Memory & knowledge

P

Reasoning-based RAG system for chatting with long PDFs. Supports local and online files.

M

Persistent memory for AI assistants. Store, search, and recall across sessions.

P

Local-first memory brain for AI coding agents: hooks capture sessions, beliefs injected per prompt.

F

Operate a floGPT workspace: AI voice agents, call transcripts, CRM, knowledge and outbound calls.

E

Shared, verifiable memory for machines and AI. Encode where data lives; decode with any AI.

F

MCP server for Freshdesk, tickets, contacts, companies, agents, groups, and knowledge base.

R

Research workspace for Zotero + Obsidian + NotebookLM. Search, ingest, sync, verify briefs.

C

External Brain for AI Agents - persistent versioned memory for creators

M

MCP server for a project's context (AGENTS.md), memory, and identity, base or drop-in extension.

L

Embedded, local-first agent memory: one SQLite file per namespace, no server, no cloud.

L

Local memory for Claude Code. Semantic recall across session history with zero API calls.

C

37-tool MCP server: context health, memory, reasoning, truthfulness & research pipeline.

S

Salesforce AgentForce knowledge graph, 40 nodes, Einstein Trust Layer, 11x fewer tokens than RAG.

C

97-domain knowledge graphs for AI agents, 4× F1 of RAG, 11× fewer tokens. MCP-native.

C

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

N

NVIDIA AI knowledge graphs, 20 domains. 4x F1, 11x fewer tokens, SHA-256 provenance. MCP-native.

N

NVIDIA NemoClaw knowledge graph, 55 nodes, F1 0.576 (+269% vs RAG), 11x fewer tokens. MCP-native.

S

MCP-first agent learning: capture failures, validate lessons, retrieve context, improve.

C

Lint AI agent context files (CLAUDE.md, AGENTS.md, etc.) against your actual codebase

R

Read-first Redis MCP: SCAN key explorer, keyspace/TTL/memory/slowlog stats, DBA advisor

C

Model Context Protocol server for CiviCRM, AuthX-first, schema-introspected, write-gated.

M

Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token.

A

Collaborative engineering KB for a mile-high city. 9 tools, 8 domains, 32 entries.

C

Local-first AI PKM memory for coding conversations.

Z

Ziggs delegate MCP: chat, agreements, context, payments via OAuth or operator key.

A

Save AI-agent handoff checkpoints, WorkStash notes, and WorkThreads in a local A2CR workspace.

L

Invoke deployed LLMGraph no-code LLM workflows (chat, RAG, automations) as MCP tools.

C

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

M

Typed, calibrated and certified decisions over a context, with abstention and evidence.

C

Persistent AI memory with shared team workspaces, typed knowledge chunks, and cross-tool support.