Alcove

Alcove is an MCP server that gives AI coding agents on-demand access to your private project docs — BM25 + vector hybrid search for precision retrieval, tree-sitter code indexing so agents understand your codebase structure, and policy enforcement for doc consistency. No context bloat, no leaking docs into public repos, no per-project config for every agent.

Demo

Claude, Codex — search · switch projects · global search · validate & generate. One setup.

alcove search · project switch · --scope global · alcove validate

The problem

Your AI agent starts every session from zero.

It doesn't know your architecture. It ignores constraints from decisions you already made. It asks you to explain the same things every session.

The context window is the bottleneck. Every token costs money and attention. Loading 10 architecture docs into context wastes 50K+ tokens on every run — and Anthropic's own docs warn that bloated config files make agents ignore your actual instructions.

So you have three bad options:

Stuff everything into agent config — every file loads into context on every run. 10 docs = context bloat = slower, more expensive, less accurate responses.

Copy-paste into every chat — works once, doesn't scale past one session.

Don't bother — your agent invents requirements you already documented, ignores constraints from decisions you already made, and you re-explain the same architecture every Monday morning.

Now multiply it across 5 projects and 3 agents. Every time you switch, you lose context.

How Alcove solves this

Alcove doesn't inject your docs. Agents search for what they need, when they need it.

~/projects/my-app $ claude "how is auth implemented?"

  → Alcove detects project: my-app
  → BM25 search: "auth" → ARCHITECTURE.md (score: 0.94), DECISIONS.md (score: 0.71)
  → Agent gets the 2 most relevant docs, not all 12

~/projects/my-api $ codex "review the API design"

  → Alcove detects project: my-api
  → Same doc structure, same access pattern
  → Different project, zero reconfiguration

Switch agents anytime. Switch projects anytime. The document layer stays standardized.

Why Alcove

Alcove gives your agents a memory that survives between sessions.

Agents don't load your docs into context. They search for what they need, when they need it. Architecture docs, design decisions, runbooks, constraints — all in one place, searchable, never in your public repo.

Agent config is for agent behavior. Alcove is for project knowledge.

Agent config files                ← agent rules, coding conventions, recurring corrections
~/.alcove/docs/my-app/
  ARCHITECTURE.md                ← tech stack, data model, system design
  DECISIONS.md                   ← why X was chosen over Y
  DEBT.md                        ← known issues, workarounds
  ...                            ← agent searches here when it needs context

Quick start

Required: Run alcove setup once after installation to configure your docs root and enable full functionality. Plugins seed the MCP connection automatically, but Alcove cannot search or index documents until setup has been run.

Using Obsidian? See the Ecosystem section for the recommended docs structure and vault configuration.

Claude Code

/plugin marketplace add epicsagas/plugins
/plugin install alcove@epicsagas

Auto-installs the binary and registers the MCP server on next session start.

alcove setup   # run once after plugin install

Updates with claude plugin update alcove@epicsagas.

Codex CLI

codex plugin marketplace add epicsagas/plugins

Skills are available immediately — no further steps needed.

macOS (Apple Silicon only)

brew install epicsagas/tap/alcove

No Homebrew? Use the installer script:

curl --proto '=https' --tlsv1.2 -LsSf \
  https://github.com/epicsagas/alcove/releases/latest/download/install.sh | sh

Note: Pre-built binaries are available for macOS Apple Silicon only. Linux and Windows users can use the one-line installers above.

Linux (x86_64 / ARM64)

curl --proto '=https' --tlsv1.2 -LsSf \
  https://github.com/epicsagas/alcove/releases/latest/download/install.sh | sh

Windows (x86_64 / ARM64)

irm https://github.com/epicsagas/alcove/releases/latest/download/install.ps1 | iex

Via Rust toolchain

cargo binstall alcove   # pre-built binary (fast)
cargo install alcove    # build from source

Note: Pre-built binaries are available for Linux (x86_64), macOS (Apple Silicon & Intel), and Windows.

First-time setup (required)

After installing via any method above, run:

alcove setup
alcove --version
alcove doctor

setup walks you through everything interactively:

1. Where your docs live

2. Which document categories to track

3. Preferred diagram format

4. Embedding model for hybrid search

5. Background server — eliminate cold-start on every session (macOS login item)

6. Which AI agents to configure (MCP + skill files — Claude Code and Codex are handled by their plugin systems)

Re-run alcove setup anytime to change settings. It remembers your previous choices.

Optional dependencies

Without pdftotext, Alcove falls back to a built-in PDF parser which may fail on some files. Run alcove doctor to check your setup.

Troubleshooting

Agent can't find Alcove tools Run alcove setup again — it re-registers the MCP server for all configured agents. Then start a new agent session (registration takes effect on next session start).

