{"id":33266077,"url":"https://github.com/ukkit/memcord","last_synced_at":"2026-06-13T04:04:58.037Z","repository":{"id":301498575,"uuid":"1009410462","full_name":"ukkit/memcord","owner":"ukkit","description":"🧠 Privacy-first MCP server for AI memory management. Save, search \u0026 organize chat history with intelligent  summarization.","archived":false,"fork":false,"pushed_at":"2026-06-10T12:48:22.000Z","size":2684,"stargazers_count":66,"open_issues_count":0,"forks_count":11,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-06-10T14:22:43.175Z","etag":null,"topics":["ai-assistant","ai-memory","antigravity","chat-history","claude-desktop","conversation-management","developer-tools","google-antigravity","local-storage","mcp-server","memory-management","memory-slots","model-context-protocol","model-context-protocol-server","privacy-first","privacy-focused","python"],"latest_commit_sha":null,"homepage":"https://coff.ee/ukkit","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ukkit.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"docs/security-vscode.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-06-27T04:59:50.000Z","updated_at":"2026-06-10T12:49:09.000Z","dependencies_parsed_at":"2025-06-27T07:31:15.112Z","dependency_job_id":"96a8e87f-c2ac-4522-b5bd-b788e893e399","html_url":"https://github.com/ukkit/memcord","commit_stats":null,"previous_names":["ukkit/memcord"],"tags_count":12,"template":false,"template_full_name":null,"purl":"pkg:github/ukkit/memcord","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ukkit%2Fmemcord","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ukkit%2Fmemcord/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ukkit%2Fmemcord/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ukkit%2Fmemcord/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ukkit","download_url":"https://codeload.github.com/ukkit/memcord/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ukkit%2Fmemcord/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34271512,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-13T02:00:06.617Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-assistant","ai-memory","antigravity","chat-history","claude-desktop","conversation-management","developer-tools","google-antigravity","local-storage","mcp-server","memory-management","memory-slots","model-context-protocol","model-context-protocol-server","privacy-first","privacy-focused","python"],"created_at":"2025-11-17T07:00:34.359Z","updated_at":"2026-06-13T04:04:58.031Z","avatar_url":"https://github.com/ukkit.png","language":"Python","funding_links":["https://buymeacoffee.com/ukkit"],"categories":["AI Memory \u0026 RAG","پیاده‌سازی‌های سرور","📦 Other"],"sub_categories":["Memory","💻 \u003ca name=\"developer-tools\"\u003e\u003c/a\u003eابزارهای توسعه‌دهنده"],"readme":"\u003cdiv align=\"center\"\u003e\n  \u003cimg src=\"assets/image/memcord_1024.png\" width=\"256\"\u003e\n  \u003ch3\u003eMEMCORD v4.0.0 (mcp server)\u003c/h3\u003e\n  \u003cp\u003eThis privacy-first, self-hosted MCP server helps you organize chat history, summarize messages, search across past chats with AI — and keeps everything secure and fully under your control.\u003c/p\u003e\n\u003c/div\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/modelcontextprotocol\"\u003e\u003cimg src=\"https://img.shields.io/badge/MCP-Server-blue\" alt=\"MCP Server\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://docs.anthropic.com/claude/docs/claude-code\"\u003e\u003cimg src=\"https://img.shields.io/badge/Claude-Code-purple\" alt=\"Claude Code\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://claude.ai/desktop\"\u003e\u003cimg src=\"https://img.shields.io/badge/Claude-Desktop-orange\" alt=\"Claude Desktop\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://code.visualstudio.com/\"\u003e\u003cimg src=\"https://img.shields.io/badge/Visual_Studio-Code-orange\" alt=\"VSCode\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://antigravity.google\"\u003e\u003cimg src=\"https://img.shields.io/badge/Google-Antigravity-4285F4\" alt=\"Google Antigravity\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://python.org\"\u003e\u003cimg src=\"https://img.shields.io/badge/Python-3.10+-green\" alt=\"Python\"\u003e\u003c/a\u003e\n  \u003ca href=\"LICENSE\"\u003e\u003cimg src=\"https://img.shields.io/badge/License-MIT-yellow\" alt=\"License\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://buymeacoffee.com/ukkit\"\u003e\u003cimg src=\"https://img.shields.io/badge/Buy%20Me%20A-Coffee-white\" alt=\"Buy Me a Coffee\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003ch2 align=\"center\"\u003eNever Lose Context Again\u003c/h2\u003e\n\u003cp align=\"center\"\u003e\u003cem\u003eTransform your Claude conversations into a searchable, organized knowledge base that grows with you\u003c/em\u003e\u003c/p\u003e\n\n\u003e **[What's new in v4.0.0](docs/versions.md#v400---openclaw--clawhub-compatibility)** — OpenClaw / ClaWHub compatibility: new `memcord_auto_save` tool for zero-setup gateway integrations, `MEMCORD_DEFAULT_SLOT` env var fallback in slot resolution, and `SKILL.md` for ClaWHub discovery.