Skip to content

cdeust/Cortex

v4.8.0 Feature

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

Published 16d MCP Data & Storage
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent-memory-system anthropic causal-inference claude claude-code claude-code-plugin
+14 more
cognitive-architecture cognitive-science episodic-memory hopfield-network llm-memory long-term-memory mcp-server memory model-context-protocol neuroscience persistent-memory predictive-coding retrieval-augmented-generation vector-db

Summary

AI summary

Updates merge, explore_features, and bench across a mixed release.

Changes in this release

Feature Medium

Adds real attribution mode for project-scoped conversations.

Adds real attribution mode for project-scoped conversations.

Source: llm_adapter@2026-07-15

Confidence: high

 —
Feature Medium

Adds per-process ephemeral test database isolation.

Adds per-process ephemeral test database isolation.

Source: llm_adapter@2026-07-15

Confidence: low

 —
Feature Low

Implements per-process test DB isolation to eliminate cross-process contention.

Implements per-process test DB isolation to eliminate cross-process contention.

Source: granite4.1:30b@2026-07-15-audit

Confidence: low

 —
Bugfix Medium

Fixes flaky database tests by isolating each pytest process on a throwaway PG database.

Fixes flaky database tests by isolating each pytest process on a throwaway PG database.

Source: llm_adapter@2026-07-15

Confidence: high

 —
Refactor Low

Refactors interpretability core-layer boundary to be typed.

Refactors interpretability core-layer boundary to be typed.

Source: llm_adapter@2026-07-15

Confidence: high

 —
Full changelog
  • release: v4.8.0 — real attribution mode, per-process test DB isolation, typed interpretability boundary
  • merge: fix/attribution-mode-hollow — attribution mode wired to real project-scoped conversations, categorical/numeric split
  • fix(explore_features): wire attribution mode to real session data
  • merge: refactor/type-explore-features — typed interpretability boundary, byte-identical responses
  • merge: fix/flaky-db-tests — per-process ephemeral test DB kills cross-process contention
  • bench: retroactive v4.7.0 non-regression manifest — MRR 0.9166 / R@10 0.982, guard green
  • refactor(explore_features): type the interpretability core-layer boundary
  • refactor(explore_features): type the interpretability core-layer boundary
  • fix(tests): isolate each pytest process on a throwaway PG database

Full Changelog: https://github.com/cdeust/Cortex/compare/v4.7.0...v4.8.0

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 cdeust/Cortex

Get notified when new releases ship.

Sign up free

About cdeust/Cortex

Persistent memory for Claude Code grounded in computational neuroscience (41 cited papers)

All releases →

Related context

Beta — feedback welcome: [email protected]