mnemonic

A local MCP memory server backed by plain markdown files, synced via git. No database. Project-scoped memory with semantic search.

For the high-level system map, see ARCHITECTURE.md. For release notes, see CHANGELOG.md.

Why mnemonic

• 🧠 Your MCP client remembers decisions, fixes, and context across sessions — no re-explaining the same project.
• 📁 Memories are plain markdown with YAML frontmatter: readable, diffable, mergeable, and easy to back up.
• 🚫 No database or always-on service: just files, git, and a local Node process.
• 🎯 Project-scoped recall surfaces the right repo context first while keeping global memories accessible.
• 🤝 Shared .mnemonic/ notes travel with the repository, so project knowledge isn't trapped in one person's chat history.
• 🔒 Embeddings stay local and gitignored — semantic search without committing generated vector data.
• 📝 Every remember, update, and consolidate creates a semantic git commit — decision log and plans travel with the code in the same history.
• 🔓 Designed for removability — though we're quietly confident you won't use that exit. Every note is plain markdown with YAML frontmatter; the knowledge you gather is independent of mnemonic and always yours.

Stability

The storage format is stable with migration support for any future changes. Keep an eye on the changelog; list_migrations shows pending work per vault after each update.

Scale: Designed for simplicity and portability — not large-scale knowledge bases.

• Hundreds to low thousands of notes: excellent fit.
• Several thousand: often fine, depending on note size, machine speed, and embedding throughput.
• Within a session, notes and embeddings are cached after first access — repeated recall, get, and project_memory_summary calls skip storage reads regardless of vault size.
• Very large collections: expect pain points around reindex time, recall latency, and git churn.
• Many concurrent writers or massive scale: consider a dedicated database and indexing layer instead.

Prerequisites

By default, mnemonic uses Ollama locally. Start Ollama and pull an embedding model:

ollama pull nomic-embed-text-v2-moe

qwen3-embedding:0.6b is an alternative with a larger context window for longer notes:

ollama pull qwen3-embedding:0.6b

No code changes required — set EMBED_MODEL=qwen3-embedding:0.6b in your environment or MCP config.

Advanced users can use OpenAI-compatible endpoints, native OpenAI, or Gemini instead. Provider settings are environment-only; mnemonic never writes API keys to notes, embedding files, vault config, or git.

Setup

Native (Node.js 20+)

npm install
npm run build
npm test

# release-confidence gate (build + full tests + isolated dogfooding)
npm run verify:release

The gate fails on required dogfood checks and reports advisory findings separately in the dogfood output.

npm run build already runs typecheck, but running it explicitly first gives a faster failure loop when iterating on the codebase.

For local dogfooding, start the built MCP server with:

npm run mcp:local

This rebuilds first, then launches build/index.js, so MCP clients always point at the latest source.

For reproducible dogfooding of recency and relationship-navigation behavior, prefer the isolated dogfood runner over the live project vault. The isolated runner copies the current .mnemonic notes into a temporary workspace, runs the chosen pack there, and deletes the workspace afterward.

Docker

docker compose build
docker compose up ollama-init  # pulls nomic-embed-text-v2-moe into the ollama volume (one-time)

Ollama runs as a container with a named volume (ollama-data) so downloaded models persist across restarts. The vault directory (~/mnemonic-vault by default) is bind-mounted from the host. Git credentials (~/.gitconfig and ~/.ssh) are mounted read-only so push/pull work inside the container.

Override the vault location:

VAULT_PATH=/path/to/your-vault docker compose run --rm mnemonic

Installing

npm

Published to the public npm registry. No authentication required.

# Latest stable release
npm install @danielmarbach/mnemonic-mcp

# Specific release
npm install @danielmarbach/mnemonic-mcp@0.2.0

Install bundled skills (Claude/OpenCode)

The npm package now includes skills/** plus a helper binary to install them into local skill directories.