Search returns no results The index may not be built yet. Run alcove index to build it, then try again.

403 Unauthorized from background server ALCOVE_TOKEN is not set in your shell. Run alcove token to print it, then add export ALCOVE_TOKEN="..." to your shell profile and reload.

alcove doctor reports issues Follow the suggestions printed by doctor — it checks binary location, MCP registration, index state, and optional dependencies like pdftotext.

Usage

CLI Search

Search through your documents directly from the terminal. By default, it searches across all projects (global scope).

# Basic search (global scope)
alcove search "authentication"

# Limit search to the current project (auto-detected via CWD)
alcove search "auth flow" --scope project

# Force grep mode (exact substring match)
alcove search "TODO" --mode grep

# Force ranked mode (BM25/Hybrid)
alcove search "data model" --mode ranked

# Adjust result limit
alcove search "deployment" --limit 5

Coding Agents (MCP)

AI coding agents use Alcove through MCP tools. You don't usually need to call these yourself; the agent will invoke them when you ask questions about your project.

Example agent interaction:

User: "How do I add a new API endpoint?" Agent: (calls search_project_docs(query="add api endpoint")) Agent: (reads the most relevant doc via get_doc_file) Agent: "According to ARCHITECTURE.md, you need to..."

How it works

flowchart LR
    subgraph Projects["Your projects"]
        A1["my-app/\n  src/ ..."]
        A2["my-api/\n  src/ ..."]
    end

    subgraph Docs["Your private docs (one repo)"]
        D1["my-app/\n  PRD.md\n  ARCH.md"]
        D2["my-api/\n  PRD.md\n  ..."]
        P1["policy.toml"]
    end

    subgraph Agents["Any MCP agent"]
        AG["Claude Code · Cursor\nAntigravity · Codex · Copilot\n+4 more"]
    end

    subgraph MCP["Alcove MCP server"]
        T["search · get_file\noverview · audit\ninit · validate"]
    end

    A1 -- "CWD detected" --> D1
    A2 -- "CWD detected" --> D2
    Agents -- "stdio MCP" --> MCP
    MCP -- "scoped access" --> Docs

Your docs are organized in a separate directory (DOCS_ROOT), one folder per project. Alcove manages docs there and serves them to any MCP-compatible AI agent over stdio.

MCP Tools

CLI

alcove              Start MCP server (agents call this)
alcove setup        Interactive setup — re-run anytime to reconfigure
alcove doctor       Check the health of your alcove installation
alcove validate     Validate docs against policy (--format json, --exit-code)
alcove lint         Semantic lint — broken links, orphans, stale markers (--format json)
alcove promote      Bring a file from an external vault into your doc-repo
alcove index        Update the search index (incremental — only changed files)
alcove rebuild      Rebuild the search index from scratch (use after schema changes)
alcove search       Search docs from the terminal
alcove index-code   Generate code structure index from source [--language LANG] [--source PATH]
alcove token        Print the bearer token (for background server auth)
alcove uninstall    Remove skills, config, and legacy files

alcove mcp <CMD>      Manage background MCP server lifecycle (start, stop, status, enable, disable)

alcove vault create   Create a new knowledge base vault
alcove vault link     Link an external directory as a vault (e.g., Obsidian)
alcove vault list     List all vaults with document counts
alcove vault remove   Remove a vault (symlinks: remove link only)
alcove vault add      Add a document to a vault
alcove vault index    Build search index for vaults
alcove vault rebuild  Rebuild vault search index from scratch

Code Indexing

Parse source files with tree-sitter and generate CODE_INDEX.md — a module-level markdown summary of your codebase that integrates with the Tantivy search pipeline.

# Index the current project's source (auto-detects all languages)
alcove index-code --source ./src

# Monorepo: index a directory with multiple languages at once
alcove index-code --source ./

# Restrict to a single language (useful when only one language should be indexed)
alcove index-code --source ./src --language typescript
alcove index-code --source ./src --language rust

Supported languages:

All 12 parsers are enabled in official binaries (lang-all feature). When no --language flag is given, all recognized extensions are indexed automatically — safe for monorepos.

The --language flag accepts both canonical names and common aliases: ts → TypeScript, cpp → C++, csharp → C#, py → Python, js → JavaScript, kt → Kotlin, rb → Ruby.

Lint

# Lint the current project (auto-detected from CWD)
alcove lint

# Lint a specific project by name
alcove lint --project my-app

# Machine-readable output for CI
alcove lint --format json

Lint checks four things:

Promote

# Copy a note from Obsidian into your doc-repo (auto-routes to matching project)
alcove promote ~/my-brain/Projects/auth-notes.md

# Route to a specific project
alcove promote ~/my-brain/Projects/auth-notes.md --project my-app

# Move instead of copy
alcove promote ~/my-brain/Projects/auth-notes.md --mv

Files with no matching project land in inbox/ for manual review.

