[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72361":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":41,"readmeContent":42,"aiSummary":43,"trendingCount":16,"starSnapshotCount":16,"syncStatus":44,"lastSyncTime":45,"discoverSource":46},72361,"basic-memory","basicmachines-co\u002Fbasic-memory","basicmachines-co","AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https:\u002F\u002Fdiscord.gg\u002FtyvKNccgqN","https:\u002F\u002Fbasicmemory.com",null,"Python",3181,212,16,66,0,29,68,166,87,108.99,"GNU Affero General Public License v3.0",false,"main",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"ai","claude","knowledge-management","knowlege-graph","llm","local-first","markdown","mcp","obsidian","obsidian-md","open-source","privacy-first","privacy-first-ai","productivity","python","2026-06-12 04:01:04","\u003C!-- mcp-name: io.github.basicmachines-co\u002Fbasic-memory -->\n[![License: AGPL v3](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-AGPL_v3-blue.svg)](https:\u002F\u002Fwww.gnu.org\u002Flicenses\u002Fagpl-3.0)\n[![PyPI version](https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Fbasic-memory.svg)](https:\u002F\u002Fbadge.fury.io\u002Fpy\u002Fbasic-memory)\n[![Python 3.12+](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fpython-3.12+-blue.svg)](https:\u002F\u002Fwww.python.org\u002Fdownloads\u002F)\n[![Tests](https:\u002F\u002Fgithub.com\u002Fbasicmachines-co\u002Fbasic-memory\u002Fworkflows\u002FTests\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fbasicmachines-co\u002Fbasic-memory\u002Factions)\n[![Ruff](https:\u002F\u002Fimg.shields.io\u002Fendpoint?url=https:\u002F\u002Fraw.githubusercontent.com\u002Fastral-sh\u002Fruff\u002Fmain\u002Fassets\u002Fbadge\u002Fv2.json)](https:\u002F\u002Fgithub.com\u002Fastral-sh\u002Fruff)\n![](https:\u002F\u002Fbadge.mcpx.dev?type=server 'MCP Server')\n![](https:\u002F\u002Fbadge.mcpx.dev?type=dev 'MCP Dev')\n\n## Skip the install — try Basic Memory in the cloud\n\nClaude, Codex, or Cursor connected in 30 seconds. No Python, no JSON, no\nterminal. **$14.25\u002Fmo locked in for life** (regular price $19). 7-day free\ntrial — cancel any time before day 7 if it's not for you. Beta pricing —\nsign up now and your rate never goes up. OSS users: code `BMFOSS` takes\nanother 20% off for 3 months.\n\n[Start free trial →](https:\u002F\u002Fbasicmemory.com?utm_source=github&utm_medium=referral&utm_campaign=readme&utm_content=banner)\n\n---\n\n# Basic Memory\n\n### Your AI never forgets again.\n\nPick up right where you left off — in Claude, Codex, Cursor, ChatGPT, or\nanything that speaks [MCP](https:\u002F\u002Fmodelcontextprotocol.io). Your knowledge\nlives as Markdown files that both you and your AI can read, write, and\nsearch.\n\n- **Local-first.** Plain text on your disk. Forever.\n- **Two-way.** AI and humans write to the same files; sync keeps them in step.\n- **A real knowledge graph.** Observations and wikilinks compound into context.\n- **Semantic search.** Find notes by meaning, not just keywords.\n- **MCP-native.** Works with every major AI client and IDE.\n- **Progressive tool discovery.** Every tool is tagged with behavior hints\n  (read-only, destructive, idempotent) so agents pick the right tool on\n  demand — no wasted context trying things to see what they do.\n- **Cloud, optional.** Sync across devices when you want — never required.\n\n## Get started\n\nPick the path that fits you. Both run the same product on the same Markdown.\n\n\u003Ctable>\n\u003Ctr>\n\u003Cth width=\"50%\">☁️   Cloud\u003C\u002Fth>\n\u003Cth width=\"50%\">💻   Local install\u003C\u002Fth>\n\u003C\u002Ftr>\n\u003Ctr>\n\u003Ctd valign=\"top\">\n\n**30 seconds.