Capability-driven autonomous project execution engine. Iterates an Operator loop over a goal, dispatching modular capabilities (Architect, CodeGenerator, TestRunner, BugFixer, etc.) until the project reaches a desired artifact state. No LangGraph dependency — designed as a standalone Layer 2 that antcrew (Layer 1) builds on top of.
Provider-agnostic multi-agent coding orchestrator in Go. Unified router for any LLM provider (Ollama local+cloud, OpenAI, Anthropic, Google Gemini) with role-based model assignment, fallback chains, and cost tracking. Inspired by gastown and LiteLLM.
Self-hosted AI gateway — route, observe, and control your LLM API traffic. OpenAI ↔ Anthropic protocol translation, cost-based smart routing, per-user budgets, built-in dashboard. Zero dependencies.
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
Local orchestration for Claude Code — session recovery, scheduling, worktrees, Token Saver, and dashboards via official CLI transport. Independent third-party software.