Context GC for LLM agents: offload large tool outputs and recall them to save tokens.
Loading the directory
Loading the directory
MCP servers for embeddings, vector stores, model gateways, and long-term memory.
Context GC for LLM agents: offload large tool outputs and recall them to save tokens.
Local-first personal knowledge base. Cited answers from your vault via vector + graph retrieval.
Ground your LLM in EU financial, crypto and AI regulation, verbatim and cited, via Compass.
SQL Server MCP with RAG capabilities for macOS (Docker SQL Server support)
AI safety middleware — detects self-harm and criminal intent in LLM prompts.
Persistent long-term memory for Claude Desktop / Claude Code, backed by EvolutionDB.
Open, Git-native memory protocol for MCP agents. Portable, versioned, human-editable.
One searchable memory of your Claude.ai chats and Claude Code sessions, served over MCP.
Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.
Git for your AI's context: local-first, deterministic memory over MCP. An elephant never forgets.
Generate QA datasets & evaluate RAG systems with failure diagnosis. Any LLM.
Verified Polish open data for AI agents: debt, budget, 460 MPs, votings, judiciary search, RAG.
MCP server for persistent, semantic memory across AI sessions
Efficient context management: code search, evidence packs, and memory for coding agents.
Local-first personal memory and model server for trusted MCP agents on macOS.
Clarity and memory persistent workspace context manager for Claude.
Dubstrata: Causal Financial & Narrative CDN providing Graph RAG & Deep Research Reports
Through-the-upgrade dependency-migration briefs for LLM coding agents.
Search the Federal Register, read & diff CFR sections, query Regulations.gov. Any LLM supported.
Shared, persistent memory for AI agents — works with Claude, Kiro, Cursor, or any MCP client.
Governed AI-agent memory, Evidence Ledger traces, evals, and portable context tools.
Graph-based memory system for LLMs with knowledge graphs and semantic search.
Persistent memory for AI agents. Remember, recall, and explore a shared knowledge graph.
Expose deterministic ChainWeaver flows as MCP tools without LLM calls between steps.