Background Server

Running a persistent background server eliminates cold-start latency on every new agent session. alcove setup enables this by default (macOS login item).

alcove mcp enable --now     # Enable and start (persists across reboots)
alcove mcp stop / start / restart / status
alcove mcp disable          # Disable and remove login item

When the background server is running, the stdio process acts as a thin proxy — forwarding requests to the warm server instead of loading the search engine each session. On startup, the stdio process checks GET /health and enters proxy mode automatically.

Search

Alcove automatically picks the best search strategy. When the search index exists, it uses BM25 ranked search (powered by tantivy) for relevance-scored results. When it doesn't, it falls back to grep. You never have to think about it.

Hybrid Search (RAG)

Alcove supports Hybrid Search which combines BM25 with Vector Similarity Search (powered by fastembed).

During alcove setup, you can choose an embedding model and download it immediately. You can also manage models manually:

# Set and download an embedding model
alcove model set MultilingualE5Small
alcove model download

# Check model status
alcove model status

Choosing a model

Once a model is downloaded and ready, Alcove will automatically use Hybrid Search for both CLI search and agent-based MCP tools. This is particularly effective for multilingual projects and complex semantic queries.

# Search the current project (auto-detected from CWD)
alcove search "authentication flow"

# Force grep mode if you want exact substring matching
alcove search "FR-023" --mode grep

The index builds automatically in the background when the MCP server starts, and rebuilds when it detects file changes. No cron jobs, no manual steps.

How it works for agents: agents just call search_project_docs with a query. Alcove handles the rest — ranking, deduplication (one result per file), cross-project search, and fallback. The agent never needs to choose a search mode.

Index lifecycle

Understanding when to run alcove index vs alcove rebuild:

First-time setup:

# Step 1: BM25 search is ready immediately after setup
alcove index            # builds full-text index (no model needed)

# Step 2: Enable Hybrid Search (optional but recommended)
alcove model set MultilingualE5Small
alcove model download   # ~235 MB download

# Step 3: Build vector index for all existing docs
alcove rebuild          # one-time full rebuild with embeddings
                        # ⚠ peak RAM = model size + corpus vectors (see note below)

# After this: incremental updates just work
alcove index            # fast — only re-embeds changed files

Switching models:

alcove model set BGEM3                     # change model
alcove rebuild                            # required: vectors are model-specific

Memory during rebuild:
Peak RAM = model size + all document vectors held in RAM while building the HNSW graph. For MultilingualE5Small with ~3,500 docs, expect ~700 MB peak. This is structural — after rebuild completes, steady-state drops to ~50–200 MB depending on your [memory] config. You can reduce steady-state further with lower max_hnsw_cache and shorter model_unload_secs.

Global search

Every architecture decision, every runbook, every project note — searchable across all your projects at once.

# Search across ALL projects
alcove search "rate limiting patterns" --scope global
alcove search "OAuth token refresh" --scope global

Agents can do the same with scope: "global" in search_project_docs. One query, every project.

Project detection

By default, Alcove detects the current project from your terminal's working directory (CWD). You can override this with the MCP_PROJECT_NAME environment variable:

MCP_PROJECT_NAME=my-api alcove

This is useful when your CWD doesn't match a project name in your docs repo.

Document policy

Define team-wide documentation standards with policy.toml in your docs repo:

[policy]
enforce = "strict"    # strict | warn

[[policy.required]]
name = "PRD.md"
aliases = ["prd.md", "product-requirements.md"]

[[policy.required]]
name = "ARCHITECTURE.md"

  [[policy.required.sections]]
  heading = "## Overview"
  required = true

  [[policy.required.sections]]
  heading = "## Components"
  required = true
  min_items = 2

Policy files are resolved with priority: project (<project>/.alcove/policy.toml) > team (DOCS_ROOT/.alcove/policy.toml) > built-in default (from your config.toml core files). This ensures consistent doc quality across all your projects while allowing per-project overrides.

Document classification

Alcove classifies docs into tiers:

The audit tool scans both your doc-repo and local project directory, then suggests actions — like generating a public README from your private PRD, or pulling misplaced reports back into Alcove.

Configuration

Config lives at ~/.config/alcove/config.toml:

docs_root = "/Users/you/documents"

[core]
files = ["PRD.md", "ARCHITECTURE.md", "PROGRESS.md", "DECISIONS.md", "CONVENTIONS.md", "SECRETS_MAP.md", "DEBT.md"]

[team]
files = ["ENV_SETUP.md", "ONBOARDING.md", "DEPLOYMENT.md", "TESTING.md", ...]

