Pinned Loading

1. carl carl Public

   Coherence-Aware Reinforcement Learning (CARL) - breakthrough LLM post-training and test-time training paradigm. carl builds the world's most advanced and intelligent agent systems that are a step c…

   Python 2 1

2. openrouter-deep-research-mcp openrouter-deep-research-mcp Public

   A multi-agent research MCP server + mini client adapter - orchestrates a net of async agents or streaming swarm to conduct ensemble consensus-backed research. Each task builds its own indexed pglit…

   JavaScript 45 11

3. observable-computation observable-computation Public

   Public research artifacts, reproducibility bundle, and package sources for observable computation studies from Terminals Tech

   TypeScript 1

4. agent-zero-openclaw agent-zero-openclaw Public

   Multi-agent orchestration with thermodynamic routing and Kuramoto coherence. Built on terminals.tech primitives.

   TypeScript