\n\n## Table of Contents\n\n- [Core Benefits](#core-benefits)\n- [Prerequisites](#prerequisites)\n- [Quick Start](#quick-start)\n- [Demo](#demo)\n- [IDE Configuration](#ide-configuration)\n- [Keeping Memcord Updated](#keeping-memcord-updated)\n- [Using Memcord in a Project](#using-memcord-in-a-project)\n- [Basic Usage](#basic-usage)\n- [Summarizer Backends](#summarizer-backends)\n- [Documentation](#documentation)\n\n## Core Benefits\n\n* **Infinite Memory** - Claude remembers everything across unlimited conversations with intelligent auto-summarization\n* **Your Data, Your Control** - 100% local storage with zero cloud dependencies or privacy concerns\n* **Effortless Organization** - Per-project memory slots with timeline navigation and smart tagging\n* **Intelligent Merging** - Automatically combines related conversations while eliminating duplicates\n\n## Prerequisites\n\n\u003cdetails\u003e\n\u003csummary\u003ePython 3.10+ and uv are required. The installer handles both — click to expand manual instructions.\u003c/summary\u003e\n\n- **Python 3.10+** — [python.org](https://python.org)\n- **uv** (Python package manager) — install with:\n\n  **macOS / Linux:**\n  ```bash\n  curl -LsSf https://astral.sh/uv/install.sh | sh\n  ```\n  **Windows (PowerShell):**\n  ```powershell\n  powershell -ExecutionPolicy ByPass -c \"irm https://astral.sh/uv/install.ps1 | iex\"\n  ```\n\n\u003c/details\u003e\n\n## Quick Start\n\n**macOS / Linux:**\n```bash\ncurl -fsSL https://github.com/ukkit/memcord/raw/main/install.sh | bash\n```\n\n**Windows (PowerShell):**\n```powershell\nirm https://github.com/ukkit/memcord/raw/main/install.ps1 | iex\n```\n\nThis will:\n- ✅ Download and setup **memcord**\n- ✅ Set up Python virtual environment using uv\n- ✅ Generate platform-specific MCP configuration files\n- ✅ Configure Claude Desktop, Claude Code, VSCode, and Antigravity IDE\n\n## Demo\n\n_A demo GIF or terminal recording will be added here. Contributions welcome!_\n\n## IDE Configuration\n\nThe installer auto-configures all supported IDEs. For manual setup or troubleshooting, see the detailed guides:\n\n| IDE / Client | Guide |\n|---|---|\n| Claude Code CLI | [Installation Guide — Claude Code](docs/installation.md#claude-code-cli-recommended-) |\n| Claude Desktop | [Installation Guide — Claude Desktop](docs/installation.md#claude-desktop) |\n| VSCode + GitHub Copilot | [VSCode Setup Guide](docs/vscode-setup.md) |\n| Google Antigravity | [Installation Guide — Other MCP Apps](docs/installation.md#other-mcp-applications) |\n| Configuration templates | [`config-templates/`](config-templates/) ([README](config-templates/README.md)) |\n\n### Manual Installation\n\n```bash\ngit clone https://github.com/ukkit/memcord.git\ncd memcord\nuv venv \u0026\u0026 uv pip install -e .\nuv run python scripts/generate-config.py\n```\n\nSee the **[Complete Installation Guide](docs/installation.md)** for updating, advanced options, and custom commands.\n\n## Keeping Memcord Updated\n\n```bash\ncd /path/to/memcord\ngit pull\nuv pip install -e .\nuv run python scripts/generate-config.py  # Regenerate configs\n\n# Optional: Enable auto-save hooks (new in v2.5.0)\nuv run python scripts/generate-config.py --install-hooks\n```\n\nThe `--install-hooks` flag is idempotent — it merges into existing `.claude/settings.json` without overwriting other settings or hooks.\n\n\u003ca id=\"using-memcord-in-a-project\"\u003e\u003c/a\u003e\n\n## Using Memcord in a Project\n\n### First-Time Setup (New Project)\n\n```bash\n# 1. Once you are in claude code, initialize the project with a memory slot (one-time setup)\nmemcord_init \".\" \"my-project-name\"\n# OR\nmemcord_init \"my_project_name\"\n# Creates .memcord file containing \"my-project-name\"\n\n# 2. Start saving your conversations\n/memcord-save-progress  # Auto-detects slot from .memcord file\n```\n\n### Subsequent Sessions (Returning to Project)\n\n```bash\n# Just use slash commands - no slot name needed!\n/memcord-read           # Reads from bound slot automatically\n\n/memcord-save           # Saves to bound slot automatically\n/memcord-save-progress  # Summarizes and saves automatically\n```\n\n### Enable Auto-Save (Optional)\n\n```bash\nuv run python scripts/generate-config.py --install-hooks\n```\n\nAutomatically saves conversation progress before context compaction and on session end. See [config-templates/README.md](config-templates/README.md#auto-save-hooks-optional) for details.