# If mnemonic is installed in this project:
npx mnemonic-install-skills --target all --mode copy

# One-off install without adding dependency:
npx -y -p @danielmarbach/mnemonic-mcp mnemonic-install-skills --target all --mode copy

Supported targets:

• --target claude -> ~/.claude/skills
• --target opencode -> ~/.config/opencode/skills
• --target all -> both (default)
• --target custom -> only use --target-dir destinations
• --target-dir <path> -> add any custom client skill directory

Update flow after upgrading @danielmarbach/mnemonic-mcp:

npx mnemonic-install-skills --target all --mode copy --update

If you prefer automatic propagation without copy refreshes, use symlink mode:

npx mnemonic-install-skills --target all --mode symlink --update

After install, load and use the skill by name:

• Skill name: mnemonic-rpi-workflow
• Prompt counterpart: mnemonic-rpi-workflow

In clients that support explicit skill loading (for example Claude Code or OpenCode), load mnemonic-rpi-workflow before running multi-step RPIR workflows.

Homebrew

The formula lives in this repository. Tap it with an explicit URL so no separate repository is needed:

brew tap danielmarbach/mnemonic-mcp https://github.com/danielmarbach/mnemonic
brew install mnemonic-mcp

Or in a single step (direct formula URL):

brew install --formula https://raw.githubusercontent.com/danielmarbach/mnemonic/main/Formula/mnemonic-mcp.rb

Docker Hub

Pre-built images for linux/amd64 and linux/arm64:

docker pull danielmarbach/mnemonic-mcp:latest

# Or a specific version
docker pull danielmarbach/mnemonic-mcp:0.5.0

MCP client config

Claude Desktop / Cursor (native)

{
  "mcpServers": {
    "mnemonic": {
      "command": "npx",
      "args": ["@danielmarbach/mnemonic-mcp"],
      "env": {
        "VAULT_PATH": "/Users/you/mnemonic-vault"
      }
    }
  }
}

For a fixed installed version, point at the local binary instead:

{
  "mcpServers": {
    "mnemonic": {
      "command": "/path/to/your/project/node_modules/.bin/mnemonic",
      "env": {
        "VAULT_PATH": "/Users/you/mnemonic-vault"
      }
    }
  }
}

Claude Desktop / Cursor (Homebrew)

{
  "mcpServers": {
    "mnemonic": {
      "command": "mnemonic",
      "env": {
        "VAULT_PATH": "/Users/you/mnemonic-vault"
      }
    }
  }
}

Claude Desktop / Cursor (Docker)

{
  "mcpServers": {
    "mnemonic": {
      "command": "docker",
      "args": ["compose", "-f", "/path/to/mnemonic/compose.yaml", "run", "--rm", "mnemonic"],
      "env": {
        "VAULT_PATH": "/Users/you/mnemonic-vault"
      }
    }
  }
}

Ollama must be running before the MCP client invokes mnemonic. Start it once with docker compose up ollama -d and it will stay up between calls.

OpenCode

Add to ~/.config/opencode/opencode.json (global) or opencode.json in your project root:

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mnemonic": {
      "type": "local",
      "command": ["npx", "@danielmarbach/mnemonic-mcp"],
      "environment": {
        "VAULT_PATH": "/Users/you/mnemonic-vault"
      }
    }
  }
}

Codex

Add to ~/.codex/config.toml (global) or .codex/config.toml in a trusted project:

[mcp_servers.mnemonic]
command = "npx"
args = ["@danielmarbach/mnemonic-mcp"]

[mcp_servers.mnemonic.env]
VAULT_PATH = "/Users/you/mnemonic-vault"

For local development against this repository's source tree, use npm run mcp:local or point your MCP client at scripts/mcp-local.sh.

Configuration

Provider configuration is read from the process environment at startup. Only non-secret compatibility metadata is stored in local gitignored embedding JSON files: provider, model, dimensions, metric, optional input mode, and compatibility key.

