Hi HN, I'm Ali. I've been building Mengram for the past year.
The problem: Every AI memory tool stores facts — "user likes dark mode." But when my agents failed at a task, they'd fail the exact same way next time. They had no memory of what happened or how to do things better.
What Mengram does: It stores 3 types of memory, modeled after how human cognition works:
- Semantic — facts and preferences (like Mem0, Zep)
- Episodic — events, decisions, outcomes (what happened and when)
- Procedural — learned workflows that evolve when they fail
The procedural part is what I'm most excited about. When an agent reports a failure, Mengram automatically evolves the procedure — adds a new step, changes the order, removes what didn't work. Your agent literally gets better at its job over time.
Example: Week 1, "Deploy" = build → push → deploy. Agent forgets migrations, DB crashes. Week 2, Mengram evolves it to build → run migrations → push → deploy. Agent hits OOM. Week 3, adds memory check step. This happens automatically.
Technical details:
- Python & JS SDKs: pip install mengram-ai
- Free cloud API (no credit card) or fully self-hostable
- MCP server for Claude Desktop / Cursor (21 tools)
- LangChain, CrewAI, OpenClaw integrations
- Knowledge graph + vector search + reranking
- Cognitive Profile: one API call generates a system prompt from all memories
What it's NOT good at (yet):
- Smaller community than Mem0 (they have 25K stars, I'm just starting)
- No SOC2/HIPAA yet (Zep has this)
- No agent-controlled memory like Letta/MemGPT
I'd love feedback on the API design and the procedural memory concept. Is this something you'd actually use in production?
GitHub: https://github.com/alibaizhanov/mengram
Docs: https://mengram.io/docs
Get a free key: https://mengram.io
Hi HN, I'm Ali. I've been building Mengram for the past year.