This release fixes issues for SREs watching stability and regressions.
✓ No known CVEs patched in this version
Topics
+14 more
Summary
AI summaryImmune no longer fails when the optional legacy ~/.claude-mem/claude-mem.db database is absent.
Full changelog
Summary
- Packaged update/doctor self-heal for runtime LaunchAgents now uses the packaged
runtime/cronslayout instead of assuming a source checkout. - LaunchAgent PATH now includes NEXO's managed Claude npm-global bin, so background automation can find the managed
claudecommand after update. - Runtime update backfills root
claude_cli.pyfor packaged installs. - Immune no longer fails when the optional legacy
~/.claude-mem/claude-mem.dbdatabase is absent. - Public release surfaces and OpenClaw bridge metadata bumped to 7.9.20.
Validation
- CI green: pytest, ruff, Bandit high/high, release-readiness, client parity, Claude plugin, ClawHub, and OpenClaw checks.
- Local targeted runtime validation: 32 passed.
- Release readiness and client parity scripts passed locally.
- Root
npm pack --dry-runpassed. - OpenClaw
npm testandnpm run buildpassed.
What's Changed
- Release 7.9.20 packaged update self-heal by @wazionapps in https://github.com/wazionapps/nexo/pull/289
Full Changelog: https://github.com/wazionapps/nexo/compare/v7.9.19...v7.9.20
What's Changed
- Release 7.9.20 packaged update self-heal by @wazionapps in https://github.com/wazionapps/nexo/pull/289
Full Changelog: https://github.com/wazionapps/nexo/compare/v7.9.19...v7.9.20
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 wazionapps/nexo
Cognitive memory for AI agents with Atkinson-Shiffrin memory model (STM/LTM/sensory register), semantic RAG, Ebbinghaus decay, trust scoring, and 76+ MCP tools.
Related context
Beta — feedback welcome: [email protected]