Skip to content

nfemmanuel/iranti

v0.2.15 Feature

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

Published 2mo AI Agents & Assistants
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Summary

AI summary

Fixed hybrid search crash caused by embedding normalization prototype traps.

Full changelog

Benchmark-driven fixes for search, ingest, observe autodetection, and MCP relationship read parity.\n\nHighlights:\n- fixed hybrid search crash caused by embedding normalization prototype traps\n- added sentence-level ingest fallback when whole-passage extraction returns zero chunks\n- improved observe autodetection for bare slug-style project identifiers\n- added MCP tools for relationship reads (iranti_related, iranti_related_deep)\n- added regression coverage for chunker fallback, vector merge hardening, and MCP surface parity

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 nfemmanuel/iranti

Get notified when new releases ship.

Sign up free

About nfemmanuel/iranti

Persistent shared memory for AI coding agents. Stores facts as `entity/key/value` triples with hybrid semantic search, task checkpoints, and conflict resolution — shared across Claude Code, Codex CLI, and GitHub Copilot.

All releases →

Related context

Beta — feedback welcome: [email protected]