** Sign up, connect your AI client, done.\n\n- Works in any browser\n- Mobile, web, desktop\n- Cross-device sync built in\n- We handle hosting, backups, snapshots\n\n**$14.25\u002Fmo locked for life** · 7-day free trial · cancel any time\n\n[**Start free trial →**](https:\u002F\u002Fbasicmemory.com?utm_source=github&utm_medium=referral&utm_campaign=readme&utm_content=quickstart)\n\n\u003C\u002Ftd>\n\u003Ctd valign=\"top\">\n\n**2 minutes.** Install, configure your AI client, run.\n\n- Free forever (AGPL-3.0)\n- All data on your disk\n- Air-gapped friendly\n- Requires Python via [`uv`](https:\u002F\u002Fdocs.astral.sh\u002Fuv\u002F)\n\n```bash\nuv tool install basic-memory\n```\n\n[**Configure your client ↓**](#connect-your-ai-client)\n\n\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftable>\n\n## What people are saying\n\n> Basic Memory changed my whole relationship with LLMs. I switched from GPT\n> and Gemini to exclusively Claude and Claude Code because of this\n> integration and am completely revamping all our company's processes around\n> a Basic Memory workflow.\n>\n> — **Alex**, TrainerDay\n\n> Basic Memory is the missing 'wow' factor in AI chatbots. Now I can't\n> imagine Claude or Claude Code without it.\n>\n> — **Caleb**, Caleb Picker Consulting\n\n> I don't code without Basic Memory anymore. It's such a time saver to be\n> able to refer to projects I don't currently have active and keep a running\n> log of all my learnings and ProTips.\n>\n> — **@groksrc**, Developer\n\nMore on [basicmemory.com](https:\u002F\u002Fbasicmemory.com?utm_source=github&utm_medium=referral&utm_campaign=readme).\n\n## Basic Memory Cloud\n\nThe hosted version of Basic Memory. Same product, same Markdown files, same\nMCP tools — we just host the database, run the sync, and put it on your\nphone.\n\n### What you get\n\n- **Every device, same brain.** Your knowledge graph on web, mobile, and\n  desktop. No copy-paste between machines.\n- **Connect any MCP client.** Claude Desktop, Claude Code, Codex, Cursor,\n  ChatGPT (Custom GPTs), VS Code — one-click connect from the web app.\n- **Bidirectional sync to local.** Edit on your phone, see it in Obsidian on\n  your laptop. rclone-powered with conflict resolution.\n- **Snapshots and backups.** Point-in-time restore. Browse history. Never\n  lose a note.\n- **No lock-in.** Your notes are plain Markdown. Export to local Markdown any\n  time — same files, same format, same wikilinks. Cancel anytime, your data\n  stays yours.\n\nBuilt on WorkOS AuthKit, Neon Postgres, and Tigris S3. Platform source at\n[basic-memory-cloud](https:\u002F\u002Fgithub.com\u002Fbasicmachines-co\u002Fbasic-memory-cloud).\n\n### Pricing\n\n**$14.25\u002Fmo, locked in for the life of your subscription** (regular price\n$19). Sign up during beta and the rate never goes up — as long as you stay\nsubscribed, you keep the price. One plan, no tiers, no surprise upgrades.\nUnlimited notes, unlimited projects, every feature.\n\n- 7-day free trial. Cancel any time before day 7 if it's not for you.\n- Cancel anytime after that too — export your notes whenever you want.\n- OSS users: code `BMFOSS` for another 20% off for 3 months (~$11.40\u002Fmo).