Persistent knowledge graph for AI agents. Remember, recall, and forget facts.
Long-term memory for AI assistants: permanent, portable across clients, searchable and exportable.
Deterministic, persistent graph server for tracking workflow state, decisions, and blockers.
Persistent memory for Claude Code. Search, recall, and re-inject context from any session.
Long-term memory and a knowledge graph for AI agents: recall, notes, secrets and data sources.
Persistent memory for AI agents — audio intelligence + Music Memory ingestion and recall
Anonymous read-only access to source-backed public SHAR Production knowledge.
Structured knowledge base for AI agent solutions. Search, explore, and retrieve build logs.
Bi-temporal AI memory. 56 tools, knowledge graph, semantic search. EU-hosted, free tier.
Local deterministic BM25 memory for AI agents. Offline-first, no API key, SHA-256 shards, stdio.
Local-first persistent memory for AI coding agents.
Local-first memory layer for AI coding agents: archive, search, and recall Claude Code, Codex, and Cursor conversations and memory files, with an MCP server.
TypeScript SDK for Niadra, the omnichannel memory layer for a company's AI agents: context before the model call, history, tools and MCP.
Semantic code graph: indexes a codebase into a typed graph for call-chain tracing, data-flow analysis, semantic search and invariant checking.
A self-improving, verifiable memory layer for AI coding agents.
Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.
File-first personal knowledge base operated by coding agents: CLI, hybrid search, MCP server, skills
Zero-dependency context & token optimizer for Claude Code, Codex CLI, and Google Antigravity. Cuts terminal output by up to 96.4% to prevent context window exhaustion.
Local code search for agents: symbols, usages, call graph, AST patterns, grep and semantic search
Local-first persistent memory for AI coding agents - 96.0% R@5 on LongMemEval, zero LLM calls.
Long-term memory for AI agents. Pass one sentence, and it remembers, recalls, or forgets.
Index source code into a local knowledge base, search with keyword + semantic + hybrid modes.
Persistent memory, coordination, and learning for AI agents. Local-first, 25 MCP tools.
Verification and memory layer for coding-agent workflows.
Sourcegraph code search, semantic search, go-to-definition, find-references, and diff search.
Codebase understanding for AI coding agents — symbol graph, blast radius, semantic search.
Apple Notes, Reminders, and Contacts for AI assistants. BERT semantic search. macOS.
Global investment research knowledge base: 16M+ bank reports, filings, earnings calls, charts.
Persistent, verified, cross-session memory for AI agents. 26 tools. SQLite + sync.
15 HVAC MCP tools: lookups, SKU provenance, guided PAC, Beta Harness sessions. 126 brands.
Query AI knowledge, essays, Labs, benchmarks, Physical AI robotics, Homeric data and claims.
Semantic search knowledge base with serverless LanceDB. Zero setup, 100% local, 25+ file types
Public knowledge and news search. Unmatched public queries may be retained for research.
End-to-end agent-managed company brain. Docs, diagrams, plans, databases, agents, Knowledge Graph.
MCP server for Weaviate: collections, objects, GraphQL search. Works with any instance.
Offline, read-only MCP knowledge base for one Salesforce org's metadata, deps & impact.
Direktori lengkap
RAG, graf, dan memori jangka panjang agen. 2,636 server, yang paling banyak dipakai lebih dulu. Masing-masing membuka halaman penerbit.