enhx-memory

A persistent, project-scoped memory layer for AI coding agents. Exposes a Model Context Protocol (MCP) server with 39 tools for capturing, searching, deduplicating, relating, and maintaining memory records across long-running coding sessions.

Enterprise-grade by default. The server is 100% automatic —

• 🔁 Auto-session: opens a session against the cwd (or INITIAL_PROJECT_PATH) at boot. You never need to call start_session.
• 📥 Auto-ingest: user prompts that flow through the MCP transport (chat/send, message/send, messages/create) are persisted as memories with the auto_ingest tag, debounced per project.
• 🔎 Auto-recall: every project-scoped tool call returns an auto_recalled array of the most relevant pinned / FTS-matched / recent memories — the agent never has to remember to call recall_memories.
• 🧠 Memory Manager enforces dedup, near-duplicate merging, project conventions, and importance scoring.

This is the TypeScript rewrite of the original Python/FastMCP enhx-memory v0.1.0. The two servers share the same SQLite schema (migrations/0001_initial.sql is byte-identical), so existing databases work without modification.

Install

A. npx (recommended — zero install)

npx enhx-memory

B. Global npm

npm install -g enhx-memory
enhx-memory

C. Single binary

Download a binary for your platform from the GitHub release page. The binary bundles Node + the server + the migrations.

MCP client configuration

Claude Desktop / Cursor / Cline

Common — the three knobs most people tweak: log verbosity, how many memories get auto-attached per tool call (the recall cap), and whether the auto-cleanup scheduler runs. Everything else falls back to its default.

{
  "mcpServers": {
    "enhx-memory": {
      "command": "npx",
      "args": ["-y", "enhx-memory"],
      "env": {
        "DATA_DIR": "/path/to/your/data",
        "LOG_LEVEL": "INFO",
        "AUTO_RECALL_LIMIT": "5",
        "ENABLE_AUTO_CLEANUP": "true"
      }
    }
  }
}

Note: there is no MAX_MEMORY_ITEMS — the closest knob is AUTO_RECALL_LIMIT, which caps how many memories are auto-attached to every tool result. To bound total storage, use ENABLE_AUTO_CLEANUP with CLEANUP_INTERVAL_HOURS and SOFT_DELETE_GRACE_DAYS (below).

Fully-configured — every variable the server reads from env, with defaults inline. Drop or change the ones you want to override; everything else is optional.

{
  "mcpServers": {
    "enhx-memory": {
      "command": "npx",
      "args": ["-y", "enhx-memory"],
      "env": {
        "DATA_DIR": "/path/to/your/data",
        "DB_FILENAME": "enhx_memory.db",
        "LOG_LEVEL": "INFO",
        "DEDUP_POLICY": "reject",
        "DEDUP_THRESHOLD": "0.8",
        "ENABLE_AUTO_CLEANUP": "true",
        "CLEANUP_INTERVAL_HOURS": "24",
        "SOFT_DELETE_GRACE_DAYS": "7",
        "ENABLE_AUTO_SESSION": "true",
        "INITIAL_PROJECT_NAME": "",
        "INITIAL_PROJECT_PATH": "",
        "INITIAL_CLIENT": "auto",
        "ENABLE_AUTO_INGEST": "true",
        "AUTO_INGEST_DEBOUNCE_SECONDS": "30",
        "AUTO_INGEST_MIN_LENGTH": "20",
        "ENABLE_AUTO_RECALL": "true",
        "AUTO_RECALL_LIMIT": "5",
        "AUTO_RECALL_MIN_SCORE": "0",
        "AUTO_DETECT_CONVENTIONS": "true"
      }
    }
  }
}

Globally-installed npm (the env block is optional — only override what you need):

{
  "mcpServers": {
    "enhx-memory": {
      "command": "enhx-memory",
      "env": {
        "LOG_LEVEL": "INFO",
        "AUTO_RECALL_LIMIT": "5",
        "ENABLE_AUTO_CLEANUP": "true"
      }
    }
  }
}

Single binary (same — env block optional):

{
  "mcpServers": {
    "enhx-memory": {
      "command": "/usr/local/bin/enhx-memory",
      "env": {
        "LOG_LEVEL": "INFO",
        "AUTO_RECALL_LIMIT": "5",
        "ENABLE_AUTO_CLEANUP": "true"
      }
    }
  }
}

CLI flags

| Flag | Behavior | |---|---| | --data-dir | Print the data directory path and exit | | --install-path | Print the install path | | --reset --yes | Wipe the database and logs (refuses without marker file) | | --uninstall --yes | Remove the install + data dir | | --upgrade | Print the npm install -g enhx-memory@latest command | | --version | Print version | | --help | Print help |

Without flags, the server starts on stdio.