\n\n[**Start your 7-day free trial →**](https:\u002F\u002Fbasicmemory.com?utm_source=github&utm_medium=referral&utm_campaign=readme&utm_content=cloud-section)\n\n## Cloud vs. local\n\n|  | Cloud | Local |\n|---|---|---|\n| **Setup time** | 30 seconds | 2 minutes (requires Python) |\n| **Cost** | $14.25\u002Fmo, locked for life (7-day trial) | Free |\n| **Storage** | We host (Tigris S3) | Your disk |\n| **Cross-device sync** | Built in | Manual (Git, Syncthing, etc.) |\n| **Mobile access** | Yes (web + app) | No |\n| **Air-gapped** | No | Yes |\n| **Your data stays yours** | Yes — export anytime | Yes — already there |\n| **Source code** | AGPL-3.0 | AGPL-3.0 |\n| **Snapshots & backups** | Built in | Roll your own |\n\nBoth paths use the same OSS engine and the same Markdown files. There's no\nlock-in either way — flip between them when your needs change.\n\n## Works with the tools you already use\n\n| Client | Transport | Notes |\n|---|---|---|\n| Cloud web app | https | Sign in at basicmemory.com — no install |\n| [Claude Desktop](#claude-desktop) | stdio\u002Fhttps | macOS \u002F Windows \u002F Linux |\n| [Claude Code](#claude-code) | stdio\u002Fhttps | `claude mcp add` |\n| [Codex](#codex-cli) | stdio\u002Fhttps | OpenAI's coding agent |\n| [Cursor](#cursor) | stdio\u002Fhttps | `.cursor\u002Fmcp.json` |\n| [VS Code](#vs-code) | stdio\u002Fhttps | Native MCP support |\n| [ChatGPT](#chatgpt) | https | Custom GPT actions (`search` \u002F `fetch`) |\n| [Obsidian](#obsidian) | — | Reads\u002Fwrites the same Markdown directly |\n| Anything MCP | stdio\u002Fhttps | If it speaks MCP, it works |\n\n## Pick up where you left off\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fa55d8238-8dd0-454a-be4c-8860dbbd0ddc\n\n## Connect your AI client\n\nIf you went the [Cloud](#get-started) route, the web app walks you through\nclient connect. The snippets below are for local installs.\n\n### Claude Desktop\n\nEdit `~\u002FLibrary\u002FApplication Support\u002FClaude\u002Fclaude_desktop_config.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"basic-memory\": {\n      \"command\": \"uvx\",\n      \"args\": [\"basic-memory\", \"mcp\"]\n    }\n  }\n}\n```\n\nRestart Claude Desktop. Notes live in `~\u002Fbasic-memory` by default.\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>Claude Code, Codex CLI, Cursor, VS Code, ChatGPT, Obsidian\u003C\u002Fb>\u003C\u002Fsummary>\n\n### Claude Code\n\n```bash\nclaude mcp add basic-memory -- uvx basic-memory mcp\n```\n\n### Codex CLI\n\nAdd to `~\u002F.codex\u002Fconfig.toml`:\n\n```toml\n[mcp_servers.basic-memory]\ncommand = \"uvx\"\nargs = [\"basic-memory\", \"mcp\"]\n```\n\n### Cursor\n\nAdd to `.cursor\u002Fmcp.json` (project) or `~\u002F.cursor\u002Fmcp.json` (global):\n\n```json\n{\n  \"mcpServers\": {\n    \"basic-memory\": {\n      \"command\": \"uvx\",\n      \"args\": [\"basic-memory\", \"mcp\"]\n    }\n  }\n}\n```\n\n### VS Code\n\nAdd to your User Settings (JSON):\n\n```json\n{\n  \"mcp\": {\n    \"servers\": {\n      \"basic-memory\": {\n        \"command\": \"uvx\",\n        \"args\": [\"basic-memory\", \"mcp\"]\n      }\n    }\n  }\n}\n```\n\n### ChatGPT\n\nBasic Memory exposes OpenAI-compatible `search` and `fetch` tools for Custom\nGPT actions. See the [ChatGPT integration\nguide](https:\u002F\u002Fdocs.basicmemory.com\u002Fintegrations\u002Fchatgpt\u002F?utm_source=github&utm_medium=referral&utm_campaign=readme).\n\n### Obsidian\n\nNo setup. Point Obsidian at `~\u002Fbasic-memory` (or your project folder) and the\nsame wikilinks, frontmatter, and Markdown your AI writes appear in your graph\nview. Edit either side — sync handles the rest.\n\n\u003C\u002Fdetails>\n\nTry a prompt:\n\n```\n\"Create a note about our project architecture decisions.\"\n\"Find information about JWT auth in my notes.\"\n\"What have I been working on this week?\"\n```\n\n## What's New\n\n- **Automatic updates.** Basic Memory keeps itself up to date for `uv tool`\n  and Homebrew installs; `bm update` triggers a manual check.