Magic post-it notes for your AI tools.

In Claude Desktop, go to Settings → Integrations → Add Custom MCP Server → enter https://mcp.stompy.ai → sign in with OAuth. That's it — 27 persistent memory tools are instantly available. For Gemini CLI, Cursor, or Codex, see /downloads for per-client setup guides.

MCP (Model Context Protocol) is an open standard for AI tool integration, used by Claude, Gemini, Cursor, and others. Stompy exposes 27 MCP tools that your AI can call directly—lock_context to store knowledge, context_search to find it semantically, recall_batch to fetch multiple contexts at once, project_brief for an AI-synthesized project overview, ticket to track tasks, detect_conflicts to find contradictions. You add one config line, your AI gets persistent memory. Not using MCP? Stompy also works via CLI commands and REST API.

No. That's the point. Stompy is fully hosted: PostgreSQL databases, S3 document storage, VoyageAI embeddings, OpenRouter Vision, NLI models—all managed. Add one block to your MCP client config (Claude Desktop, Gemini CLI, Cursor, or Codex) with your API key, and you're done. See /downloads for per-client setup guides.

Yes. Stompy connects via MCP, CLI, or REST API. Context stored by Claude is immediately available to Gemini, Codex, or any other tool. Same API key, same projects.

No. One Stompy account, one API key. Each tool connects through whichever path it supports — MCP for native integration, CLI for terminal access, REST API for everything else.

Local means you manage PostgreSQL, configure VoyageAI API keys, set up S3, handle NLI models, run Ollama. Stompy is instant: one npm command, zero infrastructure. Automatic backups, managed scaling, no DevOps. Focus on building, not maintaining memory servers.

When you call context_search, Stompy uses VoyageAI's voyage-3.5-lite embeddings to convert your query into a vector, then finds contexts with similar meaning—not just keyword matches. Ask 'how do we handle auth?' and it finds your JWT documentation even if it never mentions 'auth'. Similarity scores show match quality (92% match, 78% match).

Stompy stores content as contexts via lock_context. You can store text, code snippets, specifications, and rules as versioned, searchable snapshots. File uploads are available through the web dashboard with async processing. All content gets VoyageAI embeddings for semantic search.

Each project gets its own PostgreSQL schema—completely isolated database tables. Every tool accepts a project parameter, so you just say context_search('auth', project='client-a') and it searches only that project. Zero bleed between projects. Automatic handover loading resumes where your last session left off.

detect_conflicts uses Natural Language Inference (NLI) to find contradictions. If you stored 'always use bcrypt' last month and 'use argon2 for passwords' today, NLI catches the contradiction. resolve_conflict lets you pick the winner: keep_a, keep_b, merge, or dismiss.

Your memory stays. Stompy is the constant. Switch from Claude to Gemini tomorrow — your architecture decisions, rules, and project context are all still there.

Before storing content with lock_context, Stompy analyzes novelty against existing contexts. Content with <10% new information is rejected (mostly redundant). 10-30% novelty triggers a warning. This keeps your knowledge base clean without duplicates. Use force_store=True to bypass if needed.

Yes! db_query runs read-only SELECT statements against your project's PostgreSQL schema. Auto-adds LIMIT 100 for safety. db_schema lets you inspect table structures. Full SQL power with guardrails.

You have full control. Use context_explore to see all stored contexts, db_query to inspect raw data, project_delete to remove a project entirely. The web dashboard provides a visual interface for browsing projects, contexts, and sessions.

No. Stompy uses MCP (Model Context Protocol), an open standard implemented by Claude, Gemini, Codex, Cursor, and others. We're actively adding support for new models as they launch. Your memory is yours — not locked to any AI company.