Skip to content

Cortex

v1.2.2 Feature

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

Published 6d MCP Developer Tools
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai-agents docker fastapi karpathy-inspired karpathy-llm-wiki knowledge-base
+8 more
knowledge-graph knowledge-management llm llm-wiki markdown mcp python qmd

Summary

AI summary

Updates 1.2.0] — 2026-06-11, 1.2.2] — 2026-06-12, and 1.2.1] — 2026-06-12 across a mixed release.

Changes in this release

Feature Low

Adds optional Microsoft Teams notifications posting adaptive cards after new feedback notes.

Adds optional Microsoft Teams notifications posting adaptive cards after new feedback notes.

Source: llm_adapter@2026-06-13

Confidence: high

 —
Feature Low

Adds daily activity log mirroring vault_write, vault_ingest, and compile events to `daily/<UTC-date>.md`.

Adds daily activity log mirroring vault_write, vault_ingest, and compile events to `daily/<UTC-date>.md`.

Source: llm_adapter@2026-06-13

Confidence: high

 —
Feature Low

Adds folder‑based node typing for agents, sessions, and daily logs without filename suffixes.

Adds folder‑based node typing for agents, sessions, and daily logs without filename suffixes.

Source: llm_adapter@2026-06-13

Confidence: high

 —
Feature Low

Adds configurable search tuning via `CORTEX_QMD_CACHE_TTL_SECONDS` and `CORTEX_QMD_SEARCH_TIMEOUT_SECONDS`.

Adds configurable search tuning via `CORTEX_QMD_CACHE_TTL_SECONDS` and `CORTEX_QMD_SEARCH_TIMEOUT_SECONDS`.

Source: llm_adapter@2026-06-13

Confidence: high

 —
Feature Low

Adds feedback vault collection with tools and REST endpoints for capturing user/agent feedback.

Adds feedback vault collection with tools and REST endpoints for capturing user/agent feedback.

Source: llm_adapter@2026-06-13

Confidence: low

 —
Feature Low

Adds official MCP Registry listing with server.json and ownership marker.

Adds official MCP Registry listing with server.json and ownership marker.

Source: granite4.1:30b@2026-06-13-audit

Confidence: low

 —
Feature Low

Introduces feedback vault collection with tools, REST endpoints, status, and related_paths fields.

Introduces feedback vault collection with tools, REST endpoints, status, and related_paths fields.

Source: granite4.1:30b@2026-06-13-audit

Confidence: low

 —
Feature Low

Re‑releases 1.2.2 solely to trigger MCP Registry publishing after prior release missed the workflow.

Re‑releases 1.2.2 solely to trigger MCP Registry publishing after prior release missed the workflow.

Source: granite4.1:30b@2026-06-13-audit

Confidence: low

 —
Performance Medium

Improves QMD path index by memoizing per graph mutation.

Improves QMD path index by memoizing per graph mutation.

Source: llm_adapter@2026-06-13

Confidence: high

 —
Performance Medium

Improves vault_read by offloading note parsing to a thread for non‑blocking I/O.

Improves vault_read by offloading note parsing to a thread for non‑blocking I/O.

Source: llm_adapter@2026-06-13

Confidence: high

 —
Bugfix Medium

Fixes QMD container returning no results due to missing binary.

Fixes QMD container returning no results due to missing binary.

Source: llm_adapter@2026-06-13

Confidence: high

 —
Bugfix Medium

Fixes hybrid searches being silently truncated on CPU‑only hosts.

Fixes hybrid searches being silently truncated on CPU‑only hosts.

Source: llm_adapter@2026-06-13

Confidence: low

 —
Bugfix Medium

Fixes cached search failures from persisting empty result sets.

Fixes cached search failures from persisting empty result sets.

Source: llm_adapter@2026-06-13

Confidence: low

 —
Bugfix Low

Prevents hybrid searches from silently truncating on CPU‑only hosts by making timeout configurable (default 120 s).

