This release adds 2 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
+14 more
Summary
AI summaryAdded AnalysisBank memory layer with docs, example cards, induction prompts, and eval harness.
Full changelog
v0.2.0 — AnalysisBank reasoning memory layer
v0.2.0 adds AnalysisBank, a ReasoningBank-inspired memory layer for Agenda-Intelligence.md.
Added
analysis-bank/README.md— how to store and retrieve reasoning memories.analysis-bank/MEMORY_FORMAT.md— memory-card format.- Failure memory cards:
vague-monitoring.mdoverconfident-sanctions-upgrade.mdeu-rhetoric-treated-as-law.md
- Success memory card:
sanctions-routing-signal-classification.md
- Induction prompts:
induce-success-memory.mdinduce-failure-memory.mdinduce-contrast-memory.md
scripts/eval_before_after.py— lightweight before/after scoring harness.
Eval results
eu-ai-act.md: before 3/16 → after 14/16
red-sea-shipping.md: before 1/16 → after 13/16
sanctions-routing.md: before 2/16 → after 14/16
The validator now runs the eval script in CI.
Why this matters
Agenda-Intelligence.md is no longer just a static protocol. It now has a lightweight mechanism for accumulating reusable reasoning lessons from successes and failures.
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 Agenda Intel MD
All releases →Related context
Related tools
Earlier breaking changes
- v0.8.0 MCP tool count increased from 11 to 16, adding five new tools.
Beta — feedback welcome: [email protected]