Skip to content
@aenealabs

aenealabs

Aenea Labs

Aenea Labs

Open source infrastructure for autonomous systems


About

Aenea Labs is the home for open source projects I build and maintain. The focus is on autonomous AI systems, infrastructure tooling, and security engineering for regulated industries.

Everything here is built to ship — production-grade code with real test coverage, real infrastructure, and real documentation.

Projects

Autonomous AI security platform for enterprise code intelligence and security remediation. Multi-agent system that detects vulnerabilities, generates patches, validates in sandboxes, and queues for human approval.

More projects coming soon.

Philosophy

  • Build for regulated environments first, then scale down for everyone else
  • Open source the infrastructure, keep the deployment opinionated
  • Test everything, document decisions, ship with confidence

AI Agent Packages

Open-source packages we maintain for building AI agents. Each lives in its own repository.

We build with a zero-dependency mindset — keeping packages lightweight, auditable, and free of supply-chain bloat wherever the problem allows.

Package Description
polytools Cross-provider LLM tool schema generation from Python type hints Repo →
agentcassette Deterministic agent test recorder and replayer — record live runs, replay as mocks Repo →
contexttrim Pluggable context-window management for LLM agents Repo →
injectionshield Rule-based prompt-injection detection for LLM agents Repo →

Aenea Labs

Popular repositories Loading

  1. aura aura Public

    Autonomous AI Security Platform. (Source Available under BSL 1.1)

    Python 2

  2. .github .github Public

    Aenea Labs organization profile

  3. polytools polytools Public

    Write your tool once. Export to OpenAI, Anthropic, Gemini, and MCP. No framework lock-in, no third-party dependencies.

    Python

  4. agentcassette agentcassette Public

    Deterministic agent test recorder and replayer. Record live runs, replay as mocks. Zero dependencies.

    Python

  5. contexttrim contexttrim Public

    Pluggable context window management strategies for LLM agents. Zero dependencies.

    Python

  6. injectionshield injectionshield Public

    Rule-based prompt injection detection for LLM agents. Zero dependencies, no ML, no network.

    Python

Repositories

Showing 6 of 6 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…