Prevents hybrid searches from silently truncating on CPU‑only hosts by making timeout configurable (default 120 s).

Source: granite4.1:30b@2026-06-13-audit

Confidence: low

 —
Bugfix Low

Ensures empty result sets are not cached, avoiding persistent failures.

Ensures empty result sets are not cached, avoiding persistent failures.

Source: granite4.1:30b@2026-06-13-audit

Confidence: low

 —
Refactor Medium

Changes default search mode to `hybrid` (was `keyword`).

Changes default search mode to `hybrid` (was `keyword`).

Source: granite4.1:30b@2026-06-13-audit

Confidence: low

 —
Full changelog

[1.2.2] — 2026-06-12

Changed

  • Re-release to trigger MCP Registry publishing: 1.2.1 was tagged and released before the publish-mcp.yml workflow reached the default branch, so the registry listing never ran. No functional code changes since 1.2.1; this release exists to publish the server to registry.modelcontextprotocol.io.

[1.2.1] — 2026-06-12

Added

  • Official MCP Registry listing: Added server.json (schema 2025-12-11) describing the server under the namespace io.github.synpulse8-opensource/pulse8-ai-cortex-knowledge-vault, plus an mcp-name: ownership marker in the README so the registry can verify the PyPI package. Enables discovery via registry.modelcontextprotocol.io.

[1.2.0] — 2026-06-11

Added

  • Feedback vault collection: New feedback/ folder with vault_feedback and vault_list_feedbacks MCP tools plus REST endpoints, capturing user/agent feedback on vault quality with status and related_paths.
  • Microsoft Teams notifications: Optional TEAMS_WEBHOOK_URL posts an adaptive card after each new feedback note; optional TEAMS_APP_BASE_URL adds a "View in Cortex" link.
  • Daily activity log: Every vault_write, vault_ingest, and successful compile is mirrored into daily/<UTC-date>.md as a greppable ## [HH:MM] event | summary entry with a [[wiki-stem]] wikilink. Writes to daily/, feedback/, and .cortex/ are excluded to avoid self-reference.
  • Folder-based node typing: Files under agents/, sessions/, and daily/ are classified as AGENT_DEF, SESSION, and the new NodeType.DAILY without requiring a filename suffix. Frontmatter type: and the existing .agent.md/.session.md suffixes still take precedence/work.
  • Configurable search tuning: CORTEX_QMD_CACHE_TTL_SECONDS (result-cache TTL, default 30s) and CORTEX_QMD_SEARCH_TIMEOUT_SECONDS (search request timeout, default 120s).

Changed

  • Default search mode is now hybrid (was keyword). Clients that don't pass an explicit mode now get the best-quality BM25 + vector + re-ranking results. Set CORTEX_QMD_SEARCH_MODE=keyword to restore the previous fast-but-shallow default. Latency is mitigated by the result cache and the HTTP QMD container.

Fixed

  • QMD container returned no results: The image installed qmd via npm install -g ., which created a global symlink into a build directory deleted in the same layer — leaving a dangling qmd binary so every search failed with spawn qmd ENOENT and silently returned []. Now installed from a packed tarball with a build-time qmd --version smoke check.
  • Hybrid searches silently truncated: QMD HTTP searches hit a hardcoded 30s timeout on CPU-only hosts and returned [] while QMD was still working. Timeout is now configurable (default 120s).
  • Cached search failures: Empty result sets (transport errors/timeouts) are no longer cached, preventing a transient failure from blanking search for the full cache TTL.

Performance

  • Memoized QMD path index: build_path_index_from_graph is cached per graph mutation and no longer rebuilt on every search/read.
  • Non-blocking reads: vault_read offloads note parsing to a thread so concurrent MCP requests no longer serialize behind file I/O.
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 Cortex

Get notified when new releases ship.

Sign up free

About Cortex

All releases →

Related context

Earlier breaking changes

  • v1.2.0 Changes default search mode to hybrid from keyword.

Beta — feedback welcome: [email protected]