Nano Workforce — an Agent Graph Orchestration application for Agentic SDLC: durable BPMN processes that coordinate a graph of AI agents across the software delivery lifecycle.

Raddus Graph local CLI agent graph app.

Agent Graph host assembly: wires the Agent Graph packages to real harness services (storage, subagents, worktrees, compaction, idle) and provides the agentGraphController service the supervisor tools consume.

Install and run the agent-graph code graph CLI.

Agent Graph supervisor wake delivery: idle-gated host runtime over the durable wake rows.

Session projection unit: the standing agent-graph snapshot folded from the host's graph/change publishes.

Agent Graph supervisor tools: view_agent_graph, update_agent_graph, yield_agent_graph over a host-provided graph controller, with the orchestration:graph prompt section.

Agent Graph stream layer: pure derivations (records, trace, readiness, handoff, schedule reconcile) and the process-local coordinator.

Durable control plane for the Agent Graph: schedule updates, exactly-once intent claims, operator provisions, and supervisor wakes.

TongFlow workflow core: ABI, node registry, connection validation, workflow exporter, headless canvas model and agent graph tools.

A LangGraph-inspired Pi agent graph extension with durable execution, bounded state, artifacts, and explicit agent context modes

Graph Engineering for Agent Skills: model-free work contracts for fact-grounded routing, progressive context, and recoverable execution.

Operator executor adapter for the Agent Graph: deterministic worktree leases, durable operator bindings, and child-run serialization with terminal record emission.

A portable, dynamic multi-agents workflow system for complex codebases. Reads cc-switch config, selects the right agent architecture (loop / orchestrator-workers / multi-agent / graph / dynamic / ultracode), generates per-agent configs, enforces cost-rate

BuilderForce Agent Memory — runtime layer. SSM execution, Transformer orchestration, online distillation, enterprise RAG (ingestion pipelines, vector-store adapters, tenant/ACL-scoped hybrid retrieval), multi-agent graph orchestration, LLM telemetry and c

Execution graph for AI agents using Circle Agent Stack services. Records what the Circle CLI did; never executes, never pays.

Lightweight graph orchestration for DeepSeek Harness: scoped agent nodes, handoff contracts, bounded rework, and a layered global ledger.

TypeScript SDK for Agent Graph Builder: typed API client, run streaming, graph helpers, React hooks and an MSW test kit

OpenCode plugin for in-terminal agent graph visualization

MCP server that builds a reachability graph across multi-agent orchestration configs (LangGraph, CrewAI, AutoGen/ag2) to find transitive excessive agency — an agent with no dangerous tool of its own that can still reach one through delegation or group mem