Vault Agent Memory

Vault Agent Memory

[English](README.md) | [繁體中文](README.zh-Hant.md) | [简体中文](README.zh-CN.md)

Local-first memory governance for AI agents.

Vault Agent Memory gives Codex, Claude Code, Hermes, OpenClaw, n8n, Coze, and other agents one governed memory vault to share. It is not trying to be another notes app or vector database. It helps agents decide what should be remembered, who can use it, whether it is still current, and how to roll it back when it is wrong.

The Python package and existing install path remain vault-for-llm.

Vault is for people already building or working with agents. The main interface should still not be a long CLI manual: ask an agent to install Vault, answer a few setup questions, then read a short daily memory report.

New here? Start with the visual demo: [docs/landing/index.html](docs/landing/index.html).

30-Second Version

Vault Agent Memory exists because agent memory fails in practical ways:

• a new session acts like it joined the project on day one
• bug fixes stay buried in chat history
• old notes outrank newer decisions
• private observations leak into shared project memory
• teams cannot tell which memory was reviewed, trusted, or deprecated

flowchart TB
    subgraph Agents["🤖 Your Agents"]
        C[Codex]
        CL[Claude Code]
        H[Hermes]
        CO[Coze]
        N[n8n]
    end

    subgraph Vault["🔐 Vault — Governed Memory Layer"]
        direction TB
        Pipeline["Review PipelinePrivacy · Duplicates · Quality · Source"]
        Report["Daily ReportAuto-promote low-risk · Review high-risk"]
        subgraph Layers["Memory Layers"]
            L0["L0 Identity"]
            L1["L1 Rules"]
            L2["L2 Context"]
            L3["L3 Knowledge"]
        end
        Ledger["Task LedgerLive workbench · Handoffs"]
        Storage["SQLite / MarkdownLocal-first · Zero dependencies"]
    end

    subgraph Integrations["🔌 Integrations"]
        Obs[Obsidian Sync]
        Sup[Supabase]
        GW[Gateway API]
    end

    Agents -->|propose| Pipeline
    Agents -->|search / bounded read| Layers
    Agents -->|update status| Ledger
    Pipeline --> Report
    Report --> Layers
    Layers  Ledger
    Layers --> Storage
    Integrations |import / export / sync| Vault

    style Agents fill:#e1f5fe,stroke:#0288d1
    style Vault fill:#f3e5f5,stroke:#7b1fa2
    style Integrations fill:#e8f5e9,stroke:#388e3c

Why Vault?

| Without Vault | With Vault | |---------------|------------| | Each agent remembers separately, repeating the same mistakes | One shared memory vault — learn once, benefit everywhere | | Old info fights with new decisions; agents don't know what to trust | Temporal boundaries + expiry — always surface the most current truth | | Sensitive info leaks everywhere; no audit trail | Governance metadata — who sees what, track every change, rollback anytime | | Memory is just a pile of chat logs, hard to find signal | Candidate → Review → Promote — only what's useful stays |

The core workflow is:

propose -> review -> promote -> search -> bounded read -> rollback -> audit

In plain language:

> Vault is not about helping agents remember everything. It is about helping > teams govern what agents remember, trust, share, forget, and roll back.

Who Are You? Start Here 👇

| Role | What You Care About | Starting Point | |------|---------------------|----------------| | 🧑‍💻 Agent Developer | How do I plug Vault into my agent? | → [MCP Integration Guide](docs/mcpmemoryworkflow.md) | | 🤖 Power Agent User | How do I stop Claude/Codex from forgetting? | → [5-Minute Quickstart](docs/quickstart.md) · Copy the install prompt to your agent | | 👥 Team Collaboration | How do multiple agents share memory without chaos? | → [Three-Agent Shared Memory Demo](docs/demo/three-agent-shared-memory-runbook.md) | | 📝 Obsidian User | How can agents safely use my notes? | → [Obsidian Integration](#obsidian) | | 🏗️ Architect / Tech Lead | Is this reliable? What's the architecture? | → [Design Decisions](docs/decisionrecords/) · [Benchmarks](docs/searchqa_benchmarking.md) |

For Agent Builders: Ask Your Agent To Install It

Copy this prompt into an agent that can run local commands:

Install Vault Agent Memory for this project. Use vault-for-llm[mcp]==0.7.31.
Use the agent-assisted governed-auto memory mode.

Do not show advanced CLI flags first. Ask me only four questions:
1. Which language should Vault use: Traditional Chinese, Simplified Chinese, or English?
2. Should this be an independent vault or a shared vault for multiple agents?
3. Should Vault connect to Obsidian, Supabase, both, or neither?
4. What time should the daily memory report run?

After setup, run a smoke check and tell me:
- where the vault lives
- how I read the daily memory report
- where the local GUI or next action is

Daily rule:
safe, low-risk, sourced memories can be kept automatically;
uncertain, sensitive, conflicting, or strategic memories should go into the
daily report for my review.

