Knowledge & Memory

Git for your AI's context: local-first, deterministic memory over MCP. An elephant never forgets.

Crash-proof LLM pipelines. Resumes from failure without a database.

Search 529K US statute sections. 50 states + USC + CFR. Semantic search, citation graph, MCP.

Local-first persistent memory MCP: shared SQLite key/value store, searchable, TTL-aware, secret-safe

A label property graph on SQLite/Postgres with multi-ontology routing and a gated MCP server.

Deterministic decision engine with receipts. Define rules in YAML, query a graph, get proof.

Stale-proof repository memory with citations + just-in-time verification + TTL (repo-scoped).

Embedded memory for AI agents with SQLite, pgvector, and Neo4j graph search.

Self-hosted memory for agent teams. Bi-temporal replay, deterministic retrieval, audit log.

MCP server giving AI agents persistent SQLite memory that proves which lessons hold.

Structured session journals for AI agents. Persistent memory across sessions.

Cross-project knowledge graph for MCP — map features across mobile, backend, and admin codebases.

Persistent memory for AI agents — semantic + recency search, ONNX embeddings, Docker Compose.

Persistent agent memory as a single Go binary: knowledge graph, TUI observability, zero infra.

Biologically-inspired persistent memory engine for Claude Code MCP agents

Local-first, source-grounded memory that survives AI agent sessions.

Cross-agent memory over MCP: hybrid recall, knowledge graph, private/shared visibility, redaction.

NVIDIA Nemotron + Perplexity Sonar as knowledge graphs — 2 domains, 83 nodes. MCP-native.

Persistent knowledge system with OWL-RL reasoning and 22 MCP tools. Local-first.

A neutral memory quality-gate MCP server: save_memory, recall_memory, forget_memory over stdio.