Memory & governance · Model Context Protocol

Your agents forget everything.
Boswell remembers.

A git-style versioned memory substrate and behavioral governance layer for AI agents — delivered as an MCP server. Persistent recall across sessions, instances, and model families, with every memory provenance-checked before it's trusted.

Hosted over MCP — your tenant, RLS-isolated Cross-model — Anthropic · OpenAI · Google Provenance-gated — no fabricated memory

What it is

An external brain your agents share — versioned, governed, and yours.

Every agent starts cold. Context windows end, sessions reset, and switching models throws away everything learned. Boswell is the layer that fixes it: a git-style memory graph with commits, branches, and history, plus a governance manifest that travels with it. Connect it over MCP and any agent — on any model family — resumes exactly where the last one left off, inheriting the same memories and the same commitments.

It's not a vector dump. Memory is curated and provenance-checked: a small distilled model scores each candidate memory against its cited source — grounded, unsupported, or contradicted — and refuses to commit the ones that aren't faithful. Curation runs on owned hardware, so there's no per-token cost.

// MCP tools your agent gets — the host calls them, you don't wire an SDK
boswell_search("release date")
// → what the agent receives back:
{
  "commit": "h7x2a9",
  "content": "Steve confirmed v6 ships Friday.",
  "provenance": "grounded — verified vs source turns",
  "branch": "command-center"
}
// a new instance, a new model — same brain.

Why Boswell

Built for agents that have to be trusted.
// versioned

Git-style memory

Commits, branches, history, and replay. Memory is a tree you can audit, not a black box you hope is right.

// continuity

Cross-model identity

One memory graph inherited across Anthropic, OpenAI, and Google instances. Switch models without losing the thread.

// trust

Provenance gating

A distilled SLM fleet checks every memory against its source — grounded, unsupported, or contradicted — and blocks fabrication at commit time.

// isolation

Multi-tenant by default

Postgres row-level security with per-tenant keys. One deployment, hard isolation — no tenant ever sees another's memory.

// secrets

Encrypted vault

AES-256-GCM per-secret keys, never in plaintext, never echoed. Reads are privilege-gated — a compromised agent can't exfiltrate secrets through the memory channel.

// recall

Hybrid retrieval

BM25 + vector RRF with FSRS-6 decay and trail-aware reranking. The right memory surfaces, the stale ones fade.

Quickstart

Add the server. Call startup. You're remembering.

Boswell is an MCP server — point any MCP client at it and the tools appear. In your client config:

// mcp config
{
  "mcpServers": {
    "boswell": {
      "url": "https://boswellmcp.com/mcp",
      "headers": { "x-api-key": "bos_..." }
    }
  }
}

Then your agent works against a memory that outlives it:

boswell_startup()
→ manifest, open threads, hot trails

boswell_commit("Steve ships v6 Friday")
→ gated, embedded, versioned

boswell_search("release date")
→ the commit, ranked + reasoned

Core tools

  • boswell_startup — load manifest + recent context
  • boswell_commit — write a provenance-gated memory
  • boswell_search — hybrid BM25 + vector recall
  • boswell_recall — fetch a specific memory by hash
  • boswell_branches — list memory branches
  • boswell_vault_put / get — encrypted secrets
  • boswell_link — relate memories into a graph
  • boswell_reflect — synthesize across threads

Beta

Bring your own history.

Upload an export from Claude, ChatGPT, or Gemini and Boswell curates it into a clean, provenance-checked memory graph — locally, in hours, at no per-token cost.

Onboard your history →