After changing EMBED_PROVIDER, EMBED_MODEL, EMBED_DIMENSIONS, or endpoint semantics behind the same model alias, call the sync MCP tool with { "force": true } to rebuild local embeddings. Until rebuilt, incompatible embeddings are skipped rather than compared across vector spaces, so semantic recall may return fewer results.

Privacy note: Ollama keeps projection text local. OpenAI-compatible cloud proxies, native OpenAI, and Gemini send the note projection text used for embeddings to the configured external endpoint.

config.json

The main vault's ~/mnemonic-vault/config.json holds machine-local settings that survive across sessions. You can edit it by hand — unknown fields are ignored and invalid values fall back to defaults.

User-tunable fields:

projectMemoryPolicies and projectIdentityOverrides are written automatically by set_project_memory_policy and set_project_identity — no need to edit them by hand. Project memory policies can include protected-branch settings (protectedBranchBehavior, protectedBranchPatterns) used by mutating tools when they commit to project vaults (remember, update, forget, move_memory, and mutating consolidate strategies).

Example — raise concurrency on a fast machine and disable auto-push everywhere:

{
  "reindexEmbedConcurrency": 8,
  "mutationPushMode": "none"
}

How it works

Vault layout

Two vault types store notes:

Main vault — private global memories at ~/mnemonic-vault (its own git repo):

~/mnemonic-vault/
  .gitignore             ← auto-created, gitignores embeddings/ and projections/
  notes/
    setup-notes-a1b2c3.md
  embeddings/            ← local only, never committed
    setup-notes-a1b2c3.json
  projections/           ← local only, never committed
    setup-notes-a1b2c3.json

Project vault — project-specific memories committed into the project repo:

<git-root>/
  .mnemonic/
    .gitignore           ← auto-created, gitignores embeddings/ and projections/
    notes/
      auth-bug-fix-d4e5f6.md
    embeddings/          ← local only, never committed
      auth-bug-fix-d4e5f6.json
    projections/        ← local only, never committed
      auth-bug-fix-d4e5f6.json

Routing

cwd sets project context; scope picks storage:

• cwd + scope: "project" (default when cwd is present) → project vault (.mnemonic/)
• cwd + scope: "global" → main vault, with project association in frontmatter
• no cwd → main vault as a plain global memory

Use set_project_memory_policy to save per-project defaults:

• write scope (project, global, ask)
• consolidation mode (supersedes, delete)
• protected-branch behavior for project-vault writes (ask, block, allow)
• protected-branch patterns (glob strings; defaults are main, master, release*)

When write scope policy is ask, remember returns a clear storage choice instead of guessing. When protected-branch behavior is ask, mutating tools that would commit to the project vault return a one-time override option (allowProtectedBranch: true) plus instructions to persist block/allow.

Project identity

Project identity derives from the git remote URL, normalized to a stable slug (e.g. github-com-acme-myapp). The same project is recognized consistently across machines regardless of local clone paths. The default remote is origin; use set_project_identity to switch to upstream for fork workflows. If no remote exists, the git root folder name is used; if not in a git repo, the directory name.

Recall

recall with cwd searches both vaults. Project notes get a small tiebreaker boost — a soft signal, not a hard filter — so global memories remain accessible while project context floats to the top.

Every result carries structured quality signals to help agents decide what to trust:

• signalStrength — a composite score (0.00-0.50) from role, graph centrality, lifecycle, and recency. Higher values mean more structural support behind the note.
• confidence — high/medium/low tier derived from signalStrength, replacing a single coarse heuristic.
• diversity — theme count, role mix, and lifecycle mix across selected results.
• retrievalCoverage — fraction of high-priority anchors (alwaysLoad and summary notes) represented in results.

Hybrid recall enhances semantic search with lightweight lexical reranking over note projections. When semantic results are weak, a bounded lexical rescue path scans projections for additional candidates, improving exact-match and identifier-heavy recall without changing the storage model or adding new infrastructure. Canonical explanation promotion boosts notes that explain key decisions and concepts for "why"-style questions, using structural signals like role, connections, and format rather than keyword matching. Temporal recency: when a query suggests temporal intent, newer notes receive an additive ranking nudge in default mode.

