kael-bit/engram-rs

v0.11.0 Feature

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

Published 3mo 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

agents ai ai-agents ai-memory claudecode mcp

+4 more

mcp-server openclaw rust sqlite

Summary

AI summary

Embed queue batching, embed‑only mode without LLM key, and HNSW memory optimizations are introduced.

Full changelog

What's New

One-liner install

# macOS / Linux
curl -fsSL https://raw.githubusercontent.com/kael-bit/engram-rs/main/install.sh | bash

# Windows (PowerShell)
irm https://raw.githubusercontent.com/kael-bit/engram-rs/main/install.ps1 | iex

Interactive wizard — picks your install method, configures LLM/embeddings, sets up MCP for Claude/Cursor, and starts the server. Detects existing installs and config.

Embed queue

Embedding requests are now batched with a 500ms time window (50-item cap). First store triggers the window; flush on expiry or cap hit. Cuts API round-trips significantly during bulk ingestion.

Embed-only mode

Start engram with just ENGRAM_EMBED_URL — no LLM key needed. Semantic search works out of the box; consolidation falls back to heuristics.

HNSW memory optimization

Incremental reconcile & merge — O(new×existing) instead of O(n²)
Auto-rebuild at >20% ghost node ratio
Dynamic capacity sizing
Consolidation no longer causes 2x memory spike

Other

Resume sorted by importance (descending)
Health endpoint reports embed_queue_pending
Dockerfile for containerized deployments

Full changelog: CHANGELOG.md

Full Changelog: https://github.com/kael-bit/engram-rs/compare/v0.10.0...v0.11.0

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 kael-bit/engram-rs

Get notified when new releases ship.

About kael-bit/engram-rs

Hierarchical memory engine for AI agents with automatic decay, promotion, semantic dedup, and self-organizing topic tree. Single Rust binary, zero external dependencies.

All releases →