47,133 repositories indexed
1–7 of 7 · Most stars
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
"DeepCode: Open Agentic Coding (Agent Harness & Loop Engineering & Multi-Agent Orchestration)"
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
Multi-Agent Harness for Production AI
An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training.
FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproducible evaluation.
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.