Help us improve
Share bugs, ideas, or general feedback.
Self-hosted memory layer for Claude Code with hard per-project isolation.
npx claudepluginhub bolnet/attestorThe memory layer for agent teams. Deterministic retrieval, hard per-project isolation, zero LLM in the critical path.
Share bugs, ideas, or general feedback.
Zero-config memory for AI agents. No Docker. No API keys. Just install and go.
AI agents forget everything between sessions. Every new conversation starts from zero — no memory of what you built yesterday, what decisions you made, or what your project even does.
Built-in memory solutions (like Claude Code's MEMORY.md) store flat files that load entirely into the context window every message. No search, no ranking, no contradiction handling. As your project grows, those files become a wall of text that burns tokens without helping.
Memwright gives AI agents persistent, searchable memory that stays out of the context window until needed:
poetry add memwright, add one JSON block, donepoetry add memwright
claude mcp add memory -- memwright mcp
Restart Claude Code. Approve the server once. Done — Claude now has 8 memory tools.
Add to ~/.claude/.mcp.json (global) or .mcp.json (per-project):
{
"mcpServers": {
"memory": {
"command": "memwright",
"args": ["mcp"]
}
}
}
memwright doctor ~/.memwright
Or ask Claude to call memory_health. All 4 components should report healthy: SQLite, ChromaDB, NetworkX Graph, Retrieval Pipeline.