BaseMouse

UNIT: AGENT-MEMORYREV: 0.3STORE: CROSS-TOOL

ONE MEMORY FOR YOUR AGENTS, EVERY AI TOOL.

Your project context is trapped per tool: a CLAUDE.md here, a Cursor rules file there, the whole project re-explained to every new agent. BaseMouse gives your agents one shared memory across Claude Code, Cursor, Kiro and Grok, through a single MCP server. Every answer carries its source and version history, so you can always check what the agent was told.

Get your key Run the demo Agent governance demo Design partner intake

live session — basemouse.com

run

agent context DevOps runbook memory capsules provenance

capability matrixverified in production

ADD YOUR DOCUMENTS

Point BaseMouse at a folder of your docs. It reads them, keeps every version, and labels them so they're easy to find. Re-import whenever you like, with no duplicates, and a clear report if any file doesn't go through.

30sfolder → searchable

YOUR AGENT ASKS, AND GETS SOURCED ANSWERS

Your agent makes one request and gets back the most relevant passages, each with its source, a fingerprint that proves it hasn't been tampered with, and how recently it was updated. Ready to drop straight into a prompt.

1endpoint to integrate

SEE EXACTLY WHAT YOUR AGENT WAS TOLD

Every change is recorded, and nothing is ever silently overwritten. Even deletions stay on the record. So you can always answer two questions: where did this answer come from, and what changed since?

**100%**of edits preserved

SWITCH TOOLS, KEEP YOUR CONTEXT

Register each tool once — Claude Code, Cursor, Kiro, Grok, and more. Every one reads the same grounded context, and whatever an agent writes back in one tool is there for an agent in another, even a different vendor. Your docs and your agents' memory move with you; only the live chat stays inside each tool.

1context, every tool

APINO SDK REQUIRED

ONE CALL FROM YOUR AGENT.

The demo docs need no key. Your documents need one header.

For your engineers: it's a single HTTP call, no SDK to install. The endpoints below show exactly what comes back.

• GET /api/context-pack — cited, checksummed pack
• GET /api/search — ranked matches with scores
• POST /api/documents — your docs in (Bearer bm_…)
• GET /api/documents/:id/history — the full record

GET /api/context-pack copy curl

curl -s "https://basemouse.com/api/context-pack?q=agent%20context&limit=2"

{
  "schema": "basemouse.context_pack.v1",
  "entryCount": 2,
  "citations": [ { "label": "[agent-context-engine] …" } ],
  "entries": [ {
    "title": "Agent Context Engine",
    "relevance": { "score": 6, "matchedTerms": ["agent","context"] },
    "provenance": { "checksum": "e765f4dce81039b4", "version": 3 }
  } ]
}

RATE CARD

Pick a plan → pay → key issued instantly, shown once. Billed through Stripe. BaseMouse never sees your card.

loading plans…

OPEN COREMIT LICENSED

RUN THE CORE YOURSELF.

BaseMouse is open source at its heart. The engine that imports your docs and serves sourced answers is free and MIT-licensed. Run it on your own servers, with nothing phoning home. The paid hosted version just handles the running, billing, and support for you, so you don't have to. See the docs for exactly which features ship today versus what's on the roadmap.

View on GitHub Open-core docs

FAQPLAIN ANSWERS

QUESTIONS, ANSWERED.

What does BaseMouse actually do?

It's a place to store the documents your AI agents read from. You import your docs, your agent asks a question over one API call, and it gets back the most relevant passages with a source on each one. Every change to every document is kept on the record, so you can always check where an answer came from.

How is this different from a vector database or building RAG myself?

A vector database gives you one ingredient. BaseMouse is the finished dish: import, search, citations, tamper-proof fingerprints, and full change history behind a single endpoint. No pipeline to build, no SDK to install, nothing to keep in sync.

What can I import?

Folders of markdown today. Labels in your files are kept and made searchable, and re-importing is always safe: no duplicates, and a clear report if a file doesn't go through. Docs can also stay in sync on their own: a GitHub Action pushes a repo's agent docs on every push, and a small cross-platform CLI syncs a whole projects folder — or watches it and pushes the moment you save. Bringing docs from another source? That's exactly what the design partner program is for.

Do you train AI models on my documents?

No. BaseMouse stores your documents and serves passages back to your own agents. That's the whole job. Our operational telemetry never includes document contents, and if you self-host the core, your docs never leave your servers at all.

Can I run it myself?

Yes. The core engine is MIT-licensed and self-hostable, with no license key and nothing phoning home. The paid hosted version adds the running, billing, and support. Grab it on GitHub.

How do my agents connect?

One HTTP call, from any language or agent framework. The demo needs no key at all, and your own docs need one header. See the API section for the exact request and response. Prefer a native connection? BaseMouse speaks the Model Context Protocol at POST /mcp, so agents like Claude Code, Cursor, Codex CLI, Gemini CLI, and Grok CLI connect directly — the samesearch and get_context_pack tools, plusupsert_document so an agent can write its own decisions back (idempotently — unchanged content writes nothing), same auth and quota.

Can agents write to it, or only read?

Both. Reading is the common case — grounded, cited context packs — but agents can also persist notes and decisions by stable id via the API (?mode=upsert) or the upsert_document MCP tool. Every write is a versioned, append-only revision, so it doubles as durable agent memory across sessions without ever losing history.

Does my context follow me across tools?

Yes. Point each tool at BaseMouse once, and every one of them — Claude Code, Cursor, Kiro, Grok, and more — reads the same grounded context. Anything an agent writes back is immediately readable by an agent in a different tool, even a different vendor: your knowledge and your agents' memory travel with you. (The live chat inside each tool stays local to it — BaseMouse is the shared knowledge and memory layer, not a transcript-sync service.)