← Back to work
LilBig — Local Multi-Agent LLM Platform
A modular, offline-capable multi-agent platform — OpenAI-compatible gateway, control plane, autonomy engine, RAG, and IDE integration — with a five-mode adversarial peer-review loop and zero hosted-LLM dependency.
- 5-mode
- adversarial peer-review measured
- ~32k
- lines of code estimated
- 0
- hosted-LLM dependencies measured runs fully local / offline
Context
I wanted a senior/junior agent team I could run entirely on my own hardware — no cloud, no per-token bill, no data leaving the building — that could actually maintain and extend itself under review.
What I built
- An OpenAI-compatible gateway fronting two locally-served models, with a control plane and a browser dashboard for full visibility.
- A five-mode adversarial peer-review loop — critic, tester, log-triage, alternate-plan, and implementation-review — so generated work is challenged before it is trusted.
- An autonomy engine with an allow / approve / block policy gating every agent action, least-privilege fail-closed tool bridges, and per-project privacy isolation.
- A deterministic competence benchmark (keyword-rubric, no LLM judge) to measure and gate quality rather than assert it.
Why it matters
The whole system is a study in reliable autonomy: it keeps working, keeps itself honest, and never depends on a hosted model to run.