MemoryGuard

Governed shared memory for coding agents.
Local-first MCP memory with automatic organization, scoped rules, evidence, and rollback.

中文文档

Let agents write without turning shared memory into an unreviewed pile. MemoryGuard organizes each write, preserves the evidence behind changes, and keeps governance decisions reversible.

No account. No remote server. No telemetry. Memory stays local.

Quick start · Upgrade · Knowledge Library · Architecture · Supported hosts · Privacy and safety

_{A synthetic governed projection: signals move through memory categories while raw conversation text remains outside the graph.}

What's New in v0.6.1

• Python 3.10 SQLite hotfix: Memory and Evidence stores now validate existing base schema metadata through SQLite mode=ro before any write-capable WAL connection is opened. Future or unknown schema markers therefore fail closed without changing the database image on older SQLite builds.
• Cross-version no-write verification: V2 migration tests now use genuinely read-only SQLite observation handles, avoiding test-induced WAL checkpoints on Python 3.10.
• No V2 behavior change: the v0.6.0 production cutover, frozen-source migration, native routing, readiness gates, and explicit memoryguard-v2 operator flow remain unchanged.

Why MemoryGuard

Persistent memory solves storage. It does not solve governance.

When several coding agents write into the same context, records become duplicated, stale, contradictory, over-broad, or unsafe to reuse. MemoryGuard sits between coding agents and their shared memory to keep that context usable.

System architecture

%%{init: {"theme":"base","themeVariables":{"background":"#071521","fontFamily":"Arial, sans-serif","fontSize":"14px","primaryTextColor":"#EEF4F8","lineColor":"#557287","edgeLabelBackground":"#071521","clusterBkg":"#0A1A29","clusterBorder":"#27445A"},"flowchart":{"htmlLabels":true,"curve":"basis","nodeSpacing":32,"rankSpacing":48,"padding":14}}}%%
flowchart TB
    Hosts["CODING-AGENT HOSTS<br/>Claude Code · Codex · Cursor · TRAE&nbsp;&nbsp;&nbsp;&nbsp;"]:::host
    Gateway["LOCAL INTEGRATION<br/>MCP stdio · redirect rules · lifecycle hooks&nbsp;&nbsp;&nbsp;&nbsp;"]:::gateway

    subgraph Core["GOVERNANCE CORE&nbsp;&nbsp;&nbsp;&nbsp;"]
        direction LR
        Identity["TRUST<br/>identity · scope&nbsp;&nbsp;&nbsp;&nbsp;"]:::core
        MemoryAPI["MEMORY<br/>governed I/O&nbsp;&nbsp;&nbsp;&nbsp;"]:::active
        Rules["RULES<br/>scope · assignment&nbsp;&nbsp;&nbsp;&nbsp;"]:::rule
        HistoryAPI["HISTORY<br/>search · timeline&nbsp;&nbsp;&nbsp;&nbsp;"]:::history
        Security["SAFETY<br/>validate · quarantine&nbsp;&nbsp;&nbsp;&nbsp;"]:::danger

        Identity --> MemoryAPI
        Identity --> Rules
        Identity --> HistoryAPI
        MemoryAPI --> Security
    end

    subgraph Stores["LOCAL GOVERNED STORES&nbsp;&nbsp;&nbsp;&nbsp;"]
        direction LR
        SharedDB[("V2 DOMAIN STORES<br/>Memory · Rules · Evidence · Content&nbsp;&nbsp;&nbsp;&nbsp;")]:::store
        HistoryDB[("HISTORY STORE<br/>isolated conversations&nbsp;&nbsp;&nbsp;&nbsp;")]:::historyStore
        AuditDB[("RECOVERY STORE<br/>versions · receipts · backups&nbsp;&nbsp;&nbsp;&nbsp;")]:::store
    end

    Bootstrap["BOUNDED CONTEXT BOOTSTRAP<br/>mandatory rule pack · relevant recall&nbsp;&nbsp;&nbsp;&nbsp;"]:::bootstrap
    Control["HUMAN CONTROL<br/>CLI · desktop governance console&nbsp;&nbsp;&nbsp;&nbsp;"]:::surface

