Skip to content

CodeAbra/iai-mcp

v2.0.1 Feature

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

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

✓ No known CVEs patched in this version

Topics

agent-memory ai-memory claude claude-code codex cursor
+14 more
encrypted episodic-memory gemini llm-memory local-first long-term-memory mcp mcp-memory mcp-server model-context-protocol persistent-memory rag-alternative sqlite vector-db

Summary

AI summary

Corpus counters now update incrementally, fresh readers inherit the writer's sort index, and the graph cache stops full re‑streaming on ambient captures.

Changes in this release

Performance Medium

Updates corpus counters incrementally instead of rescanning.

Updates corpus counters incrementally instead of rescanning.

Source: llm_adapter@2026-07-15

Confidence: high

Performance Medium

Fresh readers inherit writer's sort index rather than rebuilding it.

Fresh readers inherit writer's sort index rather than rebuilding it.

Source: llm_adapter@2026-07-15

Confidence: high

Performance Medium

Graph cache no longer re-streams entire corpus on ambient captures.

Graph cache no longer re-streams entire corpus on ambient captures.

Source: llm_adapter@2026-07-15

Confidence: high

Full changelog

v2.0.1 — Lower idle CPU

  • Corpus counters update incrementally instead of rescanning.
  • Fresh readers inherit the writer's sort index instead of rebuilding it.
  • The graph cache no longer re-streams the whole corpus on ambient captures.

Background rebuild churn is cut substantially. See CHANGELOG.md.

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

Track CodeAbra/iai-mcp

Get notified when new releases ship.

Sign up free

About CodeAbra/iai-mcp

All releases →

Related context

Earlier breaking changes

  • v1.0.0 Removes previous embedded vector database, PyTorch embedding stack, and third‑party GPL/graph libraries.
  • v0.4.0 Hook log marker format changed from 'cache-hit fresh' to 'cache-hit age='
  • v0.4.0 Deferred-capture retry replaces old rename-once-and-skip behavior
  • v0.4.0 Removed 24-hour staleness cap from session-recall hook
  • v0.2.0 IAI_MCP_EMBED_QUANTIZE accepts only int8 (lowercase) or unset; other values crash daemon at startup.

Beta — feedback welcome: [email protected]