Recall modes:

• mode: "default" (default): semantic recall with optional lexical reranking and bounded relationship previews.
• mode: "temporal": enrich top matches with compact git-backed history (no raw diffs by default).
• mode: "workflow": prioritize RPIR-style chain reconstruction while remaining compatible with legacy related-to links.

Recall evidence:

• evidence: "compact" (optional recall): add compact retrieval rationale per result in text and structured output.
• retrievalEvidence includes stable abstractions such as channels, rankBand, projectRelevant, freshness, and optional supersession hints (supersededBy, supersededCount).
• Recall evidence defaults off; consolidate evidence defaults true for safety.

What temporal mode shows:

• Per-change descriptions (changeDescription): human-readable summaries like "Expanded the note with additional detail" or "Minor refinement to existing content."
• Note-level history summaries (historySummary): overall patterns like "The core decision remained stable while rationale and examples expanded." or "The note was connected to related work through incremental updates."
• Semantic change categories: create, refine, expand, clarify, connect, restructure, reverse, unknown

How it works:

mnemonic interprets change semantically using structural and statistical signals (size ratios, heading changes, section movements) rather than language-dependent analysis. Raw diffs are intentionally NOT part of default temporal output—you get interpretive summaries that explain what kind of change happened, not patch noise.

Use verbose: true together with temporal mode when you want richer change stats such as additions, deletions, files changed, and change classification. Those stats describe the whole commit that touched the note, not a raw diff excerpt, so recall stays bounded and does not return full diffs.

The scope parameter on recall narrows results:

• "all" (default) — project memories boosted, then global
• "project" — only memories for the detected project
• "global" — only memories with no project association

Note lifecycle

Each note carries a lifecycle:

• "permanent" (default) — durable knowledge for future sessions
• "temporary" — working-state scaffolding (plans, WIP checkpoints) that can be cleaned up once consolidated

Store what should help future work: decisions, outcomes, corrections, constraints, and lessons learned. Leave routine chatter out. Cleanup stays explicit through lifecycle and consolidation choices; mnemonic does not auto-expire notes.

Roles and lifecycle

Roles are optional prioritization hints, not required schema. mnemonic infers a role and importance from structural signals (heading count, bullet density, inbound references, relationship types) — inference is language-independent and never overwrites explicit frontmatter. Valid roles: summary, decision, plan, context, reference, research, review. Valid importance values: high, normal, low.

Set alwaysLoad: true in a note's frontmatter to mark it as an explicit session anchor; it receives the highest recall and relationship-expansion priority regardless of inferred role.

mnemonic works without roles. Inferred roles stay internal-only, prioritization is language-independent by default, and lifecycle remains the separate durability axis. When lifecycle is omitted, remember applies soft defaults based on role: research, plan, and review default to temporary; decision, summary, and reference default to permanent. Explicit lifecycle always overrides the role-based default.

RPIR workflow conventions

For structured workflows, use the RPIR stages: research -> plan -> implement -> review (iterate only when needed).

• Create one request root note per workflow: role: context, lifecycle: temporary, tags: ["workflow", "request"].
• Keep one current plan note per request (role: plan) and update or supersede as the plan evolves.
• For apply/task notes, do not add a new role: use role: plan for executable steps and role: context for execution observations; tag both with apply.
• Keep relationships sparse and immediate-upstream only: research -> request, plan -> request/research, apply -> plan, review -> apply/plan, outcome -> plan (optionally request).
• Consolidate at workflow end: keep the durable outcome, preserve details that still matter, and explicitly remove temporary scaffolding when safe.

Note format

Notes are standard markdown with YAML frontmatter:

---
title: Auth bug fix approach
tags: [auth, bugfix]
project: github-com-acme-myapp
projectName: myapp
createdAt: 2026-03-07T10:00:00.000Z
updatedAt: 2026-03-07T10:00:00.000Z
---

We fixed the JWT expiry issue by switching to RS256 and...