\n- **Semantic vector search.** Find notes by meaning, not just keywords.\n  Hybrid full-text + vector ranking with FastEmbed embeddings, on SQLite or\n  Postgres.\n- **Schema system.** Infer, validate, and diff the structure of your\n  knowledge base with `schema_infer`, `schema_validate`, `schema_diff`.\n- **Per-project cloud routing.** Route individual projects through the cloud\n  while others stay local, via API key (`bm project set-cloud`).\n- **Smarter editing.** `edit_note` append\u002Fprepend auto-creates notes when\n  missing; `write_note` guards against accidental overwrites.\n- **Richer search results.** Matched chunk text is included so the LLM gets\n  context, not just hits.\n- **FastMCP 3.0 + tool annotations.** Every tool ships with MCP behavior\n  hints (`readOnlyHint`, `destructiveHint`, `idempotentHint`,\n  `openWorldHint`) so agents can discover capabilities progressively at\n  runtime instead of guessing or burning tokens.\n- **CLI overhaul.** `--json` output for scripting, workspace-aware commands,\n  and an htop-inspired project dashboard.\n\nFull [CHANGELOG](CHANGELOG.md) for v0.18 → v0.20.\n\n## Why Basic Memory\n\nMost LLM conversations are ephemeral. You ask a question, get an answer, then\neverything is forgotten. Workarounds have limits:\n\n- **Chat history** captures conversations but isn't structured knowledge.\n- **RAG** lets the LLM query your documents but not write back to them.\n- **Vector DBs** need complex infra and usually live in someone else's cloud.\n- **Knowledge graphs** need specialized tooling to maintain.\n\nBasic Memory takes a simpler path: **structured Markdown files that humans\nand LLMs both read and write.**\n\n- All knowledge stays in plain files you control.\n- Both sides read and write to the same files.\n- Familiar Markdown with semantic patterns — no new format to learn.\n- A traversable graph the LLM can follow link by link.\n- Works with the editors you already use (Obsidian, VS Code, anything).\n- Just files plus a local SQLite index. No servers required.\n\n## How it works\n\nYou're chatting normally about coffee:\n\n> I've been experimenting with brewing methods. Pour over gives more clarity\n> than French press, water at 205°F seems best, and freshly ground beans\n> make a huge difference.\n\nAsk the LLM to capture it:\n\n> \"Make a note on coffee brewing methods.\"\n\nA Markdown file appears in your project directory in real time:\n\n```markdown\n---\ntitle: Coffee Brewing Methods\npermalink: coffee-brewing-methods\ntags: [coffee, brewing]\n---\n\n# Coffee Brewing Methods\n\n## Observations\n- [method] Pour over highlights subtle flavors over body\n- [technique] Water at 205°F (96°C) extracts optimal compounds\n- [principle] Freshly ground beans preserve aromatics\n\n## Relations\n- relates_to [[Coffee Bean Origins]]\n- requires [[Proper Grinding Technique]]\n- affects [[Flavor Extraction]]\n```\n\nNext session, the LLM picks up the thread. It follows the relations to\nsurface what you already know about Ethiopian beans and burr grinders, and\nbuilds on it instead of starting over. You see the same files in Obsidian or\nyour editor. Edit them by hand — the AI sees your changes too.\n\nReal two-way flow: humans edit Markdown, LLMs read\u002Fwrite through MCP, sync\nkeeps everything consistent, and the source of truth is always your files.\n\n## The Markdown format\n\nEach file is an `Entity`. Entities have `Observations` (facts about them) and\n`Relations` (links to other entities). That's the whole grammar.