alibaizhanov/mengram

v2.23.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 1mo AI Agents & Assistants

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-memory ai-agents ai-memory claude-desktop cognitive-architecture cohere

+14 more

cursor-ai episodic-memory knowledge-graph letta-alternative llm-memory mcp-server mem0-alternative model-context-protocol multilingual-embeddings pgvector procedural-memory python llm semantic-search

Affected surfaces

auth breaking_upgrade

Summary

AI summary

Signup can bypass email verification via DISABLE_EMAIL_VERIFICATION and health checks now support a /health alias.

Full changelog

Self-Hosting Improvements

Signup without email verification — set DISABLE_EMAIL_VERIFICATION=true in Docker Compose to get API keys immediately, no Resend dependency needed
BASE_URL env var — configures all OAuth redirects, email links, and dashboard URLs for your domain (default: https://mengram.io)
/health endpoint alias — works alongside /v1/health for standard health check conventions
Clipboard fallback — copy buttons now work on non-HTTPS contexts (Docker, localhost) using execCommand('copy') fallback
Verification codes logged to stdout — when RESEND_API_KEY is not set, codes appear in docker compose logs mengram
Version footer from package metadata — landing page shows the actual installed version via importlib.metadata

JS SDK

Retry logic with exponential backoff — automatically retries on 429, 500, 502, 503, 504 with configurable maxRetries (default: 3) (#20)
504 restored to retryable statuses — gateway timeouts are retried again

OpenClaw

Human-readable 402 error — shows upgrade prompt with plan details instead of raw JSON when quota is exceeded

Other

Drip emails now mention OpenClaw and AI agent features
GitHub Sponsors funding config added

Full changelog: https://github.com/alibaizhanov/mengram/compare/v2.22.0...v2.23.0

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track alibaizhanov/mengram

Get notified when new releases ship.

About alibaizhanov/mengram

Human-like memory layer for AI agents with semantic, episodic, and procedural memory. Claude Code hooks (auto-save, auto-recall, cognitive profile). 29 MCP tools, knowledge graph, smart triggers, multi-user isolation. Python & JS SDKs.

All releases →