    Hosts --> Gateway --> Identity
    MemoryAPI --> SharedDB
    Rules --> SharedDB
    HistoryAPI --> HistoryDB
    Security --> AuditDB
    SharedDB --> Bootstrap
    Control --> Identity

    classDef host fill:#12243A,stroke:#38D5C8,color:#EEF4F8,stroke-width:1.4px;
    classDef gateway fill:#0D3338,stroke:#38D5C8,color:#EEF4F8,stroke-width:2.4px;
    classDef core fill:#12243A,stroke:#557287,color:#EEF4F8,stroke-width:1.4px;
    classDef active fill:#0D383A,stroke:#38D5C8,color:#EEF4F8,stroke-width:2px;
    classDef rule fill:#3B2C18,stroke:#F3B562,color:#EEF4F8,stroke-width:1.8px;
    classDef history fill:#102F45,stroke:#73C7F5,color:#EEF4F8,stroke-width:1.8px;
    classDef danger fill:#3A2028,stroke:#EA6A6A,color:#EEF4F8,stroke-width:1.8px;
    classDef bootstrap fill:#EEF4F8,stroke:#38D5C8,color:#071521,stroke-width:2.4px;
    classDef store fill:#0B1624,stroke:#7F96A8,color:#EEF4F8,stroke-width:1.4px;
    classDef historyStore fill:#102436,stroke:#73C7F5,color:#EEF4F8,stroke-width:1.4px;
    classDef surface fill:#EEF4F8,stroke:#38D5C8,color:#071521,stroke-width:2px;

    style Core fill:#081827,stroke:#27445A,stroke-width:1px,color:#EEF4F8
    style Stores fill:#081827,stroke:#27445A,stroke-width:1px,color:#EEF4F8
    linkStyle default stroke:#557287,stroke-width:1.4px;

Quick start

1. Install

python -m pip install agent-memguard

For the desktop governance console:

python -m pip install "agent-memguard[gui]"

2. Authorize the current project

memoryguard source add .

3. Connect or repair your coding agent

Global provider configuration is rebuilt from the real binding in the canonical user data home. The command is idempotent and removes superseded MemoryGuard project-level overrides after a successful global takeover.

# Repair one provider
memoryguard provider repair claude
memoryguard provider repair codex
memoryguard provider repair cursor
memoryguard provider repair trae

# Repair every detected provider
memoryguard provider repair all

Restart the host after installation, then verify the integration:

memoryguard doctor
memoryguard mcp-status
memoryguard hooks status --provider all

Launch the desktop console:

memoryguard gui

memoryguard-gui . remains available for desktop shortcuts. In PowerShell and other terminals, use memoryguard gui . so startup errors remain visible. With no path, MemoryGuard uses MEMORYGUARD_WORKSPACE or the fixed user-level control directory (MEMORYGUARD_HOME, defaulting to %LOCALAPPDATA%\MemoryGuard on Windows). It no longer remembers a previously selected project, infers a workspace from the launch directory, or opens a folder picker. On Windows, memoryguard gui detaches the native window from the terminal, so closing PowerShell does not close the GUI.

Provider-specific setup and behavior:

• Claude Code installation
• Codex installation
• Cursor installation

Upgrade

MemoryGuard currently upgrades through Python's package manager:

python -m pip install --upgrade agent-memguard
memoryguard --version
memoryguard doctor

If you installed the GUI extra, keep it during the upgrade:

python -m pip install --upgrade "agent-memguard[gui]"

There is no separate memoryguard update self-update command yet. The package manager is the authoritative package-upgrade path.

Existing v0.5.x workspaces: explicit V2 cutover

v0.6.0 never auto-activates an existing workspace. Upgrade the package first, then use the packaged operator CLI:

# Read-only manifest status
memoryguard-v2 status -w .

# Build a frozen-source V2 shadow and stop at V2_READY
memoryguard-v2 prepare -w . --apply

# Activate only after the prepare result is V2_READY / ready=true
memoryguard-v2 activate -w . --confirm V2_ACTIVE

The prepare step uses coherent SQLite online backups, preserves V1 and migration-backups, and rechecks live-source drift before READY. Activation performs another fresh drift check before changing the manifest. Do not delete legacy V1 data or migration backups as part of the upgrade.

