Knowledge & Memory

Persistent memory graph for coding agents: hypotheses, evidence, and decisions survive sessions.

Code intelligence MCP server: impact analysis, dependency graphs, dead code detection.

Local-first, auditable memory for MCP-compatible AI agents with explicit writes and SQLite storage.

Local deterministic BM25 memory for AI agents. Offline-first, no API key, SHA-256 shards, stdio.

File-first, local-first MCP memory for AI coding assistants: Markdown + YAML, no vector DB.

One searchable memory of your Claude.ai chats and Claude Code sessions, served over MCP.

Bitemporal memory for AI agents with point-in-time recall and tamper-evident audit history.

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.

AI agent security: prompt injection detection, semantic memory, output scanning, prompt hardening

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.

Tracks documented and undocumented Microsoft Graph API schema changes, with an MCP Apps visualiser

Offline agentic memory: remember/recall/relate/forget/why over a fused vector+graph+columnar engine

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.

Persistent memory for Claude Code. Search, recall, and re-inject context from any session.