Seven months after the first launch, this one is about the work, not memory types. Hooks for Claude Code, Codex and Cursor: recall on every prompt, save after each turn, a checkpoint before compaction that puts the working state back. New: `mengram resume`, a task card (done, remaining, last test and its commit) the next session or agent picks up, keyed by repo and branch. Every fact says which tool wrote it and when. Benchmark: 23-62x fewer context tokens than sending history, losses published.

AI memory API with 3 types: semantic (facts), episodic (events), and procedural (learned workflows). One API call extracts all three automatically. Killer feature: your agent completes a task → Mengram saves the steps → next time it already knows the optimal path with success/failure tracking. Works with Claude (MCP), LangChain, CrewAI, OpenClaw. Free, open-source, Apache 2.0.