Knowledge Library

The desktop console can turn a selected folder into one governed local knowledge library. Source files remain where they are; MemoryGuard stores the searchable index in its user data home instead of copying a runtime database into every source project.

Open the desktop console and choose Knowledge Library. Remote embedding or model-backed indexing is opt-in and requires explicit authorization; local full-text retrieval remains available without sending source text to a remote provider.

Write and governance lifecycle

%%{init: {"theme":"base","themeVariables":{"background":"#071521","fontFamily":"Arial, sans-serif","fontSize":"14px","primaryTextColor":"#EEF4F8","lineColor":"#557287","edgeLabelBackground":"#071521","clusterBkg":"#0A1A29","clusterBorder":"#27445A"},"flowchart":{"htmlLabels":true,"curve":"basis","nodeSpacing":30,"rankSpacing":42,"padding":14}}}%%
flowchart TD
    subgraph Intake["01 · INTAKE    "]
        direction LR
        Write(["Memory write    "]):::entry
        Scope["Resolve identity<br/>scope · audience&nbsp;&nbsp;&nbsp;&nbsp;"]:::core
        Validate{"Authorized?&nbsp;&nbsp;&nbsp;&nbsp;"}:::decision
        Reject["Reject<br/>no persistence&nbsp;&nbsp;&nbsp;&nbsp;"]:::danger
        Write --> Scope --> Validate
        Validate -- NO --> Reject
    end

    subgraph Organize["02 · ORGANIZE&nbsp;&nbsp;&nbsp;&nbsp;"]
        direction TB
        Secret{"Sensitive?&nbsp;&nbsp;&nbsp;&nbsp;"}:::decision
        Quarantine["Quarantine<br/>outside active set&nbsp;&nbsp;&nbsp;&nbsp;"]:::danger
        Compare["Classify · compare<br/>governed records&nbsp;&nbsp;&nbsp;&nbsp;"]:::active
        Relation{"Relationship&nbsp;&nbsp;&nbsp;&nbsp;"}:::decision
        New["NEW<br/>create active record&nbsp;&nbsp;&nbsp;&nbsp;"]:::result
        Duplicate["DUPLICATE<br/>merge provenance&nbsp;&nbsp;&nbsp;&nbsp;"]:::result
        Correction["CORRECTION<br/>supersede old record&nbsp;&nbsp;&nbsp;&nbsp;"]:::rule
        Conflict["CONFLICT<br/>preserve both sides&nbsp;&nbsp;&nbsp;&nbsp;"]:::danger

        Secret -- YES --> Quarantine
        Secret -- NO --> Compare --> Relation
        Relation --> New
        Relation --> Duplicate
        Relation --> Correction
        Relation --> Conflict
    end

    subgraph Govern["03 · GOVERN&nbsp;&nbsp;&nbsp;&nbsp;"]
        direction LR
        Receipt[("Evidence event<br/>version receipt&nbsp;&nbsp;&nbsp;&nbsp;")]:::store
        Review["CLI or desktop review&nbsp;&nbsp;&nbsp;&nbsp;"]:::surface
        Action["Correct · merge<br/>restore · delete&nbsp;&nbsp;&nbsp;&nbsp;"]:::rule
        Snapshot["Reversible<br/>snapshot&nbsp;&nbsp;&nbsp;&nbsp;"]:::active
        Receipt --> Review --> Action --> Snapshot
    end

