Heartwood Memory — governed memory for AI agents
Heartwood Memory — governed AI agent memory; signed provenance.
Connector by jermayne36 · GitHub account verified by the MCP Registry
Chalk Labs
Need help deploying Heartwood Memory — governed memory for AI agents?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/jermayne36-heartwood-memory
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 26, 2026.
- Tools
- 5 read · 1 write · 0 delete · 2 not yet classified
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Python package
Tools by what they do 8
Read from the source code; the running server may list different tools.
Read 5 · Look things up without changing anything.
assess_faithfulnessevaluate_egressexplain_recallhealthrecall
Write 1 · Create, change, send or run things.
remember
Not yet classified 2 · We could not tell from the name and description.
forgetmemory
Secrets and settings it asks for
Other settings (environment variables or headers).
HEARTWOOD_DB_PATHHEARTWOOD_MCP_ALLOWED_TOOLSHEARTWOOD_TENANT
Network hosts it talks to 3
agent-plugins.org· found in codegithub.com· found in codeheartwoodmemory.com· found in code
Files it touches
/proc/self/statm/usr/lib/libSystem.dylib- Your home directory (~)
- Any path the agent passes to its tools
Tools (8)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
assess_faithfulnessEvaluate generated-memory claims against cited source spans this server's principal can read.
evaluate_egressEvaluate whether source spans may leave the deployment boundary before model use. Cited memories resolve only if this server's principal can read them.
explain_recallWhy was this recalled? Candidates considered, ranking signals, freshness.
forgetGDPR Art.17 erasure: crypto-shred the subject key + purge derived artifacts. Audit retained.
healthReadiness, warmed tenants, model names, and key-custody mode.
memoryAnthropic memory-tool-compatible ops over the /memories files this server's principal can read, backed by governed Heartwood memories. commands: view | create | str_replace | insert | delete | rename.
recallPolicy-enforced hybrid recall as this server's principal. Restricted memories never leak; results carry provenance.
rememberStore a governed memory as this server's principal (provenance-signed, policy-tagged, audited). Returns its id. Heartwood does not detect that a memory replaces an older one. When it does, pass the older ids in supersedes: they are retired in the same step and default recall stops returning them. Only memories this server's principal can read and may retire (its own, or any with a reviewer or approver role) can be superseded.
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Weekly downloads
- 92
- Last commit
- Oct 22, 2026 (9 days ago)
- Last release
- Oct 9, 2026 (22 days ago)
- Last package publish
- Oct 9, 2026 (22 days ago)
From GitHub (fetched Oct 24, 2026) and the package registry.
Details
- Registry name
io.github.jermayne36/heartwood-memory- Version
- 0.2.9
- Auth
- No auth
- Packages
- pypi heartwood-memory
- License
- BUSL-1.1
- Repository
- github.com/jermayne36/heartwood-memory
- Website
- heartwoodmemory.com/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Heartwood Memory — governed memory for AI agents running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Heartwood Memory — governed memory for AI agents MCP server. Agent Mart. https://agentmart.dev/connectors/jermayne36-heartwood-memory (last updated 2026-10-24)