by agentkitai
Cross-agent memory over MCP: hybrid recall, knowledge graph, private/shared visibility, redaction.
pypi:lore-sdk · local packagepublished 2 mo ago
Storage, memory and knowledge management for agents.
Cross-agent memory over MCP: hybrid recall, knowledge graph, private/shared visibility, redaction.
Comprehensive tools for discrete mathematics: logic, algorithms, number theory, cryptography
Static code map generator: MAP.md + map.json for any repo, plus a Claude Code /map plugin
NVIDIA NemoClaw knowledge graph — 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.
NVIDIA AI knowledge graphs — 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.
NVIDIA Nemotron + Perplexity Sonar as knowledge graphs — 2 domains, 83 nodes. MCP-native.
97-domain knowledge graphs for AI agents — 4× F1 of RAG, 11× fewer tokens. MCP-native.
Salesforce AgentForce knowledge graph — 40 nodes, Einstein Trust Layer, 11x fewer tokens than RAG.
Official, multi-account Instagram Graph API MCP: read, publish, analytics, comments, DMs.
Persistent knowledge system with OWL-RL reasoning and 22 MCP tools. Local-first.
Save AI-agent handoff checkpoints, WorkStash notes, and WorkThreads in a local A2CR workspace.
A neutral memory quality-gate MCP server: save_memory, recall_memory, forget_memory over stdio.
Knowledge graph for AI agents. Query concepts, walk edges, get advisories.
Persistent long-term memory for Claude Desktop / Claude Code, backed by EvolutionDB.
Persistent memory for any AI — zero token cost until recall
Coordination memory with verification: reconcile-against-GitHub, verdict freshness, provenance.
Long-term memory for AI agents: semantic facts, episodic events, and procedural workflows
Persistent memory, task coordination, and HITL queue for AI coding sessions.
Persistent memory layer for AI coding agents — your agent remembers what you taught it.
Persistent memory + context layer for AI dev teams. 17 tools via MCP.