10 projects
endless-learning
Knowledge-graph-driven synthesis of verifiable RL training tasks (open reproduction of the Kimi K3 task-synthesis pipeline)
swerl
Swarm Engine RL — a reinforcement learning framework for training LLM agent swarms.
openrsi
Toolkit for managing agentic self-improvement pipelines.
autonomation
Autonomation — name reservation placeholder. Real SDK coming soon.
cognitive-core
Cognitive Core - A meta-learning framework for learning from agent trajectories
acp-factory
A library for spawning and managing agents through the Agent Client Protocol (ACP)
openasi
OpenASI - coming soon
git-checkpoint
A Git-based workspace state management system
sudocode
A simple Python library
autogenesis
A simple Python library
