agent-aegis 0.9.3

Auto-instrument AI agent frameworks with runtime security. One line to govern LangChain, CrewAI, OpenAI, Anthropic — injection blocking, PII masking, action policy, audit trail. Zero code changes.

Agent-Aegis

Find ungoverned AI calls in your codebase. Fix them before production.

pip install agent-aegis && aegis scan . — detects ungoverned AI calls across 15 frameworks in 30 seconds.
Then add one line to govern them all: aegis.auto_instrument() adds injection blocking, PII masking, and audit trail to 12 frameworks. No code changes.

Try It (30s) • Add to CI • Auto-Instrumentation • Policy CI/CD • Quick Start • Docs • Playground

English • 한���어

---

Try It (30 Seconds)

pip install agent-aegis
aegis scan .

Aegis Governance Scan
=====================
Scanned: 47 files in ./src

Found 5 ungoverned tool call(s):
  agent.py:12   OpenAI        function call with tools= — no governance wrapper  [ASI02: Tool Misuse]
    → Wrap with aegis: import aegis; aegis.auto_instrument()
  tools.py:8    LangChain     @tool "search_db" — no policy check  [ASI02: Tool Misuse]
    → Wrap with aegis: import aegis; aegis.auto_instrument()
  llm.py:21     LiteLLM       litellm.completion() — no governance wrapper  [ASI02: Tool Misuse]
    → Wrap with aegis: import aegis; aegis.auto_instrument()
  run.py:5      subprocess    subprocess.run — direct shell execution  [ASI08: Uncontrolled Code Execution]
    → Use aegis sandbox policy to govern shell execution
  api.py:14     HTTP          requests.post — raw HTTP in agent code  [ASI07: Data Leakage]
    → Route through aegis-governed HTTP client or add policy rule

OWASP Agentic Top 10 Risks:
  ASI02: Tool Misuse & Exploitation: 3 finding(s)
  ASI07: Data Leakage & Exfiltration: 1 finding(s)
  ASI08: Uncontrolled Code Execution: 1 finding(s)

Governance Score: D (5 ungoverned call(s))

Supports --format json|sarif|suggest, --threshold A-F, --no-fixes, .aegisscanignore, and # aegis: ignore inline pragmas.

Add to CI

- uses: Acacian/aegis@v0.9.2
  with:
    command: scan
    fail-on-ungoverned: true

Every PR gets scanned. Ungoverned AI calls block the merge. See all options.

---

Auto-Instrumentation

Add guardrails to any project in one line. No refactoring, no wrappers.

import aegis
aegis.auto_instrument()

# Every LangChain, CrewAI, OpenAI, Anthropic, LiteLLM, Google GenAI,
# Pydantic AI, LlamaIndex, Instructor, and DSPy call now passes through:
#   - Prompt injection detection (blocks attacks)
#   - PII detection (warns on personal data exposure)
#   - Prompt leak detection (warns on system prompt extraction)
#   - Full audit trail (every call logged)

Or zero code changes — just set an environment variable:

AEGIS_INSTRUMENT=1 python my_agent.py

Supported Frameworks

Framework	What gets patched	Status
LangChain	BaseChatModel.invoke/ainvoke, BaseTool.invoke/ainvoke	Stable
CrewAI	Crew.kickoff/kickoff_async, global BeforeToolCallHook	Stable
OpenAI Agents SDK	Runner.run, Runner.run_sync	Stable
OpenAI API	Completions.create (chat & completions)	Stable
Anthropic API	Messages.create	Stable
LiteLLM	completion, acompletion	Stable
Google GenAI	Models.generate_content (new + legacy)	Stable
Pydantic AI	Agent.run, Agent.run_sync	Stable
LlamaIndex	LLM.chat/achat/complete/acomplete, BaseQueryEngine.query/aquery	Stable
Instructor	Instructor.create, AsyncInstructor.create	Stable
DSPy	Module.__call__, LM.forward/aforward	Stable

Default Guardrails

Guardrail	Default	What it catches
Prompt injection	Block	10 attack categories, 85+ patterns, multi-language (EN/KO/ZH/JA)
PII detection	Warn	13 categories (email, credit card, SSN, IBAN, API keys, etc.)
Prompt leak	Warn	System prompt extraction attempts
Toxicity	Warn	Harmful, violent, or abusive content

All guardrails are deterministic regex — no LLM calls, no network. 2.65ms cold / <1us warm per check. Benchmarks.

---

Policy CI/CD

Security tools protect at runtime. Aegis also manages the policy lifecycle.

aegis plan — Preview before deploying

aegis plan current.yaml proposed.yaml --audit-db aegis_audit.db

# Policy Impact Analysis
#   Rules: 2 added, 1 removed, 3 modified
#   Impact (replayed 1,247 actions):
#     23 actions would change from AUTO → BLOCK

aegis test — Regression testing for policies

aegis test policy.yaml tests.yaml              # Run in CI
aegis test policy.yaml --generate              # Auto-generate test suite
aegis test new.yaml tests.yaml --regression old.yaml  # Regression check

# .github/workflows/policy-check.yml
- uses: Acacian/aegis@main
  with:
    policy: aegis.yaml
    tests: tests.yaml
    fail-on-regression: true

---

Quick Start

1. Install

pip install agent-aegis

2. Auto-instrument (recommended)

import aegis
aegis.auto_instrument()
# All 12 frameworks are now governed.

