memcord

- Infinite Memory- Claude remembers everything across unlimited conversations with intelligent auto-summarization
- Your Data, Your Control- 100% local storage with zero cloud dependencies or privacy concerns
- Effortless Organization- Per-project memory slots with timeline navigation and smart tagging
- Intelligent Merging- Automatically combines related conversations while eliminating duplicates

uv(Python package manager) — install with:

curl -LsSf https://astral.sh/uv/install.sh | sh

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

curl -fsSL https://github.com/ukkit/memcord/raw/main/install.sh | bash

irm https://github.com/ukkit/memcord/raw/main/install.ps1 | iex

- ✅ Download and setupmemcord
- ✅ Set up Python virtual environment using uv
- ✅ Generate platform-specific MCP configuration files
- ✅ Configure Claude Desktop, Claude Code, VSCode, and Antigravity IDE

curl -fsSL https://github.com/ukkit/memcord/raw/main/install.sh | bash

irm https://github.com/ukkit/memcord/raw/main/install.ps1 | iex

- ✅ Pull the latest changes (fast-forward only — aborts safely if you have local edits)
- ✅ Reuse your existing virtual environment and upgrade dependencies
- ✅ Regenerate MCP configuration files
- ✅ Leave your memory data (memory_slots/) and generated configs untouched

cd /path/to/memcord git pull uv pip install -e . --upgrade uv run python scripts/generate-config.py # Regenerate configs # Optional: Enable auto-save hooks (new in v2.5.0) uv run python scripts/generate-config.py --install-hooks

The--install-hooksflag is idempotent — it merges into existing.claude/settings.jsonwithout overwriting other settings or hooks.

Switching an Existing Install to Global Scope

Fresh installs register memcordglobally(~/.claude.json) by default — available in every project. If you have an older install that's still project-scoped (a local.mcp.json), switch it explicitly — re-running the updater alone won't do this for you, since it auto-detects and preserves an existing project-scoped setup on purpose:

cd /path/to/memcord uv run python scripts/generate-config.py --scope user

Verify from adifferentproject directory:claude mcp listshould now show memcord. The original.mcp.jsonis left in place and still works (harmless, just redundant) — delete it only if you want that directory to stop pinning its own local copy instead of falling through to the global one.

The 17memcord-slash commands ship in.claude/commands/and are already usable from inside the memcord checkout the moment you clone it. To use them fromany*project directory, install them globally into~/.claude/commands/:

uv run python scripts/generate-config.py --manage-commands # interactive picker uv run python scripts/generate-config.py --commands all # non-interactive: install all

Fresh installs prompt for this automatically (skipped when non-interactive, e.g.curl | bash). Re-run anytime to change your selection — only memcord's own command files are ever added or removed.

# 1. Once you are in claude code, initialize the project with a memory slot (one-time setup) memcord_init "." "my-project-name" # OR memcord_init "my_project_name" # Creates .memcord file containing "my-project-name" # 2. Start saving your conversations /memcord-save-progress # Auto-detects slot from .memcord file

Subsequent Sessions (Returning to Project)

# Just use slash commands - no slot name needed! /memcord-read # Reads from bound slot /memcord-save # Saves to bound slot /memcord-save-progress # Summarizes and saves

Searching & Querying (Direct Tool Calls)

memcord_select_entry "2 hours ago" # Jump to a point in the timeline memcord_list # List all slots memcord_search "API design" # Full-text search memcord_query "What did we decide?" # Natural language query

All readand writeoperations follow the same slot resolution priority:
- Explicitslot_nameargument (always wins)
- Currently active slot (set bymemcord_useormemcord_name)
- .memcordbinding file in the current working directory

When the.memcordbinding is used and the slot already exists, it is alsoauto-activatedfor the rest of the session — so subsequent operations skip re-detection automatically.

This means aftermemcord_init, a fresh session (nomemcord_usecall needed) will correctly routememcord_save,memcord_save_progress,memcord_configure, andmemcord_readto the bound slot.

Point a slot's data file at any directory — e.g. a Dropbox/OneDrive folder — to share it across devices, viamemcord_configure. Once linked, the slot's settings (summarizer backend, etc.) travel with the data too, so every device sharing the folder sees the same configuration.

memcord_name "shared_slot" memcord_configure action="set" key="custom_storage_path" value="D:\Dropbox\shared" memcord_save "..." # writes directly to the external path

memcord_configure action="set" key="custom_storage_path" value="D:\Dropbox\shared" # Existing data is moved automatically — memcord_read/memcord_list keep working

Memcord supports four pluggable summarizer backends (nltk,sumy,semantic,transformers), switchable per slot viamemcord_configure action="set" key="summarizer_backend" value="..."— no restart required. New slots default tosumy(no downloads); existing slots keepnltkfor backward compatibility.

The installer auto-configures all supported IDEs. For manual setup or troubleshooting, see the detailed guides:

git clone https://github.com/ukkit/memcord.git cd memcord uv venv && uv pip install -e . uv run python scripts/generate-config.py

If you find this project helpful, consider:

MIT License- see LICENSE file for details.

Local-first agent memory: a plain-Markdown Obsidian vault is the source of truth, with a rebuildable DuckDB index for hybrid BM25 + vector + graph recall.

Open-source shared AI memory and team knowledge layer with 44 MCP tools for notes, memories, URLs, emails, projects, graph search, semantic search, and Git sync.

Local-first second brain for Claude. Saves notes as Markdown and recalls them across sessions with offline semantic search, no cloud and no API keys.

Search what you've saved, pull up full articles, add new links, and write notes in Memlane

Local-first MCP memory server with no external dependency, source citations and OKF/Markdown KB.

Personal knowledge twin with semantic search. Store voice notes, documents, URLs, principles, and skills from any AI chat, then retrieve them with inline provenance citations. Hosted, multi-tenant, with per-user bearer-token auth and full data isolation.

Centralized note store across AI clients: Claude, ChatGPT, Cursor, Codex, Windsurf. Save in one client, access in another instantly. Across devices — phone, desktop, everywhere. Cross-session context: 'catch me up' surfaces plans and findings from any prior session. AES-256-GCM encryption at rest, per-user key isolation. Soft delete with 30-day recovery window. Pin notes to exempt from cleanup and prioritize. Tag notes for categorization and filtering ('tag: auth'). Your mctx account is your identity — instant access from any AI tool.

Self-maintaining knowledge vault: figure-level search, auto-wikilinks, and sleep-based memory compression.

Interact with TheBrain's knowledge management system using its API.