allinluna¶

⭐ 41 · ✅ active · agent · ⬆️ +2 recently


Type	agent	Category	Multi-agent
Stars	⭐ 41	Status	✅ active
Author	zenx0x	Updated	2026-08-14

One-liner¶

Resource-aware multi-agent orchestration for Codex and DeepSeek Harness (All in Flash DSH plugin).

About¶

简体中文 Give All in Luna one big goal. It turns the work into independent top-level tasks: run what can run in parallel, wait only on real dependencies, keep each task's context separate, and bring the results back together. Each task can still use its own subagents, tools, Skills, or MCPs. Parallel across tasks. Recursive inside tasks. ---

✨ Key Features¶

the context keeps growing;
unrelated work starts contaminating other work;
earlier constraints become easier to forget;
one local blocker stalls the whole flow;
subagent results become harder to manage;
a new conversation has to reconstruct what really happened;

📦 Install¶

python -m pip install "allinluna==2.0.0rc7"

allinluna --db C:/absolute/path/runtime.db start --goal "Finish the authentication refactor" --repository-root C:/absolute/path/repository
allinluna --db C:/absolute/path/runtime.db status RUN_ID --invariants
allinluna --db C:/absolute/path/runtime.db drive RUN_ID
allinluna --db C:/absolute/path/runtime.db lane finalize RUN_ID TASK_ID

🚀 Quick Start¶

allinluna --help

📚 Learn more¶

Example

Suppose you say: > “Refactor this application's authentication system, including backend, frontend, migration, and tests.” All in Luna can organize it as: Authentication refactor ├─ Task 1 — Auth backend │ ├─ session/token logic │ ├─ API │ └─ backend tests │ ├─ Task 2 — Frontend auth flow │ ├─ login │ ├─ logout │ └─ protected routes │ ├─ Task 3 — Migration │ └─ waits for auth contract │ └─ Tas

You do not have to configure anything

Most users do not need to choose a model policy first. If you do not specify one, All in Luna uses resources available through the current environment, host, or deployment policy. It does not require every user to use one fixed model or provider.