    Validate -- YES --> Secret
    Quarantine --> Receipt
    New --> Receipt
    Duplicate --> Receipt
    Correction --> Receipt
    Conflict --> Receipt

    classDef entry fill:#EEF4F8,stroke:#38D5C8,color:#071521,stroke-width:2.4px;
    classDef core fill:#12243A,stroke:#557287,color:#EEF4F8,stroke-width:1.5px;
    classDef decision fill:#0D3338,stroke:#38D5C8,color:#EEF4F8,stroke-width:2px;
    classDef active fill:#0D383A,stroke:#38D5C8,color:#EEF4F8,stroke-width:2px;
    classDef result fill:#12243A,stroke:#38D5C8,color:#EEF4F8,stroke-width:1.6px;
    classDef rule fill:#3B2C18,stroke:#F3B562,color:#EEF4F8,stroke-width:1.8px;
    classDef danger fill:#3A2028,stroke:#EA6A6A,color:#EEF4F8,stroke-width:1.8px;
    classDef store fill:#0B1624,stroke:#7F96A8,color:#EEF4F8,stroke-width:1.4px;
    classDef surface fill:#EEF4F8,stroke:#38D5C8,color:#071521,stroke-width:2px;

    style Intake fill:#081827,stroke:#27445A,stroke-width:1px,color:#EEF4F8
    style Organize fill:#081827,stroke:#27445A,stroke-width:1px,color:#EEF4F8
    style Govern fill:#081827,stroke:#27445A,stroke-width:1px,color:#EEF4F8
    linkStyle default stroke:#557287,stroke-width:1.4px;

The console is not an approval queue. Agents keep moving. MemoryGuard records the outcome and exposes the evidence needed to correct it later.

What you can govern

Rules and history stay separate

MemoryGuard deliberately keeps governed long-term memory and raw conversation history on different paths.

History retrieval is progressive: search results, then a bounded timeline, then an explicitly selected turn or session. Extracting from history creates a preview first; it does not silently write a long-term memory.

%%{init: {"theme":"base","themeVariables":{"background":"#071521","fontFamily":"Arial, sans-serif","fontSize":"14px","primaryTextColor":"#EEF4F8","lineColor":"#557287","edgeLabelBackground":"#071521","clusterBkg":"#0A1A29","clusterBorder":"#27445A"},"flowchart":{"htmlLabels":true,"curve":"basis","nodeSpacing":30,"rankSpacing":42,"padding":14}}}%%
flowchart LR
    subgraph HistoryPath["CONVERSATION EVIDENCE    "]
        direction TB
        Archive[("Raw local history    ")]:::historyStore
        Search["Search summaries    "]:::history
        Timeline["Bounded timeline    "]:::history
        Read["Explicit turn or session    "]:::history
        Preview["Evidence-backed<br/>extraction preview&nbsp;&nbsp;&nbsp;&nbsp;"]:::history
        Confirm["Explicit acceptance&nbsp;&nbsp;&nbsp;&nbsp;"]:::surface
        Isolation["NO AUTOMATIC<br/>BOOTSTRAP PATH&nbsp;&nbsp;&nbsp;&nbsp;"]:::barrier

        Archive --> Search --> Timeline --> Read --> Preview --> Confirm
        Archive -.-> Isolation
    end

    subgraph GovernedMemory["GOVERNED LONG-TERM MEMORY&nbsp;&nbsp;&nbsp;&nbsp;"]
        direction TB
        Mandatory["Scoped mandatory rules&nbsp;&nbsp;&nbsp;&nbsp;"]:::rule
        Assignments["Agent · project<br/>role · group scope&nbsp;&nbsp;&nbsp;&nbsp;"]:::core
        RulePack["Mandatory-rule<br/>budget&nbsp;&nbsp;&nbsp;&nbsp;"]:::budget
        Ordinary["Facts · preferences<br/>projects · procedures&nbsp;&nbsp;&nbsp;&nbsp;"]:::memory
        Recall["Task-relevant<br/>recall budget&nbsp;&nbsp;&nbsp;&nbsp;"]:::budget
        Context["BOUNDED CONTEXT PACKET&nbsp;&nbsp;&nbsp;&nbsp;"]:::context

        Mandatory --> Assignments --> RulePack --> Context
        Ordinary --> Recall --> Context
    end