Environment variables

| Variable | Default | Description | |---|---|---| | DATA_DIR | ~/enhx-memory | Where the DB and logs live | | DB_FILENAME | enhx_memory.db | Database filename | | LOG_LEVEL | INFO | DEBUG | INFO | WARNING | ERROR | | DEDUP_POLICY | reject | reject | merge | warn | off | | DEDUP_THRESHOLD | 0.8 | Jaccard similarity cutoff for near-duplicates | | ENABLE_AUTO_CLEANUP | true | Run the cleanup scheduler | | CLEANUP_INTERVAL_HOURS | 24 | Cleanup cycle period | | SOFT_DELETE_GRACE_DAYS | 7 | Days to keep soft-deleted rows before purging | | ENABLE_AUTO_SESSION | true | Open a session at boot against cwd / INITIAL_PROJECT_PATH | | INITIAL_PROJECT_NAME | (none) | Force a specific project name when auto-sessions boot | | INITIAL_PROJECT_PATH | (cwd) | Force a specific project root path when auto-sessions boot | | INITIAL_CLIENT | auto | Client name recorded on the auto-opened session | | ENABLE_AUTO_INGEST | true | Persist user prompts as memories (auto-debounced) | | AUTO_INGEST_DEBOUNCE_SECONDS | 30 | Debounce window per content hash | | AUTO_INGEST_MIN_LENGTH | 20 | Minimum text length to ingest | | ENABLE_AUTO_RECALL | true | Attach auto_recalled to every project-scoped tool result | | AUTO_RECALL_LIMIT | 5 | Max memories attached per tool call | | AUTO_RECALL_MIN_SCORE | 0 | Minimum score for non-pinned recall hits | | AUTO_DETECT_CONVENTIONS | true | Detect project conventions on start_session |

Note: ENABLE_AUTO_INGEST, ENABLE_AUTO_RECALL, and ENABLE_AUTO_SESSION all default to true so the server runs as a fully automatic memory layer out of the box. Set any of them to false to opt out of that specific behavior.

The 39 tools

Lifecycle (5)

• start_session — open a session against a project (auto-creates if needed). When called with no arguments, delegates to AutoSessionManager and returns an auto_recalled array of relevant memories.
• get_project_summary — counts + recent memories for the active project, plus auto_recalled.
• list_projects — all known projects.
• notify_project_change — explicit signal that the agent has switched projects (e.g. into a git worktree, multi-repo monorepo, or any case the cwd watcher can't see). Takes {cwd?, project_name?, root_path?, reason?}; rebinds the active project, opens a fresh session, and returns the new active project + an auto_recalled array.
• get_active_project — return the currently active project and session (auto-recovers a session if none is active).

Conventions (4)

• detect_project_type — sniff files at a root path
• detect_and_save_project_conventions — persist conventions on the project row
• remember_project_pattern — save a project-specific pattern as a memory
• get_project_conventions — return saved conventions

Auto-ingest (2)

• set_auto_ingest — toggle + configure the auto-ingest middleware
• get_auto_ingest_status — current config + counters

Recall & ingest (2)

• recall_memories — free-text recall: pinned first, then FTS hits, then recent backfill. Returns RecalledMemory[] with score and reason.
• add_user_message — convenience tool for the agent to persist every user prompt as a conversation-type memory tagged user_prompt. Auto-recall is also attached.

Memories (8)

Every project-scoped tool here returns an auto_recalled array of relevant memories, so the agent never needs to issue a separate recall_memories call.

• add_memory — insert with optional type/tags/importance/file paths
• get_memory — fetch a single row (bumps access count)
• list_memories — paginated list with filters
• search_memories — FTS5 + LIKE search
• update_memory — patch fields on an existing memory
• delete_memory — soft-delete (preserved until cleanup)
• count_memories — fast count with filters
• bulk_add_memories — insert many in one call

Dedup (3)

• find_duplicates — scan project for near-duplicates
• merge_memories — combine two memories (rewires relations, hard-deletes source)
• set_dedup_policy — reject / merge / warn / off + threshold

Relations (5)

• add_relation — directed edge between two memories
• remove_relation — drop edges (optionally filtered by type)
• get_relations — incoming + outgoing edges for a memory
• get_related_memories — BFS up to N hops
• list_relation_types — distinct types currently used

Tasks (4)

• create_task — new task in the active project
• list_tasks — paginated with status/priority filters
• update_task_status — pending / in_progress / done / cancelled
• delete_task — remove by id

Cleanup (3)

• cleanup_old_data — purge soft-deleted rows + VACUUM/ANALYZE
• optimize_memories — drop orphans + canonicalize JSON
• set_cleanup_policy — adjust interval / grace / enable

System (3)

• health_check — DB, FTS, active project, scheduler, auto-ingest status
• get_database_stats — table row counts + size
• get_performance_stats — per-tool call counts, latencies, error rates

Development

git clone https://github.com/enhx/enhx-memory.git
cd enhx-memory
npm install
npm run typecheck   # tsc --noEmit
npm run lint        # eslint
npm test            # vitest run (208 tests)
npm run build       # tsc → dist/
npm start           # node bin/enhx-memory.mjs (uses dist/)
npm run dev         # tsx src/index.ts (no build needed)

Test coverage is configured to fail under 80 % line coverage (vitest --coverage).

Architecture

src/
  index.ts              # entry — boots DB, AppContext, McpServer, transport
  config.ts             # ServerConfig (zod-validated, env-driven)
  logging.ts            # pino + rotating file
  context.ts            # AppContext (DI bag)
  perf/tracker.ts       # per-tool latency tracking
  errors.ts             # ToolError / DatabaseError / ValidationError
  util/                 # csv, json, signals, time
  db/                   # DatabaseManager + per-table CRUD (better-sqlite3)
  dedup/                # normalize + MinHash + Jaccard
  domain/               # MemoryManager, RelationsManager, TasksManager,
                        # ProjectConventionLearner, AutoIngestMiddleware,
                        # CleanupScheduler
  tools/                # 39 MCP tools (9 files + register.ts)
migrations/             # 0001_initial.sql (verbatim from Python v0.1.0)
bin/enhx-memory.mjs     # CLI launcher
tests/                  # vitest suite (helpers, db, domain, dedup, unit, integration)

The full rewrite plan is in TS_REWRITE_PLAN.md.

License

MIT