Governed recall for AI agents

Give your agent the right memory — not just more memory.

Heartwood filters out stale, superseded, and restricted records before ranking, then returns each answer with a verifiable source trail. Add it beside your existing stack with Python or MCP.

python -m pip install "heartwood-memory[recall,mcp]" · embedded Python · local MCP · source-available

python
from heartwood import Heartwood, Principal

hw = Heartwood(
    path="./heartwood.db",
    tenant="tenant:acme",
)

hw.remember(
    "Refunds over $500 require finance approval.",
    subject="policy:refunds",
    created_by="agent:support",
)

# signed, provenance-carrying, tenant-scoped recall
principal = Principal(
    id="agent:support",
    tenant="tenant:acme",
    clearance="internal",
)
hits = hw.recall(
    "what is our refund policy?",
    principal=principal,
)
Evidence, not adjectives

Inspect the proof behind every trust claim.

0.812
Benchmark — 56 queries, held-out
Typed-router MRR@10

Product-path enterprise retrieval over 56 queries (nDCG@10 0.818).

100%
Trust-suite gate
Provenance coverage

Every recalled memory carries its source chain, model version, and signature.

0
Trust-suite gate — adversarial probes
Policy leaks

Zero cross-tenant policy leakage under adversarial probes in the single-trust-domain trust suite.

30/30
Trust-suite gate
Trust gates passing

Retrieval, policy, faithfulness, deletion, egress, and resilience gates.

<500ms
Controlled benchmark — not a production SLO
Warm recall p95

The pre-registered Phase 1 gate, measured warm with the store, index, embedder, and reranker hot in one process. On our hosted gateway, real production p95 measured 795ms across 873 recalls over a 7-day window in July 2026. We publish the benchmark because it is the budget we design hook- and agent-loop integrations against — not a service level we commit to.

0.972
Benchmark — filtered-search evaluation
Filter-first MRR@10

Policy-before-ranking vs. 0.000 leakage when filtering after the vector search.

Every figure above states how it was measured. Gate results come from executable gates in the Heartwood core with pre-registered thresholds and paired-bootstrap confidence intervals; figures marked as benchmarks are controlled measurements and are not production service levels.

What makes it governed

Five ways Heartwood keeps agent memory trustworthy.

Stop stale memory from answering

Validity windows and supersession keep expired or replaced records out of default recall. Historical records stay available when you intentionally ask for an audit or past-state view.

Filter before you rank

Heartwood removes memories the agent is not cleared to use before search scoring begins. Restricted records are never scored or returned.

Trace every answer to its source

Each memory is signed when stored and rechecked when recalled. Results include source IDs, content-hash status, and a provenance tree that follows derived memories back to their origins.

Detect changes in the record

Remember, expiry, supersession, and deletion events join a hash-chained audit log. Verification detects an edited or missing row, so the history can be checked instead of merely trusted.

Integrate without replacing your stack

Use the embedded Python library or a local MCP server beside your existing systems. MCP starts read-only unless you explicitly enable write or erase tools.

Need to erase a subject? Hard-delete destroys the per-subject key, purges governed derivatives, and returns a receipt; it does not claim byte-level deletion proof.

Who it’s for

For agents where being wrong is expensive.

Built for teams running high-stakes agents over support tickets, customer records, operational Postgres, internal policy and knowledge bases, and compliance-sensitive workflows — teams that already have agents but need stronger answers for provenance, policy, deletion, and auditability.

Regulated support agents

Answer from policy and customer evidence, cite where every claim came from, and get a key-destruction receipt — key destroyed, derived artifacts purged — when a customer is deleted.

Operations & workflow assistants

Carry workflow memory and audit trails across long-running tasks without leaking one tenant’s state into another.

Research & synthesis agents

Produce source-grounded summaries that are gated on faithfulness before they are trusted as memory.

Compliance-sensitive copilots

Keep restricted material behind classification clearance; on governed generation paths, egress is evaluated before the external-model call — by policy, not by prompt.

The control plane between your agents and your systems of record — not a replacement for your database, and not “unlimited memory.”

The path in

See governed recall in one working example.

1

Install

Add the embedded library with one pip command, or start the local MCP server.

2

Remember

Store one policy or fact with its subject, source, and access rules. Heartwood signs it and records the write.

3

Recall and verify

Ask one question, then inspect the returned source IDs, signature status, and recall explanation.

Pricing

Source-available core. Pay when you need governance backed by a team.

Community

Free
Source-available core, self-hosted

Engineering teams proving the fit.

Free to read, run, and self-host for non-production use at any size. Organizations that qualify as a Small Organization under the licence — fewer than 100 employees and contractors, and under $1,000,000 in total revenue in the prior tax year — may also run it in production at no charge. See the LICENSE for the controlling definition.

  • Embedded library (Python) + MCP server
  • Provenance, typed memory, policy-gated recall
  • Crypto-shred deletion + tamper-evident audit
  • Run the governance test suite yourself
  • Community support
Start free

Team

$349/mo
Per organization, billed monthly

Organizations taking governed memory from a laptop into production.

Team is sold through a short conversation — we scope the deployment before it starts.

  • Everything in Community
  • Production recall gateway, hosted by us — serve recall to your app, authenticated and remote (or self-host it from the source-available core)
  • Supported production deployment configuration
  • Commercial-use license for production
  • Email support (no SLA)
Talk to us
Most popular

Professional

$6,000/year
Per organization, billed annually

Organizations governing agent memory under compliance pressure.

Professional is available now. Annual subscription, billed once per year, renews automatically until cancelled.

  • Everything in Team
  • Dedicated isolated tenant — your own instance, volume, and hostname; per-credential principal binding enforced server-side
  • Per-answer evidence — every recall returns a hash-chained audit row and an explain_recall rationale you can re-run
  • Priority support with a one-business-day response target (defined in Terms of Service §16.K) and security advisories
Buy Professional

Enterprise

Let’s talk
Scoped per organization, custom quote

Regulated organizations with auditors in the room.

Enterprise is scoped by conversation and billed by custom quote.

  • Everything in Professional
  • Self-hosted and air-gapped deployment, scoped with you
  • Custom framework adapters and audit consulting
Contact sales

Professional is billed annually through Edukas Solutions and renews automatically until cancelled. Team and Enterprise are scoped by conversation. Prices are per organization, in USD. Subscriptions are currently offered to organizations in the United States only.

See whether Heartwood fits your hardest agent.

Bring the agent, the data it recalls, and the rule it cannot break. We’ll map the smallest governed-memory path and show which claims you can verify yourself.