This release adds 2 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Summary
AI summaryArtifact auto-capture now persists any ---‑delimited content block (≥200 chars) from assistant responses.
Full changelog
What's new
Artifact auto-capture at attend post-response
When attend(phase='post-response') is called with the assistant response, Iranti now automatically detects and persists generated content blocks. Previously, only narrow sentence-level patterns (like "the next step is...") were extracted. Now, any ----delimited content block of sufficient length (>=200 chars) is captured as a durable artifact fact.
This closes the gap where valuable generated content — drafts, plans, analysis results — was lost between sessions unless the agent explicitly called iranti_write.
Details
- New
extractResponseArtifacts()function inautoRemember.ts - Detects
----delimited blocks, skips YAML frontmatter, generates stable normalized keys - Integrated into
rememberAssistantResponseFacts()pipeline - 10 new tests covering extraction, filtering, key generation, and integration
- Capped at 3 artifacts per response to avoid noise
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 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.
Related context
Related tools
Beta — feedback welcome: [email protected]