanned for .env, credentials.json, *.pem, .ssh/, AWS / GCP configs — none found

• MCP: launch path

  launch declared in pyproject.toml

• MCP: @modelcontextprotocol/sdk in dependencies

  non-Node server (pyproject.toml) — uses its language's MCP SDK

• MCP: ESM package

  non-Node server (pyproject.toml) — n/a

• MCP: server surface

  0 tools

• CI configuration detectedwarn

  no CI config found (looked for GitHub Actions, CircleCI, GitLab CI, etc.)

  Add a simple workflow (lint + test on PR) — it tells consumers the artifact is built reproducibly.

• Recent activity

  last push 3 days ago

• Tests detected

  1 test directory · 4 test files

This artifact hasn't produced behavioral results yet: the evaluation sandbox couldn't run it (it may need credentials we don't provide, or a build our environment doesn't support). That's a limitation of our environment, not a verdict on the artifact.