l33tdawg/sage

v9.2.2 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 3h 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

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

Changes in this release

Type	Severity	Summary	CVE
Feature	Low	Adds snapshot retention and pruning on each Take. Adds snapshot retention and pruning on each Take. Source: llm_adapter@2026-06-04 Confidence: high	—
Dependency	Low	Bumps SDK version from 9.2.1 to 9.2.2. Bumps SDK version from 9.2.1 to 9.2.2. Source: llm_adapter@2026-06-04 Confidence: high	—

Full changelog

SAGE v9.2.2

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

e2b5678e8e18ea820e9530f70f7ae3845b27a401 docs(readme): add v9.2.1 What's New (FTS5 backfill startup hotfix + two-sided app-v9/app-v10 fork-branch metrics + on-chain nonce seed); demote v9.2.0 to Older releases
9fe256a5dc74ccf48968801928146dea95b9cef5 feat(snapshot,boot): wire snapshot retention — prune after each Take + boot staging sweep + snapshot CLI
f082ac2e9df0e4da06a184dacd5b4ad783be2278 release(v9.2.2): snapshot retention/pruning (KeepLast wired + boot staging sweep + snapshot CLI); bump SDK 9.2.1 -> 9.2.2

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 →