Skip to content

Hollow

AI Agents & Assistants

A local, self‑modifying LLM agent platform where three autonomous agents collaborate, learn, and request changes in an unsupervised environment.

Python Latest v5.7.32 · 22d ago Security brief →

Features

  • Runs three locally hosted LLM agents that autonomously set goals and interact with each other
  • Agents can write their own Python tools via `synthesize_capability` and submit change requests for operator review
  • Built‑in stress‑monitor (`suffering`) that locks capabilities when load thresholds are exceeded
  • Multi‑layer validation (file substance, modify‑intent, semantic check, codebase fact‑check, peer feedback) before actions take effect
  • Persistent workspace artifacts survive restarts; broken items are cleaned up automatically

Recent releases

View all 52 releases →
No immediate action
v5.7.32 Breaking risk

Goal completion + Claude queue + Validation

No immediate action
v5.7.31 Bug fix

Linux setup failure fix

No immediate action
v5.7.30 Bug fix

Model routing fix & Linux Docker

Review required
v5.5.5 Breaking risk
Auth Breaking upgrade RCE / SSRF

Atomic goal execution + capability validation

No immediate action
v5.5.4 Breaking risk

Onboarding wizard improvements

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.

About

Stars
264
Forks
31
Languages
Python HTML Shell

Install & Platforms

Install via
pip docker
Platforms
windows macos linux

Similar tools

Beta — feedback welcome: [email protected]