Skip to content

nfemmanuel/iranti

v0.2.0 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

Added temporal versioning with asOf query support.

Full changelog

Added

  • Temporal versioning with asOf query support and ordered fact history.
  • External TypeScript HTTP client package under clients/typescript for @iranti/sdk.
  • Conflict-resolution benchmark suite with documented 7/16 (44%) baseline.
  • Consistency-model documentation and empirical validation suite with 4/4 baseline.
  • Ebbinghaus-style opt-in memory decay with Archivist maintenance coverage.
  • Hardened MCP tool descriptions and stdio smoke testing.
  • Refined single-entity ingest pipeline with per-fact extraction confidence and clearer provenance.
  • Expanded setup wizard flow for port checks, PostgreSQL mode selection, optional Docker bootstrap, and project scaffolding.

Changed

  • README and launch-facing docs now cite measured retrieval, conflict, and consistency results instead of generic claims.
  • TypeScript, Python, MCP, seed, and API version surfaces aligned to 0.2.0.
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 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]