Acacian/aegis

v0.4.1 Feature

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

Published 2mo 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

New async guardrail APIs and significant performance improvements.

Full changelog

v0.4.1 — Performance & Correctness

13 improvements across 8 files

Performance

Policy cache: FIFO → LRU (OrderedDict + move_to_end)
Rate limiter: pre-compiled glob patterns (module-level _glob_to_re cache)
O(n) → O(log n) timestamp pruning (bisect)
SQLite WAL mode + 4 indexes (session_id, timestamp, agent_id, action_type)
execute(parallel=True) — concurrent actions via asyncio.gather()
acheck() / acheck_and_transform() — async guardrail wrappers

Correctness

Cache key correctness: conditional rules can no longer be shadowed by cached unconditional results
Lock memory leak fix: reset(agent_id) cleans up stale locks
Batch audit flush race: buffer swap moved inside lock
Time-bounded rate calculation for accurate anomaly spike detection

New APIs

AnomalyDetector.check_all() — returns all anomalies simultaneously
GuardrailEngine.acheck() / acheck_and_transform() — non-blocking async
Runtime.execute(parallel=True) — parallel action execution

Install

pip install agent-aegis==0.4.1

Full Changelog

See CHANGELOG.md

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 →