The agent will usually run:

python3 -m venv .venv
source .venv/bin/activate
pip install "vault-for-llm[mcp]==0.7.31"
vault quickstart

You can also print the install prompt from Vault itself:

vault guide --intent install

vault quickstart is the small first-run wizard. It asks only for language, independent/shared memory, optional Obsidian/Supabase connections, and daily report time. See [docs/quickstart.md](docs/quickstart.md) for the 5-minute walkthrough and FAQ. Advanced integration flags stay under vault setup-agent.

Agent-assisted quickstart uses governed-auto by default. Internally this is still the consumer setup path, but that does not mean Vault is a zero-learning consumer app. Low-risk, sourced candidates that pass privacy, duplicate, metadata, and quality gates may enter the active vault. Strategy, private, sensitive, conflicting, or low-trust memories stay in the daily report for human review. Nothing is hard-deleted automatically.

Daily Use

The intended human surface is small:

1. Agents propose reusable lessons while they work.
2. Vault checks privacy, duplicates, quality, and source evidence.
3. Safe low-risk memories can enter the vault.
4. Uncertain decisions are summarized in a daily report.
5. The user approves, rejects, defers, or keeps both sides for conflicts.

The report should answer:

• What did Vault remember today?
• What few memory decisions need my attention?
• Are there stale, sensitive, conflicting, or low-quality memories to review?

That is the product shape: more automatic over time, but still governed.

What Vault Is Not

Vault is not an Obsidian replacement.

Obsidian is great for humans reading notes. Vault helps agents use those notes safely, with source ranges and review boundaries.

Vault is not just RAG.

RAG usually focuses on retrieving context. Vault focuses on the memory lifecycle: who wrote it, whether it was reviewed, which agents can read it, when it stops being current, and how to roll it back.

Vault is not a raw chat-history landfill.

It is candidate-first. Agents can suggest memory, but long-term memory should stay source-backed, reviewable, and clean.

Vault is not a zero-setup app-store product for people who do not use agents.

The first public audience is agent-assisted builders: people using Codex, Claude Code, Hermes, OpenClaw, n8n, Coze, or similar systems who want one governed memory layer without studying every internal command.

Killer Demo: Shared Governed Memory

Run the local demo:

vault demo agent-governance --json

It simulates Codex, Claude Code, and Hermes sharing one governed vault:

1. one agent proposes a lesson from a bug fix
2. the memory stays a candidate until reviewed
3. a reviewer promotes it with source evidence
4. another agent finds it later with search and bounded read
5. the memory can be deprecated or rolled back when it becomes outdated

The generated demo pack also includes three follow-up guides: consumer-mode-demo.md, automation-mode-demo.md, and multi-host-sync-demo.md.

Start here:

• [Agents Need Memory Governance, Not Just RAG](docs/articles/agents-need-memory-governance-not-just-rag.md)
• [Three-agent shared-memory runbook](docs/demo/three-agent-shared-memory-runbook.md)
• [Demo pack](docs/demo/agent-governance-demo-pack.md)
• [Strategy docs](docs/strategy/)

3-Minute Demo (Coming Soon)

> 🎬 A 3-minute walkthrough GIF is coming soon. > > In the meantime, here's what it will show: > > 1. Install — pip install vault-for-llm[mcp] and vault quickstart > 2. Configure — Answer 4 simple questions (language, vault type, integrations, report time) > 3. Propose — An agent suggests a memory with vault_memory_propose > 4. Review — The daily report surfaces candidates for human approval > 5. Promote & Search — Approved memory shows up in vault_search with bounded reads > > Prefer a text walkthrough? → [5-Minute Quickstart](docs/quickstart.md)

One-Click Install

macOS / Linux

curl -sSL https://raw.githubusercontent.com/zycaskevin/Vault-Agent-Memory/main/scripts/install.sh | bash

Windows (PowerShell)

irm https://raw.githubusercontent.com/zycaskevin/Vault-Agent-Memory/main/scripts/install.ps1 | iex

After the installer finishes, run vault quickstart to complete setup.

These raw GitHub URLs are available from main and install the pinned release version used by this README. If you prefer release-tagged documentation, use the next release that includes these installer scripts.

Source: [scripts/install.sh](scripts/install.sh) · [scripts/install.ps1](scripts/install.ps1)

Developer Quickstart

pip install "vault-for-llm[mcp]==0.7.31"

vault init ~/Vaults/demo
vault add "First lesson" \
  --content "The bug was caused by a missing cache key. The fix was adding provider metadata." \
  --project-dir ~/Vaults/demo
vault compile --project-dir ~/Vaults/demo --no-embed
vault search "cache key" --project-dir ~/Vaults/demo
vault --project-dir ~/Vaults/demo map build
vault --project-dir ~/Vaults/demo map read 1 --lines 1-20
vault --project-dir ~/Vaults/demo gui

vault add takes content through --content or --file. For bounded source reads, use vault map read --lines START-END.

