Acacian/aegis

v0.9.2 Breaking

This release includes breaking changes for platform teams planning a safe upgrade.

Published 1mo MCP Security & Auth

View tool

✓ No known CVEs patched

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

✓ No known CVEs patched in this version

Topics

agent-security ai-agent-security ai-agents ai-governance ai-safety ai-security

+14 more

audit-trail compliance guardrails langchain llm-security mcp mcp-security model-context-protocol pii-detection policy-as-code policy-engine policy-testing prompt-injection selection-governance

Summary

AI summary

GitHub Action now posts policy results as PR comments and README restructured around aegis scan.

Full changelog

What's New

Scan-First Experience

README restructured around aegis scan — "Find ungoverned AI calls in 30 seconds" is now the first thing you see
Playground: new aegis scan demo tab as the default landing experience with 4 presets

GitHub Action: PR Comments

aegis GitHub Action now posts policy results (scan/score/plan/test) as PR comments
Upserts existing comments to avoid spam
New inputs: comment (true/false), github-token

Playground: Policy CI/CD Demo

New interactive "Policy CI/CD" tab with 4 scenarios
Simulates aegis plan → aegis test → PR comment preview workflow

Fixes & Cleanup

Windows compatibility: UTF-8 encoding for YAML files, path normalization, timer resolution
Removed dead MANIFEST.in (hatchling build)
Synced server.json version
Exported 5 previously unreachable modules (killswitch, autopolicy_llm, rate_limiter_redis, tenant, tiers)

Full Changelog: https://github.com/Acacian/aegis/compare/v0.9.1...v0.9.2

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 Acacian/aegis

Get notified when new releases ship.

About Acacian/aegis

Policy-based governance for AI agent tool calls. YAML policies, approval gates, risk assessment, and audit logging. Cross-platform: LangChain, OpenAI, Anthropic, MCP.

All releases →