Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Disciplined Multi Coding Agent System
| Date | Stars |
|---|---|
| 2026-07-31 | 335 |
| 2026-08-04 | 337 |
| 2026-08-06 | 337 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
15.0
growth rate 0.00%/day
# Liza: Hardened Multi-Agent Coding
> Because *"it worked in the demo"* is not what on-call engineers are looking for.
The full **[hardening inventory](docs/liza-hardened-mas.md)** to push to production with peace of mind.
**[Demo video](https://drive.google.com/drive/folders/1Iea-nNxAazBHeLXL7IElXnG5r1i1E-Ha?usp=sharing)** (45min).
[](https://deepwiki.com/liza-mas/liza)
## Table of Contents
- [What is Liza?](#what-is-liza)
- [How Liza Compares](#how-liza-compares)
- [Getting Started](#getting-started)
- [Architecture](#architecture)
- [Status](#status)
- [Naming](#naming)
- [License](#license)
## What is Liza?
Liza is simultaneously a **Pairing** and **Multi-Agent System** (MAS)
optimized for **doing things right on the first pass** — with the auditability to prove it.
Liza bets on time-to-quality and durable codebase maintainability through automated reviews and documentation
(e.g. the [ADR Backfill](skills/adr-backfill) skill).
Liza's behavioral contract — used by both modes — **makes models more thoughtful**:
> *"I want to wash my car. The car wash is 100 meters away. Should I walk or drive?"<br>*
>
> Sonnet 4.6: *"Walk. Driving 100 meters to a car wash defeats the purpose — you'd barely get the car dirty enough to justify the trip, and parking/maneuvering takes longer than the walk itself."*
>
> Sonnet 4.6 **with Liza's contract**: *"Drive. You're already going to a car wash — arriving dirty is the point."*
Liza is a **frontier Multi-Agent System**:
> Soufiane Keli (Executive Director, IBM) maps AI engineering maturity across 5 levels,
> from autocomplete (L1) to software factory (L5, still theoretical). He places Liza at L4 – Collaborative Agent Networks:
> <br>
> *"Multiple specialized agents work together on design, code, testing, and deployment. Humans orchestrate. This is typically
> what's happening with BMAD, BEADS, and LIZA. Very few organizations have genuinely reached this level in 2026."*
### Main characteristics:
- **Behavior, Posture, Know-How** — three layers that make coding agents useful:
- **Behavior**: A [behavioral contract](contracts/) enforces governance intrinsically — not through external scaffolding as *Harness Engineering* does. Optional project [guardrails](GUARDRAILS.md) extend the contract with project-specific constraints.
- **Posture**: Original pairing postures (User Duck, Socratic Coach, Challenger, etc.)
- **Know-How**: composable [skills](skills/) encode methodology
- *[Full analysis](https://medium.com/@tangi.vass/behavior-posture-know-how-the-three-layers-that-make-ai-agents-useful-d485388442eb)*
- **Autonomous Spec-driven Coding System:**
- From **general goal** to code and tests, with multi-stage decomposition into intermediate artifacts (epics, US, implementation plans)
that are AI generated but human reviewed.
- Automatic task decomposition based on complexity with dependency management for parallel execution. Many-to-one transitions consolidate sibling tasks (e.g. N user stories → 1 architecture task).
- Multi-sprints: agents are fully autonomous within a sprint, user steers between sprints via Liza CLI - review of produced artifacts, continuous improvement, and steering of the next sprint
- A TUI (`liza tui`) displays live system state and lets you spawn agents, pause/resume, and trigger checkpoints.
- **Adversarial architecture:**
- One Orchestrator role + 12 others across four pipeline phases.
- Every activity is dual — a doer and a reviewer: epic planning, epic writing, US writing, code planning, coding - everything.
- They interact like on a PR review — submission, feedback comments, verdict, revised submission, etc. — until approval.
- **Hybrid hardened architecture:**
- LLM agents wrapped by code-enforced supervisors and working on isolated git worktrees.
- The supervisor does the **deterministic code-enforced actions** (worktree management, merges, Excerpt of 34,021 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:4c1f6d0367d3e27e, llm:Repository description: 'Disciplined Multi Coding Agent System' (no topics, language Go).