Content is markdown-linted on remember/update: fixable issues are auto-corrected before save; non-fixable issues are rejected.

Embeddings and projections

Embeddings are generated through the configured provider (ollama, openai-compatible, openai, or gemini), stored as local JSON alongside notes, and gitignored. The sync MCP tool backfills missing or stale embeddings on every run; call it with { "force": true } to rebuild all embeddings after provider/model/dimension changes.

Embedding records include non-secret compatibility metadata so mnemonic can avoid comparing vectors from incompatible embedding spaces. Provider configuration itself remains environment-only.

Projections improve embedding quality by extracting structured representations instead of embedding raw markdown. Each note has a projection stored in projections/<noteId>.json (also gitignored) containing:

• projectionText: compact embedding input (max 1200 chars) with title, lifecycle, tags, summary, and h1–h3 headings
• summary: extracted from the first non-heading paragraph, first bullet list, or first 200 chars of body
• headings: up to 8 deduplicated h1–h3 headings (plain text, in order)
• updatedAt: staleness anchor matching the note's updatedAt timestamp

Projections are built lazily on first embed and rebuilt when note.updatedAt !== projection.updatedAt. No global rebuild needed — staleness is timestamp-based. If projection generation fails, the system falls back to raw title + content so embeds never block.

Migrations

Each vault has its own config.json with a schemaVersion, so main and project vaults migrate independently:

• list_migrations reports schema version and pending migrations per vault.
• Startup warns when a vault is behind schema, but does not auto-migrate.
• execute_migration supports dry-run to preview changes before applying.
• Failed migration runs roll staged note writes back instead of leaving partial edits.
• Metadata-only migrations do not re-embed automatically; re-embedding happens on title/content change or during sync backfill.

The main vault config.json also controls mutation push behavior:

• mutationPushMode: "main-only" (default) - auto-push main-vault mutations, but leave project-vault commits local until the user pushes or runs sync
• mutationPushMode: "all" - auto-push mutating writes in both vault types
• mutationPushMode: "none" - never auto-push mutating writes; use sync or manual git commands instead

This keeps unpublished project branches from failing on remember/update, while still letting the main vault stay in sync by default.

CLI commands

mnemonic ships CLI commands in addition to the MCP server.

mnemonic migrate

Apply pending schema migrations to your vaults. Always preview with --dry-run first.

# Preview what would change
mnemonic migrate --dry-run

# Apply and auto-commit
mnemonic migrate

# Limit to one project vault
mnemonic migrate --dry-run --cwd=/path/to/project
mnemonic migrate --cwd=/path/to/project

# List available migrations and pending count
mnemonic migrate --list

mnemonic import-claude-memory

Import Claude Code auto-memory into your vault. Claude Code stores per-project auto-memory at ~/.claude/projects/<encoded-path>/memory/*.md. Each ## heading becomes a separate mnemonic note tagged with claude-memory and imported. Notes whose titles already exist in the vault are skipped, so the command is safe to re-run.

# Preview what would be imported
mnemonic import-claude-memory --dry-run

# Import from the current directory's Claude memory
mnemonic import-claude-memory

# Import for a specific project path
mnemonic import-claude-memory --cwd=/path/to/project

# Use a non-default Claude home
mnemonic import-claude-memory --claude-home=/custom/.claude

Imported notes are written to the main vault with lifecycle: permanent and scope: global. After importing, ask your MCP client to run the sync tool to embed them and push to your remote.

Prompts

Tools

Theme emergence

project_memory_summary categorizes notes by theme. Themes emerge automatically from your notes:

• Tag-based classification — notes with matching tags (e.g., ["decisions"], ["bugs"]) are grouped immediately
• Keyword graduation — keywords that appear across multiple notes become named themes over time
• "other" bucket — notes that don't match any theme are grouped here; this shrinks as themes emerge

No predefined schema required. The system adapts to your project's vocabulary.

