10 projects
ckg-ai-platforms
AI developer and agent platforms as source-pinned traversable knowledge graphs - MCP-native
langchain-ckg
LangChain retriever backed by Compact Knowledge Graphs (CKG) — deterministic, SHA-256 anchored, MCP-native
ckg-nvidia-ai
NVIDIA AI developer stack as a traversable knowledge graph — 20 CKGs, 1006 nodes, MCP-native
ckg-nvidia-nemoclaw
Auditable knowledge graph for NVIDIA NemoClaw with cryptographic source traceability — 3.8× F1 over RAG, 11× fewer tokens, MCP-native, deterministic agent answers
ckg-agentforce
Salesforce AgentForce as a traversable knowledge graph — 40 nodes, Einstein Trust Layer, Resolution Criteria, 2-dollar-per-resolution billing path. 11x fewer tokens than RAG. MCP-native.
ckg-agent-protocols
Agent protocol stack as traversable knowledge graphs — A2A v1.0, x402, MCP 2026-07-28, ERC-8004, Google ADK, SDK ecosystem. 460 nodes, 8 domains, SHA-256 provenance. MCP-native.
ckg-mcp
Context optimization for AI agents — 97 domain knowledge graphs (68 free + 29 Pro), MCP-native traversal. 4× F1 of RAG, 11× fewer tokens per query. Works with Claude, GPT-4o, Gemini, and any MCP client.
ckg-nemotron-perplexity
NVIDIA Nemotron + Perplexity Sonar as traversable knowledge graphs — 2 domains, 83 nodes, MCP-native agent traversal.
ckg-nvidia-nemotron
Compressed Knowledge Graph for NVIDIA Nemotron 3 Ultra 550B A55B — 71 nodes, 120+ edges. Architecture, training pipeline, reasoning modes, deployment, benchmarks, and agentic integrations.
ckg-nvidia-guardrails
NeMo Guardrails as a traversable knowledge graph — 50 nodes, MCP-native, free
