Focus
Agents
Multi-step systems where the hard part is handoffs, state, and failing closed — not a clever prompt.
Agents fail at orchestration, not reasoning. A chain of 90% steps becomes a 59% system unless every boundary is boring and checkable.
This page collects agent work: schema gates between tools, speculative multi-agent setups, graph-augmented retrieval, and compliance copilots that explain their rules. More builds will land here as they ship.
On this shelf
Compliance Agent · Work · open sourceExplainable YAML rule packs over RAG retrieval — screening, not unsupervised legal advice.OpenDeterministic gate for multi-agent validation · WorkFail-closed checks between agent steps so bad state does not propagate.OpenGraph-augmented agentic RAG · WorkWhen vector search is the wrong topology and the graph is the unit of reasoning.OpenAgents fail at orchestration, not reasoning · NotesWhy multi-agent accuracy compounds down, and what to instrument first.Open
More agent systems · Coming soonAdditional production and open-source agents will be listed here as they are ready to show.Soon