Language handling: The system degrades gracefully for non-English notes. Stopwords and synonyms are optional English enhancements; keywords that don't match pass through unchanged, allowing non-English keywords to graduate if they meet frequency thresholds.

Relationships

Notes can be linked with typed edges stored in frontmatter:

relatedTo:
  - id: auth-bug-fix-a1b2c3d4
    type: related-to
  - id: security-policy-b5c6d7e8
    type: explains

workflow recall mode prefers directional and typed relationships first, then falls back to related-to for long-term compatibility with older vaults.

relate is bidirectional by default. forget automatically removes any edges pointing at the deleted note.

Multi-repository attachments

Multi-repo attachment support lets you link external repositories as federated knowledge sources alongside your own project vault. By default, attached repos are read-only; set writable: true on add_attachment to enable write-through.

Key concepts:

• add_attachment links a repo by its absolute localPath (supports ~ expansion); optional branch, vaultFolder, writable, and pushBranch select branch, sub-vault, write access, and push target.
• remove_attachment removes by projectSlug; list_attachments shows all attachments with status.
• set_attachment_enabled toggles an attachment on/off without removing config; set_attachment_branch changes the branch.
• Max 5 attachments per project (configurable via maxAttachmentsPerProject in project memory policy).
• Storage label format: attached:<slug>/.mnemonic
• Use storedIn: "attached" on list, recall, or where_is_memory to audit attached-repo notes; storedIn: "any" includes all vaults.
• sync fetches attached repo branches and reconciles embeddings in the same call.
• Writable attached vaults: when writable: true, remember, update, forget, relate, unrelate, consolidate, and move_memory can modify notes in the attached vault; commits push to pushBranch (or the attachment's branch if omitted).
• Cross-vault relationships: notes in different vaults can be related; the Relationship type includes a vaultPath field for cross-vault traversal.
• If an attached repo or branch is unavailable, reads fail-soft and the rest of the session continues unaffected.

See AGENT.md for the full tool descriptions and attachment architecture details.

Multi-machine workflow

Main vault:

# First time on a new machine:
git clone git@github.com:you/mnemonic-vault.git ~/mnemonic-vault
# Then ask your agent to call the `sync` MCP tool — it pulls, pushes, and backfills embeddings in one step.

Project vault:

# Already in the project repo — clone the project as normal.
# The .mnemonic/ directory comes along with it.
# Ask your agent to call the `sync` MCP tool with the project cwd to pull/push and backfill embeddings.

After the first sync, call the sync MCP tool (with cwd for project vaults) whenever you switch machines. It handles pull, push, and embeddings in one shot.

FAQ

Is the advantage over plain markdown files and grep just easier search?

Easier search is part of it, but three things work together:

• Semantic search over vector embeddings. Each note is indexed through your configured embedding provider so recall finds the right note even when you don't remember the exact words — searching "JWT expiry bug" can surface a note titled "RS256 migration rationale". grep only matches strings you already know.
• A connected knowledge graph. Notes link to each other with typed relationships (explains, supersedes, example-of). Related context surfaces together automatically; memory_graph shows the full web. A folder of markdown files has no edges between them.
• Decision history travels with the code. Every remember, update, and consolidate creates a descriptive git commit, so your decision log and implementation plans evolve alongside the code they describe — attributed and timestamped in git log.

mnemonic is designed to be removable — so give it a try with confidence. We think once you do, you'll stay. But if you ever leave, all the knowledge you've gathered is independent: plain markdown with standard YAML frontmatter, readable in any editor, searchable with grep, committable to git. No rescue operation required.

Are mnemonic's embeddings the same as what Claude uses?

No. The embeddings here are retrieval vectors generated by the provider you configure. With the default Ollama provider, projection text stays on your machine. With OpenAI-compatible cloud proxies, native OpenAI, or Gemini, projection text is sent to that external endpoint. The resulting vectors are stored as local gitignored JSON files. This is the same idea as retrieval-augmented generation (RAG): each note is converted to a dense numeric vector so recall can find semantically related notes even when you don't remember the exact words you used. It has nothing to do with how Claude processes tokens internally.

