An autonomous agent that automates GitHub contributions end-to-end, from issue analysis and code changes to pull requests, conflict resolution, and review updates.
An autonomous multi-agent orchestration layer that generates a bespoke software engineering organization for a given objective, runs parallel OpenCode workers in isolated git worktrees, and integrates reviewed code through a replan loop.
Enforces structured, evidence-guided software engineering tasks with cognitive actions (investigate, plan, verify, remember) and persistent state for LLM-based coding agents.
A disciplined engineering harness for AI coding agents that provides ground-truth MCP tools and adversarial enforcement skills to transform generic LLMs into high-precision engineers.