    HistoryPath ==>|GOVERNED WRITE&nbsp;&nbsp;&nbsp;&nbsp;| GovernedMemory

    classDef rule fill:#3B2C18,stroke:#F3B562,color:#EEF4F8,stroke-width:1.8px;
    classDef core fill:#12243A,stroke:#557287,color:#EEF4F8,stroke-width:1.4px;
    classDef memory fill:#0D383A,stroke:#38D5C8,color:#EEF4F8,stroke-width:1.8px;
    classDef budget fill:#12243A,stroke:#38D5C8,color:#EEF4F8,stroke-width:1.6px;
    classDef context fill:#EEF4F8,stroke:#38D5C8,color:#071521,stroke-width:2.4px;
    classDef history fill:#102F45,stroke:#73C7F5,color:#EEF4F8,stroke-width:1.6px;
    classDef historyStore fill:#102436,stroke:#73C7F5,color:#EEF4F8,stroke-width:1.6px;
    classDef surface fill:#EEF4F8,stroke:#73C7F5,color:#071521,stroke-width:2px;
    classDef barrier fill:#3A2028,stroke:#EA6A6A,color:#EEF4F8,stroke-width:2px;

    style GovernedMemory fill:#081827,stroke:#27445A,stroke-width:1px,color:#EEF4F8
    style HistoryPath fill:#081827,stroke:#27445A,stroke-width:1px,color:#EEF4F8
    linkStyle default stroke:#557287,stroke-width:1.4px;

Supported hosts

Provider status is reported honestly as redirected, observed, operational, or unsupported. MemoryGuard does not claim it can disable every host's native memory when the host exposes no reliable integration point.

Architecture

V2 uses separate authoritative SQLite domains rather than one shared-memory database. The runtime reads and writes V2 only after the manifest reaches V2_ACTIVE; V2_BUILDING and V2_READY never silently fall back or dual-write. Evidence remains traceable without being treated as automatically trusted memory.

Privacy and safety

• MemoryGuard runs as a local MCP stdio server.
• All governed data stays local unless you explicitly authorize a remote model or embedding operation.
• The Knowledge Library database uses MEMORYGUARD_HOME or the platform user data directory, so a selected source folder does not receive its own knowledge database.
• V2 authoritative workspace state is separated under .memoryguard/ into explicit Memory, Rules, Evidence, Content, Runtime, Projection, Assets, CodeGraph, Skills, and System domains. Legacy V1 artifacts are preserved as local rollback/audit evidence after cutover and are no longer the active V2 runtime write path.
• Source scanning is read-only by default.
• Mutating governance paths use validation, explicit scope, provenance, and reversible state.
• Quarantined records stay outside active shared memory.
• Raw conversation history is never injected into bootstrap automatically.
• Shared-group history access follows current active membership and does not grant deletion rights over another Agent's source.

CLI

The installed memoryguard command exposes these top-level operations:

The old V1 plan, apply, verify, undo, import, and gc workflows remain parseable for compatibility but are explicitly retired under V2_ACTIVE; they return a stable retired result instead of writing through a legacy store.

Run memoryguard --help or memoryguard <command> --help for the live command reference.

MCP API

The MCP server exposes tools for:

• governed memory read, search, write, update, delete, and status;
• bounded context bootstrap with mandatory-rule isolation;
• rule creation, feedback, merge governance, undo, and scope statistics;
• Agent binding and shared-group inspection;
• source scanning, graph projection, import previews, and build planning;
• external MCP discovery and import;
• document extraction previews and candidate acceptance;
• conversation-history search, timeline, explicit read, export, deletion, and extraction preview;
• provider installation and host-agent enrichment.

Use MCP tools/list as the source of truth for the exact tool set supported by the installed version.

Project links

• PyPI package
• GitHub releases
• Changelog
• Memory continuity and lossless storage spec
• Contributing guide
• Contributor License Agreement
• Issue tracker

Roadmap

• Current: production-active V2 data plane, frozen-source migration and cutover, native MCP/CLI/GUI/Hook routing, scoped Memory/Rules, Content/Evidence, conversation archives, provider adapters, Reference Audit, maintenance, and governance UI.
• Next: richer scenario/profile projections, broader CodeGraph/Skills ingestion, more operator-friendly maintenance reports, and additional migration observability. Long-term records are not retired merely because they are old.
• Later: team and enterprise capabilities only after validated demand.

Contributing

Issues and pull requests are welcome. Read CONTRIBUTING.md before submitting a change. Pull requests require agreement to the CLA.

License

MIT