vault-for-llm 0.7.29

Local-first memory governance for AI agents: shared, reviewable, auditable memory via SQLite and MCP.

Vault-for-LLM

English | 繁體中文 | 简体中文

Local-first memory governance for AI agents.

Vault-for-LLM 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.

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.

30-Second Version

Vault-for-LLM 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

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.

For Agent Builders: Ask Your Agent To Install It

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

Install Vault-for-LLM for this project. Use vault-for-llm[mcp]==0.7.29.
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]==0.7.29"
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 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
• Three-agent shared-memory runbook
• Demo pack
• Strategy docs

Developer Quickstart

pip install "vault-for-llm[mcp]==0.7.29"

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 <knowledge_id> --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
• MCP memory workflow

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/memory_governance.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
• Automation strategy

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
• Agent-first usage
• Gateway / remote contract

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]==0.7.29"
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.

Docs:

• Supabase setup
• Supabase read policy
• Gateway security foundation

Memory Migration

Import memory from other tools as candidates, not as trusted active memory:

vault import memory --source ~/Downloads/chatbox-export.json --format auto --dry-run
vault import memory --source ~/Downloads/chatbox-export.json --write-candidates --only summaries,decisions,preferences

Imported items pass the same privacy, duplicate, metadata, and quality gates.

Retrieval Quality

Vault includes Search QA so retrieval can be measured instead of trusted by intuition alone.

vault search-qa run \
  --qa-file benchmarks/search_qa/basic.en.json \
  --mode keyword \
  --output /tmp/vault-searchqa.json

Current public claims should be read as retrieval evidence, not final answer quality:

• project onboarding proof runs found source-backed memory across 28/28 tasks
• LoCoMo retrieval probes showed high evidence recall with hierarchical retrieval
• official answerer/judge scores are separate and require model-provider runs

More detail:

• Agent onboarding benchmark
• Search QA benchmarking

Maturity

Area	Status
local SQLite, Markdown compile, keyword search	stable
CLI setup, candidate memory, bounded reads	usable
MCP tools	usable, profile selection recommended
agent-assisted setup and governed-auto daily loop	usable, improving
Obsidian import/export/conflict inbox	usable, sync UX still improving
Supabase sync and Gateway / Remote Server	advanced optional
semantic search, embedding providers, rerank, benchmark adapters	evolving
Profile / Dream / Forgetting agents	guidance-first, not autonomous deletion

Vault-for-LLM is pre-1.0. The core local path is intentionally conservative. Advanced remote and automation paths are powerful, but should be enabled deliberately.

Documentation Map

• Agent install runbook
• CLI reference
• Agent integrations
• Local GUI console
• Memory governance
• Automation
• MCP tool reference
• MCP workflow
• LLM integration
• OKF integration
• Vision notes

Development

Common Python path:

git clone https://github.com/zycaskevin/Vault-for-LLM.git
cd Vault-for-LLM
python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev,mcp]"
pytest -q

Reproducible Agent/developer environment:

git clone https://github.com/zycaskevin/Vault-for-LLM.git
cd Vault-for-LLM
uv sync --extra dev --extra mcp
uv run pytest -q

pip install vault-for-llm remains the public user install path. The uv workflow is for source development, CI smoke checks, and agents that need to rebuild the same local environment reliably.

Contributing

Vault is ready for small, bounded contributions from Agent-assisted builders. Start with CONTRIBUTING.md, the good first issue ideas, and the Code of Conduct. Please do not include real secrets, private chats, customer records, medical data, or production vault exports in public issues or pull requests.

License

Apache-2.0. See LICENSE.