l33tdawg/sage

v8.8.0 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 2d AI Agents & Assistants

View tool

✓ No known CVEs patched

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

✓ No known CVEs patched in this version

Topics

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

Summary

AI summary

Governance‑activatable app‑v7 content validation with a regression halt floor.

Changes in this release

Type	Severity	Summary	CVE
Feature	Medium	Adds governance-activatable app-v7 content-validation. Adds governance-activatable app-v7 content-validation. Source: granite4.1:30b@2026-06-02-audit Confidence: low	—
Dependency	Low	Bumps SDK from version 8.7.0 to 8.8.0. Bumps SDK from version 8.7.0 to 8.8.0. Source: llm_adapter@2026-06-02 Confidence: high	—
Bugfix	Medium	Implements version-regression halt floor. Implements version-regression halt floor. Source: granite4.1:30b@2026-06-02-audit Confidence: low	—

Full changelog

SAGE v8.8.0

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

e423b7b7cd021285578d70eb0fcc9a235f5eb6e3 release(v8.8.0): governance-activatable app-v7 content-validation + version-regression halt floor; bump SDK 8.7.0 -> 8.8.0

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 →