l33tdawg/sage

v11.7.3 Security

This release includes 1 security fix for security teams reviewing exposed deployments.

Published 15d AI Agents & Assistants

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

This release patches 1 known CVE

Topics

agentic-ai artificial-intelligence bft-consensus bft-network distributed-systems governance

Affected surfaces

auth rbac

Summary

AI summary

Updates Quick Start (sage-gui) ```bash, sage-gui, and cerebrum across a mixed release.

Changes in this release

Type	Severity	Summary	CVE
Bugfix	Medium	Stop settings store-scan polling in cerebrum component Stop settings store-scan polling in cerebrum component Source: llm_adapter@2026-07-15 Confidence: high	—
Bugfix	Medium	Enforce agent and domain isolation in tasks subsystem Enforce agent and domain isolation in tasks subsystem Source: llm_adapter@2026-07-15 Confidence: low	—

Full changelog

SAGE v11.7.3

Sovereign Agent Governed Experience — persistent, governed memory for AI agents.

Quick Start (sage-gui)

# Download and extract for your platform, then:
./sage-gui setup    # Interactive setup wizard
./sage-gui serve    # Start your personal memory node

See the README for full documentation.

Changelog

2b00c13a73fa257646844f34c2199011a8ba266e docs(release): keep isolation example generic
60073bc279898e7df64d7f814ff70c462920b9f0 docs(release): note task isolation hardening
c211271d9a7bfff8459f4f3863fad81aad3af036 fix(cerebrum): stop settings store-scan polling
ecc15f288313ef448ed78a74e23817975382d2c3 fix(tasks): enforce agent and domain isolation

Security Fixes

Enforce agent and domain isolation — closes abuse vector where tasks could access foreign data

View diff on GitHub

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

Share on X Share on Bluesky

Track l33tdawg/sage

Get notified when new releases ship.

About l33tdawg/sage

Institutional memory for AI agents with real BFT consensus. 4 application validators vote on every memory before it's committed — no more storing garbage. 13 MCP tools, runs locally, works with any MCP-compatible model. Backed by 4 published research papers.

All releases →