[public]
files = ["README.md", "CHANGELOG.md", "CONTRIBUTING.md", "SECURITY.md", ...]

[diagram]
format = "mermaid"

[server]
host = "127.0.0.1"          # bind address (0.0.0.0 for all interfaces)
port = 57384                  # listen port
token = "alcove-a3f7b2..."   # auto-generated bearer token

[memory]
reader_ttl_secs   = 300   # evict idle IndexReader after N seconds (0 = never)
max_cached_readers = 1    # max concurrent IndexReader instances in RAM
model_unload_secs  = 600  # unload embedding model after N seconds of inactivity (0 = never)
max_hnsw_cache     = 3    # max HNSW graphs held in memory simultaneously

All of this is set interactively via alcove setup. You can also edit the file directly.

Memory usage note: During initial indexing or a full rebuild, Alcove loads the embedding model (~235–500 MB) and holds all document vectors in RAM while constructing the HNSW graph — peak usage scales with corpus size and is unavoidable for that operation. The [memory] settings above control steady-state RAM after indexing is complete.

File lists are fully customizable — add any filename to any category, or move files between categories to match your team's workflow:

[core]
files = ["PRD.md", "ARCHITECTURE.md", "DECISIONS.md", "MY_SPEC.md"]  # added custom doc

[public]
files = ["README.md", "CHANGELOG.md", "PRD.md"]  # PRD exposed as public for this project

Supported agents

Agents with skill support activate Alcove automatically when you ask about project architecture, conventions, decisions, or status. They can also be invoked explicitly:

/alcove                          Summarize current project docs and status
/alcove search auth flow         Search docs for a specific topic
/alcove what conventions apply?  Ask a doc question directly

Supported languages

The CLI automatically detects your system locale. You can also override it with the ALCOVE_LANG environment variable.

# Override language
ALCOVE_LANG=ko alcove setup

Updating

alcove --version

Uninstall

alcove uninstall          # remove skills & config
cargo uninstall alcove    # remove binary

Knowledge Base Vaults

Beyond project documentation, Alcove supports independent knowledge base vaults for research notes, reference materials, and curated knowledge that LLMs can search.

# Create a vault for AI research notes
alcove vault create ai-research

# Link an existing Obsidian vault (no copying — indexes in place)
alcove vault link my-obsidian ~/Obsidian/research

# Add a document
alcove vault add ai-research ~/Downloads/transformer-survey.md

# Build the vault search index
alcove vault index

# List all vaults
alcove vault list
#   areas (8 docs) → (linked)
#   resources (71 docs) → (linked)
#   zettelkasten (17 docs) → (linked)

# Search from CLI
alcove search "attention mechanism" --vault ai-research

# Agents search via MCP
search_vault(query="attention mechanism", vault="ai-research")

# Search ALL vaults at once
search_vault(query="transformer", vault="*")

Vaults are completely isolated from project docs — separate indexes, separate caches, separate search. Your coding agent's project doc search is never affected by vault activity.

Vault Configuration

By default, vaults are stored in ~/.alcove/vaults/. You can change this in your config.toml:

[vaults]
root = "/path/to/your/vaults"

Refer to the Configuration section for more details on config.toml.

Ecosystem

obsidian-forge

Alcove pairs naturally with obsidian-forge, an Obsidian vault generator and automation daemon. For the best integration, your alcove docs_root should point to the obsidian-forge project archives.

1. Set Documents Root Point your primary docs to the obsidian-forge project directory (directly or via symlink):

# During alcove setup, set docs_root to:
~/Obsidian/SecondBrain/99-Archives/projects

2. Link Knowledge Areas as Vaults Link the other three obsidian-forge categories as independent alcove vaults. This creates symlinks in ~/.alcove/vaults/:

# Link obsidian-forge categories
alcove vault link areas ~/Obsidian/SecondBrain/02-Areas
alcove vault link resources ~/Obsidian/SecondBrain/03-Resources
alcove vault link zettelkasten ~/Obsidian/SecondBrain/10-Zettelkasten

Now your agents have structured access:

• search_project_docs: Searches archived project knowledge (PRDs, etc.)

• search_vault: Searches your broader knowledge areas and research notes.

You can verify the physical storage mapping by checking the symlinks in ~/.alcove/vaults/.

Roadmap

• Multi-user remote access — REST API for team doc sharing over LAN/VPN (bearer token auth, rate limiting already implemented). Requires: write API, concurrent index coordination, project lifecycle management.

Contributing

Bug reports, feature requests, and pull requests are welcome. Please open an issue on GitHub to start a discussion.

License

Apache-2.0