3. Or use a YAML policy for full control

aegis init  # Creates aegis.yaml

# aegis.yaml
guardrails:
  pii: { enabled: true, action: mask }
  injection: { enabled: true, action: block, sensitivity: medium }

policy:
  version: "1"
  defaults:
    risk_level: medium
    approval: approve
  rules:
    - name: read_safe
      match: { type: "read*" }
      risk_level: low
      approval: auto
    - name: no_deletes
      match: { type: "delete*" }
      risk_level: critical
      approval: block

4. See what happened

aegis audit

  ID  Session       Action        Target   Risk      Decision    Result
  1   a1b2c3d4...   read          crm      LOW       auto        success
  2   a1b2c3d4...   bulk_update   crm      HIGH      approved    success
  3   a1b2c3d4...   delete        crm      CRITICAL  block       blocked

---

Install Options

pip install agent-aegis                   # Core (includes auto_instrument for all frameworks)
pip install langchain-aegis               # LangChain standalone integration
pip install 'agent-aegis[mcp]'            # MCP server + proxy
pip install 'agent-aegis[server]'         # REST API + dashboard
pip install 'agent-aegis[all]'            # Everything

MCP Proxy — govern any MCP server with zero code changes

{
  "mcpServers": {
    "filesystem": {
      "command": "uvx",
      "args": ["--from", "agent-aegis[mcp]", "aegis-mcp-proxy",
               "--wrap", "npx", "-y",
               "@modelcontextprotocol/server-filesystem", "/home"]
    }
  }
}

Works with Claude Desktop, Cursor, VS Code, Windsurf. Tool poisoning detection, rug-pull detection, argument sanitization, policy evaluation, full audit trail.

---

Why Aegis?

	Writing your own	Platform guardrails	Enterprise platforms	Aegis
Setup	Days of if/else	Vendor-specific config	Kubernetes + procurement	pip install + one line
Code changes	Wrap every call	SDK-specific	Months of integration	Zero — auto-instruments
Cross-framework	Rewrite per framework	Their ecosystem only	Usually single-vendor	12 frameworks
Policy CI/CD	None	None	None	aegis plan + aegis test
Audit trail	printf debugging	Platform logs only	Cloud dashboard	SQLite + JSONL + webhooks
Compliance	Manual docs	None	Enterprise sales cycle	EU AI Act, NIST, SOC2 built-in
Cost	Engineering time	Free-to-$$$	$$$$ + infra	Free (MIT). Forever.

What Only Aegis Does

Other tools check inputs and outputs. Aegis governs the decision itself.

Capability	What it means	Based on
Selection Governance	Audits what agents exclude, not just what they choose. A model that "helpfully" omits risky options is exerting selection power — Aegis detects this.	Santander et al., arXiv:2602.14606
Justification Gap	6-dimensional asymmetric scoring: agents declare impact; Aegis independently assesses it. Under-reporting triggers escalation or block.	COA-MAS (Carvalho)
Tripartite ActionClaim	Every tool call splits into Declared (agent-authored, untrusted), Assessed (Aegis-computed), and Chain (delegation) fields. The structural separation makes cosmetic alignment detectable.	—
Monotone Trust Constraint	Delegated agents cannot escalate their own authority. Trust levels must be non-increasing along the chain — violations auto-block.	Lattice-based access control
Full Lifecycle	Scan (detect) → Instrument (protect) → Policy CI/CD (test) → Runtime (govern) → Proxy (gateway) → Audit (trace). One library, one pip install.	—

---

CLI

aegis scan ./src/                       # Detect ungoverned AI calls
aegis score ./src/ --policy policy.yaml # Governance score (0-100)
aegis init                              # Generate starter policy
aegis validate policy.yaml              # Validate syntax
aegis plan current.yaml proposed.yaml   # Preview policy changes
aegis test policy.yaml tests.yaml       # Policy regression testing
aegis audit                             # View audit log
aegis serve policy.yaml                 # REST API + dashboard
aegis probe policy.yaml                 # Adversarial policy testing
aegis autopolicy "block deletes"        # Natural language → YAML

Documentation

Full documentation at acacian.github.io/aegis:

• Integration guides — LangChain, CrewAI, OpenAI, MCP, and more
• Policy reference — conditions, templates, best practices
• Security features — guardrails, anomaly detection, compliance
• Architecture — how the codebase is structured
• Interactive playground — try in browser, no install

Contributing

git clone https://github.com/Acacian/aegis.git && cd aegis
make dev      # Install deps + hooks
make test     # Run tests
make lint     # Lint + format check

Contributing Guide • Good First Issues •

License

MIT -- see LICENSE for details.

Copyright (c) 2026 구동하 (Dongha Koo, @Acacian). Created March 21, 2026.

---

_{Policy CI/CD for AI agents. Built for the era of autonomous AI agents.
If Aegis helps you, consider giving it a star -- it helps others find it too.}