This release adds 3 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
Summary
AI summaryUpdates Quick Start (sage-gui) ```bash, sage-gui, and mcp across a mixed release.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Adds corroboration integrity guard and on-chain author field to app-v10. Adds corroboration integrity guard and on-chain author field to app-v10. Source: llm_adapter@2026-06-04 Confidence: high |
— |
| Feature | Medium |
Adds sage_corroborate tool exposing corroboration on the MCP surface. Adds sage_corroborate tool exposing corroboration on the MCP surface. Source: llm_adapter@2026-06-04 Confidence: high |
— |
| Dependency | Low |
Bumps SDK version from 9.1.0 to 9.2.0. Bumps SDK version from 9.1.0 to 9.2.0. Source: llm_adapter@2026-06-04 Confidence: high |
— |
Full changelog
SAGE v9.2.0
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
- 80d62a4e48c03d8da5e1f8345f58e47efcd97944 feat(abci,store): app-v10 fork — corroboration integrity guard + on-chain author field
- 0a28c8afac7ca37c23cf304db76f947c41e724a2 feat(mcp): sage_corroborate tool exposing corroboration on the MCP surface (issue #31, by @ihubanov)
- 43e4fc29d16d3f4b9d1b82a4a485dd9518d70932 release(v9.2.0): app-v10 corroboration integrity guard + on-chain author field + sage_corroborate MCP tool; bump SDK 9.1.0 -> 9.2.0
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
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.
Related context
Related tools
Beta — feedback welcome: [email protected]