This release includes 1 breaking change for platform teams planning a safe upgrade.
✓ No known CVEs patched in this version
Topics
+14 more
ReleasePort's take
Light signalThe release swaps the Python/hnswlib backend for a new Rust‑based storage and graph engine and introduces a desktop dashboard for live memory graph interaction.
Why it matters: Affects storage, graph processing, and monitoring; triggers evaluation of performance and security post‑migration to Rust components.
Summary
AI summaryNew Rust‑based storage and graph engine replaces Python/hnswlib, introducing a desktop app with live memory graph monitoring.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Adds desktop app providing a local, loopback‑only dashboard for live memory graph interaction. Adds desktop app providing a local, loopback‑only dashboard for live memory graph interaction. Source: llm_adapter@2026-07-15 Confidence: high |
— |
| Feature | Medium |
Adds new memory operations: document study/teach, anticipatory foresight packs, and combined lexical + semantic search. Adds new memory operations: document study/teach, anticipatory foresight packs, and combined lexical + semantic search. Source: llm_adapter@2026-07-15 Confidence: high |
— |
| Dependency | Low |
Drops remaining GPL‑adjacent dependencies; project now ships its own storage and graph engines under MIT. Drops remaining GPL‑adjacent dependencies; project now ships its own storage and graph engines under MIT. Source: llm_adapter@2026-07-15 Confidence: high |
— |
| Refactor | High |
Replaces Python/hnswlib backend with new Rust storage and graph engine. Replaces Python/hnswlib backend with new Rust storage and graph engine. Source: llm_adapter@2026-07-15 Confidence: high |
— |
Full changelog
What's new in v2.0.0
- New Rust storage and graph engine — replaces the previous Python/hnswlib backend. Existing stores migrate automatically on first run, no manual steps.
- Desktop app — a local, loopback-only dashboard to watch the memory graph live, add a memory, and hint records into the forgetting queue.
- New memory operations — document study/teach, anticipatory foresight packs, and combined lexical + semantic search.
- Dropped the last GPL-adjacent dependencies; the project now ships its own storage and graph engines under MIT.
Windows support is beta. See CHANGELOG.md for details.
Breaking Changes
- Replaced Python/hnswlib storage and graph backend with a new Rust implementation; existing stores migrate automatically on first run.
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
About CodeAbra/iai-mcp
All releases →Related context
Related tools
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]