Why do project memories appear first in recall results even when global memories are more similar?

When you call recall with cwd, mnemonic adds a small fixed project tiebreaker (currently +0.03) to notes belonging to the detected project. This is a soft boost, not a hard filter — global memories are still included when relevant. The tiebreaker helps project context float to the top without overwhelming stronger global matches.

I want to brainstorm with no repo yet. Should I create a temp folder first?

Usually, no. If you're talking to an LLM with mnemonic MCP configured, treat it like a normal brainstorming chat and ask it to store key points in the main vault (global memory).

Example conversation style:

You: I have an idea for a meal-planning app. Let's brainstorm v1 scope.
LLM: Great. I can capture key decisions and open questions in global memory while we explore.

You: Please remember that the app should build weekly meals from pantry items, and avoid recipes with too many missing ingredients.
You: Also remember that I'm undecided on mobile-first vs web-first.

When the idea becomes a real repo, switch to that project context and ask the LLM to migrate only the notes that became project-specific.

You: We're creating the repo now at /path/to/meal-planner.
You: Recall my earlier meal-planner brainstorm notes and move the implementation-relevant ones into this project's vault.

This keeps early ideation reusable as personal/global knowledge while moving concrete project context into .mnemonic/ once collaboration and implementation begin.

How does mnemonic differ from Beads?

mnemonic and Beads address complementary concerns. mnemonic is a knowledge graph: it stores notes, relationships between them, and lets agents retrieve relevant context through semantic search. Beads is a task and dependency tracker: it models work items and their dependencies so agents can determine what is ready to execute next. Both tools can coexist in the same workflow — mnemonic stores knowledge and reasoning while Beads manages execution.

How does mnemonic differ from Memory Bank MCP?

mnemonic and Memory Bank MCP both provide persistent memory for agents, but differ in hosting and scope. Memory Bank MCP is a centralized service — your memory lives in a remote MCP service and is accessed across projects through that single endpoint. mnemonic is local-first — your memories live as plain markdown files on your machine: project-scoped notes in .mnemonic/ within each repo, and personal notes in a global vault under your home directory. There is no always-on server to configure or depend on; the MCP server spawns on demand per session.

How does mnemonic differ from Basic Memory?

Both tools are local-first and use markdown, but with different scoping models. Basic Memory maintains a knowledge base per project that agents can search and update, with optional cloud sync. mnemonic splits memory into two distinct vaults: a global personal vault (~/mnemonic-vault/) for cross-project knowledge, and a project-scoped vault (.mnemonic/) that travels with the repo and is shared via git. This lets you capture early ideas globally before a repo exists, then migrate only project-relevant notes into the shared vault once collaboration begins.

What are temporary notes?

mnemonic distinguishes between two lifecycle states. temporary notes capture evolving working-state: hypotheses, in-progress plans, experiment results, draft reasoning. permanent notes capture durable knowledge: decisions, root cause explanations, architectural guidance, lessons learned. As an investigation progresses, a cluster of temporary notes is typically consolidated into one or more permanent notes, and the scaffolding is discarded. Consolidation should keep the useful outcome without flattening away details future work may need. This two-phase lifecycle keeps exploratory thinking from polluting long-term memory while still giving agents a place to reason incrementally before committing to a conclusion.

Roles, when present, are separate from lifecycle: they help prioritization and retrieval, not retention policy. mnemonic still works without roles, and any inferred role metadata remains an internal hint rather than part of the user-facing note contract.

Contributing

See CONTRIBUTING.md for development setup, dogfooding workflow, testing requirements, and pull request guidelines.

Repository layout

src/       TypeScript runtime code
tests/     Vitest test files
build/     Compiled JavaScript output
.mnemonic/ Project-scoped memories for this repo

Agent instructions

See SYSTEM_PROMPT.md for the recommended agent instructions.