Knowledge & Memory

Seven-layer agent memory: episodic, semantic, procedural and core. Local SQLite, no account.

Pi coding-agent package for The Librarian: the 7 memory/handoff tools + primer injection, backed by a remote Librarian MCP server.

It just remembers.

Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.

MCP server that gives Claude Code persistent memory across sessions. Index your codebase once, search symbols, bundle source, scan for vulnerabilities, and checkpoint/resume work — across Java, TypeScript, Vue, Python, SQL and more.

Local-first context engine for AI coding agents. Pre-indexes your codebase into a dependency graph and feeds any MCP agent only the code that matters — 87% fewer tokens per call. New in 2.5: mechanical work verification and a PII/secret scanner. Works wit

Governed graph substrate for coding agents (Claude Code, OpenCode, any MCP-stdio host) — Apply-Gate + on-disk Kuzu store + MCP tools

1-click MCP server for KnowDrive — run `npx -y @knowdrive/mcp` to give any MCP client (Claude Desktop, Claude Code, Cursor) memory backed by your KnowDrive KnowDB.

Hosted persistent memory for AI agents that learns which facts help — feedback re-ranks recall — one key across Claude Code, Cursor, VS Code & ChatGPT, no infra to run

Dependency intelligence for AI agents. CVE scanning, health checks, upgrade planning.

Local-first code graph: index a repo into an import/symbol graph and retrieve the relevant slice instead of whole files. Ships as a CLI, an MCP server for AI agents, a TypeScript API, and a VS Code chat participant.

Persistent memory for agents. Corrections stick, context compounds, every session starts smarter.

Long-term memory for AI coding agents. Memory + CodeGraph + Wiki in one SQLite file. Auto-recall, auto-capture, no API key, no cloud.

Production-grade AI coding toolkit — 70 agents (incl. devil-mode adversarial crew), 194 skills, 97 commands, parallel multi-agent commands, semantic intent routing, self-learning memory, and a built-in MCP server (16 tools / 6 prompts / 377 resources) tha

MCP server that turns TriliumNext Notes into a persistent, graph-structured second brain for Claude and other LLM clients.

Wontopos (WOS) long-term memory (beta) - one memory across Claude Code, Cursor, and your agents.

UnClick gives MCP-compatible agents 667 customer-visible apps and 1586 actions, plus persistent cross-session memory.

MCP server for AutoMem: AI memory storage and recall

Local-first memory, hybrid RAG, and agent personalization for AI coding agents (OpenCode, Claude Code, Codex, Gemini CLI, Antigravity). MCP server + CLI with persistent context, document ingestion, vector + SQLite FTS5 retrieval, sync, setup, and safe uni

Enterprise-ready portable memory for AI agents: encrypted, shareable, provably erased. Join SAIHM.