l33tdawg/sage

v7.0.0 Feature

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

Published 20d 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

Introduces Claude Code lifecycle hooks for SAGE auto-capture as v7.0 groundwork.

Changes in this release

Type	Severity	Summary	CVE
Feature
Feature	Medium	LongMemEval-S harness for SAGE v7.0 hybrid recall added LongMemEval-S harness for SAGE v7.0 hybrid recall added Source: llm_adapter@2026-05-21 Confidence: high	—
Feature	Medium	direct-write SessionStart and SessionEnd hooks introduced (Option A for v7.0) direct-write SessionStart and SessionEnd hooks introduced (Option A for v7.0) Source: llm_adapter@2026-05-21 Confidence: high	—
Feature	Medium	Claude Code lifecycle hooks enabled for SAGE auto-capture (v7.0 groundwork) Claude Code lifecycle hooks enabled for SAGE auto-capture (v7.0 groundwork) Source: llm_adapter@2026-05-21 Confidence: high	—
Feature	Medium	Hybrid recall (BM25 ⊕ vector via RRF) and branch-aware memory implemented (v7.0 groundwork) Hybrid recall (BM25 ⊕ vector via RRF) and branch-aware memory implemented (v7.0 groundwork) Source: llm_adapter@2026-05-21 Confidence: high	—
Feature	Medium	hook scripts and HOOKS.md documentation added (v7.0 groundwork) hook scripts and HOOKS.md documentation added (v7.0 groundwork) Source: llm_adapter@2026-05-21 Confidence: low	—

Full changelog

SAGE v7.0.0

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

8abb3f220a8bec8ba9836bc74dc004744171ee1c bench(longmemeval): --per-type sampler + v7.0 30-Q baseline JSON
6cb54b3485b40bf7ee0950005054ce7f8e32803d bench(longmemeval): v7.0 full 500-Q result JSON
3a189062d26c214a60adbd822c59e96091d6914e chore: bump v6.8.8 to v7.0.0 (Recall Quality + Ambient Capture)
030964e7635ff2c5d1079b84747ade77b2210b1a docs(readme): tidy What's New — add v7.0 section, compress v6.8 + v6.7
48e81eca3121d5708d3737f1898ae6fa155989d0 feat(bench): LongMemEval-S harness for SAGE v7.0 hybrid recall
7c1ba92879d441b863aec8346c741e6996326b6b feat(hooks): direct-write SessionStart + SessionEnd (Option A for v7.0)
71b3b814ace218085b954c45ed6a530c9b88800e feat(hooks,docs): Claude Code lifecycle hooks for SAGE auto-capture (v7.0 groundwork)
954d8a51aae8ba79143d8e283ffd02fcb916fc2e feat(hooks,docs): add hook scripts + HOOKS.md referenced by previous commit
6ac4f33833a0e6fc01e73dedf13a50fad7a68814 feat(store,rest,mcp): hybrid recall (BM25 ⊕ vector via RRF) + branch-aware memory (v7.0 groundwork)

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 →