For MCP-capable runtimes:

vault-mcp --project-dir ~/Vaults/demo --tool-profile core

Start most agents with core:

• vault_search
• vault_read_range
• vault_memory_propose
• vault_stats
• vault_update_status
• vault_automation_handoff

Use larger MCP profiles only when needed:

| Profile | Use when | |---|---| | core | Daily search, bounded reads, candidate memory, status, handoff | | review | Candidate review, capture, promotion, dream review | | remote | Reading a synced remote memory view | | maintenance | Import, freshness, convergence, scheduled curation | | full | Trusted local power-user compatibility |

Detailed MCP docs:

• [MCP tool reference](docs/mcptoolreference.md)
• [MCP memory workflow](docs/mcpmemoryworkflow.md)

Memory Model

Vault uses L0-L3 for memory depth:

| Layer | Purpose | |---|---| | L0 | identity and project framing | | L1 | stable facts, rules, preferences | | L2 | reviewed recent context and summaries | | L3 | detailed knowledge, SOPs, bugs, decisions, source notes |

Task Ledger is not L2. It is the live workbench for blockers, next actions, evidence links, due dates, and handoff notes. Only durable lessons, decisions, and summaries should be promoted into L2/L3 after review.

Access is not controlled by layer alone. Use governance metadata:

• scope: private, project, shared, public
• sensitivity: low, medium, high, restricted
• owner_agent
• allowed_agents
• memory_type
• expires_at
• valid_from / valid_until
• supersedes_id

Temporal fact windows are separate from expiry. expires_at means "move this out of normal recall later." valid_until means "this fact stopped being true, but keep it for history and audit."

vault memory temporal status
vault memory temporal list --state past
vault search "office location" --exclude-expired

More detail: [docs/memorygovernance.md](docs/memorygovernance.md).

Automation And Daily Reports

Automation is report-first by default. It can rank candidates, summarize stale memory, suggest consolidation, and prepare a short review queue without silently rewriting long-term memory.

vault daily-report --language en
vault automation brief --pretty
vault automation review-summary --write-summary
vault automation handoff

Enable stronger automation deliberately:

vault setup-agent \
  --automation-schedule cron \
  --automation-apply \
  --automation-auto-promote-low-risk

That path can promote only low-risk, sourced candidates that pass the normal gates, with a per-run cap. Private, high-sensitivity, duplicate, weak, or sourceless candidates stay in review.

Automation docs:

• [Automation](docs/automation.md)
• [Automation strategy](docs/automation_strategy.md)

Integrations

| System | Path | |---|---| | Codex / Claude Code / OpenCode | CLI or local stdio MCP | | Hermes Agent / OpenClaw | CLI, MCP, generated agent install files | | n8n | generated workflow templates and Gateway/Supabase adapters | | Coze or hosted agents | OpenAPI templates, Gateway, or Supabase read RPC | | Obsidian | import notes, export reviewed memory, conflict inbox | | Other memory tools / chat exports | candidate-first migration | | Headroom | optional compression after Vault narrows context |

Start here:

• [Agent integrations](docs/agent_integrations.md)
• [Agent-first usage](docs/agentfirstusage.md)
• [Gateway / remote contract](docs/decision_records/2026-07-02-vault-remote-gateway-contract.md)

Obsidian

Import an existing Obsidian vault:

vault import obsidian --vault ~/Documents/ObsidianVault --project-dir ~/Vaults/my-project --dry-run
vault import obsidian --vault ~/Documents/ObsidianVault --project-dir ~/Vaults/my-project --compile

Export reviewed Vault knowledge back into Obsidian-readable notes:

vault export obsidian --project-dir ~/Vaults/my-project --vault ~/Documents/ObsidianVault --dry-run --json
vault export obsidian --project-dir ~/Vaults/my-project --vault ~/Documents/ObsidianVault

The conflict inbox uses explicit resolver choices: accept Obsidian, accept Vault, or keep both.

Remote Sharing

Local SQLite remains the simplest source of truth. For remote sharing, choose the adapter that fits the deployment.

Supabase is useful when hosted agents or other machines need a filtered read copy:

pip install "vault-for-llm[supabase]==0.7.31"
vault remote status --project-dir ~/Vaults/my-project
python -m scripts.sync_to_supabase --db ~/Vaults/my-project/vault.db --document-map --health

Gateway / Remote Server is useful when many agents can reach one trusted self-hosted endpoint:

export VAULT_GATEWAY_TOKEN="choose-a-stable-secret"
vault remote-server health --project-dir ~/Vaults/my-project --json
vault remote-server openapi --project-dir ~/Vaults/my-project --json
vault remote-server serve --project-dir ~/Vaults/my-project --host 0.0.0.0

Remote contributions should enter as review candidates. This is centralized sharing, not offline multi-master sync.

For multi-agent or multi-device memory, use the Central Memory Station surface:

vault start
vault memory-sync run-once --push-read-copy --push-central-store --pull-candidates --dry-run --json
vault memory-sync run-once --central-backend self-host --pull-candidates --dry-run --json
vault memory-review inbox --json
vault memory-lifecycle status --json
vault ops security --json

The detailed remote, sync, dream, usage, and automation commands stay available as advanced tools. The central surface is the smaller operator entry for Supabase o

…

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: zycaskevin
• Source: zycaskevin/Vault-Agent-Memory
• License: Apache-2.0
• Homepage: https://zycaskevin.github.io/Vault-Agent-Memory/

Install and usage instructions live in the source repository linked above.