\n\n### How Auto-Detection Works\n\nAll read **and write** operations follow the same slot resolution priority:\n\n1. Explicit `slot_name` argument (always wins)\n2. Currently active slot (set by `memcord_use` or `memcord_name`)\n3. `.memcord` binding file in the current working directory\n\nWhen the `.memcord` binding is used and the slot already exists, it is also **auto-activated** for the rest of the session — so subsequent operations skip re-detection automatically.\n\nThis means after `memcord_init`, a fresh session (no `memcord_use` call needed) will correctly route `memcord_save`, `memcord_save_progress`, `memcord_configure`, and `memcord_read` to the bound slot.\n\n## Basic Usage\n\n### Saving \u0026 Retrieving\n\n```bash\nmemcord_name \"project_meeting\"          # Create or select a slot\nmemcord_save \"Our discussion about...\"  # Save exact text\nmemcord_save_progress                   # Save a compressed summary\nmemcord_read                            # Read the slot\n```\n\n### Navigating \u0026 Searching\n\n```bash\nmemcord_select_entry \"2 hours ago\"    # Jump to a point in the timeline\nmemcord_list                          # List all slots\nmemcord_search \"API design\"           # Full-text search\nmemcord_query \"What did we decide?\"   # Natural language query\n```\n\n### Project \u0026 Privacy\n\n```bash\nmemcord_init \".\" \"my-project\"  # Bind a memory slot to this directory\nmemcord_zero                   # Privacy mode — nothing gets saved\n```\n\nSee **[Complete Tools Reference](docs/tools-reference.md)** for all 23 tools with full parameters and examples.\n\n## Summarizer Backends\n\nMemcord supports four summarizer backends. New slots default to **sumy** (graph-based, no downloads required). Existing slots keep **nltk** to preserve prior behavior.\n\n| Backend | Type | Speed | Quality | Extra install |\n|---|---|---|---|---|\n| `nltk` | Extractive | Fast | Good | None (built-in) |\n| `sumy` | Extractive (graph) | Fast | Better | None (built-in) |\n| `semantic` | Extractive (embeddings) | Medium | Best extractive | `uv pip install \"memcord[semantic]\"` (~80 MB) |\n| `transformers` | Abstractive (BART) | Slow | Best overall | `uv pip install \"memcord[transformers]\"` (~400 MB) |\n\n### Switching Backends\n\nUse `memcord_configure` to change the backend for any slot — no restart required:\n\n```bash\n# Check current config\nmemcord_configure action=\"get\"\n\n# Switch to the BART abstractive summarizer (best for conversations)\nmemcord_configure action=\"set\" key=\"summarizer_backend\" value=\"transformers\"\n\n# Switch to embedding-based semantic summarizer\nmemcord_configure action=\"set\" key=\"summarizer_backend\" value=\"semantic\"\n\n# Switch sumy algorithm (lexrank / lsa / edmundson)\nmemcord_configure action=\"set\" key=\"sumy_algorithm\" value=\"lsa\"\n\n# Reset to defaults\nmemcord_configure action=\"reset\"\n```\n\nTo apply one backend to **all slots** (e.g. in Docker or CI), set the environment variable:\n\n```bash\nexport MEMCORD_SUMMARIZER=transformers\n```\n\nSee **[Tools Reference — memcord_configure](docs/tools-reference.md)** for the full parameter list.\n\n## Documentation\n\n| Guide | Description |\n|---|---|\n| **[Installation Guide](docs/installation.md)** | Complete setup instructions for all MCP applications |\n| **[Feature Guide](docs/features-guide.md)** | Complete list of features |\n| **[Tools Reference](docs/tools-reference.md)** | Detailed documentation for all 23 tools |\n| **[Import \u0026 Merge Guide](docs/import-and-merge.md)** | Comprehensive guide for Phase 3 features |\n| **[Search \u0026 Query Guide](docs/search-and-query.md)** | Advanced search features and natural language queries |\n| **[Usage Examples](docs/examples.md)** | Real-world workflows and practical use cases |\n| **[Data Format Specification](docs/data-format.md)** | Technical details and file formats |\n| **[Troubleshooting](docs/troubleshooting.md)** | Common issues and solutions |\n| **[Version History](docs/versions.md)** | Changelog for all releases |\n\n---\n\nIf you find this project helpful, consider:\n\n - ⭐ Starring the repository on GitHub\n - ☕ [Support Development](https://buymeacoffee.com/ukkit)\n - 🐛 Reporting bugs and suggesting features\n\n---\n\n**MIT License** - see LICENSE file for details.\n\n---\n\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=ukkit/memcord\u0026type=date\u0026legend=top-left)](https://www.star-history.com/#ukkit/memcord\u0026type=date\u0026legend=top-left)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fukkit%2Fmemcord","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fukkit%2Fmemcord","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fukkit%2Fmemcord/lists"}