Skip to content

l33tdawg/sage

v8.5.1 Maintenance

This release keeps dependencies and maintenance posture current for teams operating this 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

Minor fixes and improvements.

Changes in this release

Feature Low

Implements divergence guard in NormalizeWeights.

Implements divergence guard in NormalizeWeights.

Source: granite4.1:30b@2026-06-01-audit

Confidence: low

Dependency Low

Bumps SDK version from 8.5.0 to 8.5.1.

Bumps SDK version from 8.5.0 to 8.5.1.

Source: llm_adapter@2026-06-01

Confidence: high

Bugfix Medium

Adds byte-parity check for replay_v8_3.

Adds byte-parity check for replay_v8_3.

Source: granite4.1:30b@2026-06-01-audit

Confidence: low

Refactor Low

Updates documentation based on PoE Phase 2 audit feedback.

Updates documentation based on PoE Phase 2 audit feedback.

Source: granite4.1:30b@2026-06-01-audit

Confidence: low

Full changelog

SAGE v8.5.1

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

  • 8122a91bf561c9c5c99bea380871116c70785988 release(v8.5.1): PoE Phase 2 audit follow-ups — replay_v8_3 byte-parity + NormalizeWeights divergence guard + doc fixes; bump SDK 8.5.0 -> 8.5.1

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

Track l33tdawg/sage

Get notified when new releases ship.

Sign up free

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 →

Beta — feedback welcome: [email protected]