Skip to content

Acacian/aegis

v0.1.0 Feature

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

Published 2mo MCP Security & Auth
✓ 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

Introduces a policy engine with YAML rules, five adapters, and an SQLite audit log.

Full changelog

Aegis v0.1.0

Open-source policy & approval runtime for AI agents acting on systems you don't own.

Install

pip install agent-aegis

What's included

  • Policy engine — YAML rules with glob matching, 4 risk levels, 3 approval modes
  • 5 adapters — Playwright, LangChain, CrewAI, OpenAI Agents SDK, Anthropic Claude
  • Approval handlers — CLI interactive, auto-approve, callback-based
  • SQLite audit log — full action lifecycle tracking
  • Runtime pipeline — plan → approve → execute → verify → audit
  • CLI toolsaegis validate, aegis audit
  • Documentation — https://acacian.github.io/aegis/

Quick start

from aegis import Action, Policy, Runtime

runtime = Runtime(
    executor=PlaywrightExecutor(),
    policy=Policy.from_yaml("policy.yaml"),
)
plan = runtime.plan([
    Action("read", target="salesforce", params={"selector": ".contacts"}),
])
results = await runtime.execute(plan)

See the README for full documentation.

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 Acacian/aegis

Get notified when new releases ship.

Sign up free

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 →

Beta — feedback welcome: [email protected]