\n\n### Frontmatter\n\n```markdown\n---\ntitle: \u003CEntity title>\ntype: note\npermalink: \u003Curi-slug>\ntags: [optional, list]\n---\n```\n\n### Observations\n\nFacts about the entity. Categories in `[brackets]`, tags with `#`, optional\ncontext in parens.\n\n```markdown\n- [method] Pour over highlights subtle flavors\n- [tip] Grind medium-fine for V60 #brewing\n- [fact] Lighter roasts contain more caffeine than dark\n- [resource] James Hoffmann's V60 technique on YouTube\n- [question] How does temperature affect compound extraction?\n```\n\n### Relations\n\nWiki-style links that form the graph. Single-token relation types, or quote\nmulti-word ones.\n\n```markdown\n- pairs_well_with [[Chocolate Desserts]]\n- grown_in [[Ethiopia]]\n- requires [[Burr Grinder]]\n- \"pairs well with\" [[Dark Chocolate]]\n```\n\nBare `- [[Target]]` and prose `- Worth checking out [[Target]]` index as\n`links_to`. Full reference in the\n[docs](https:\u002F\u002Fdocs.basicmemory.com\u002Fgetting-started\u002Fnote-formatting\u002F?utm_source=github&utm_medium=referral&utm_campaign=readme).\n\n## MCP tools\n\nBasic Memory exposes these tools to any MCP client. Every tool is annotated\nwith MCP behavior hints (read-only, destructive, idempotent, open-world) so\nagents can pick the right one without trial-and-error:\n\n- **Content:** `write_note`, `read_note`, `edit_note`, `move_note`,\n  `delete_note`, `read_content`, `view_note`\n- **Search & discovery:** `search`, `search_notes`, `recent_activity`,\n  `list_directory`\n- **Knowledge graph:** `build_context` (navigates `memory:\u002F\u002F` URLs),\n  `canvas` (Obsidian canvas generation)\n- **Projects:** `list_memory_projects`, `create_memory_project`,\n  `get_current_project`, `sync_status`\n- **Schema:** `schema_infer`, `schema_validate`, `schema_diff`\n- **Cloud:** `cloud_info`, `release_notes`\n\nAll MCP tools default to text output; pass `output_format=\"json\"` for\nstructured responses. Full tool reference in the\n[docs](https:\u002F\u002Fdocs.basicmemory.com\u002F?utm_source=github&utm_medium=referral&utm_campaign=readme).\n\n## CLI essentials\n\n```bash\n# Projects\nbasic-memory project list\nbasic-memory project add research ~\u002Fresearch\nbasic-memory project set-cloud research   # route through cloud\nbasic-memory project set-local research   # revert\n\n# Health & maintenance\nbasic-memory status\nbasic-memory doctor              # file \u003C-> DB consistency check\nbasic-memory tool edit-note ...  # CLI access to MCP tools\nbasic-memory update              # check for and install updates\n\n# Imports\nbasic-memory import claude conversations\nbasic-memory import chatgpt\nbasic-memory import memory-json\n```\n\nRouting flags (`--local` \u002F `--cloud`) force a target when you're in mixed\nmode. Full CLI reference in the\n[docs](https:\u002F\u002Fdocs.basicmemory.com\u002Fguides\u002Fcli-reference\u002F?utm_source=github&utm_medium=referral&utm_campaign=readme).\n\n## Auto-updates\n\nCLI installs check for updates every 24 hours by default and apply them\nsilently (so the MCP server keeps responding).\n\n- Supported install sources: `uv tool`, Homebrew\n- Skipped for `uvx` (ephemeral runtime managed by uv)\n- Manual: `bm update` (check + apply) or `bm update --check` (check only)\n\nDisable in `~\u002F.basic-memory\u002Fconfig.json`:\n\n```json\n{ \"auto_update\": false }\n```\n\n## Telemetry\n\nMinimal, anonymous events to understand the CLI-to-cloud conversion funnel.\n\n**What we collect:** cloud promo impressions, cloud login attempts and\noutcomes, promo opt-out events.\n\n**What we don't:** file contents, note titles, knowledge base data, PII, IP\naddresses, per-command or per-tool tracking.\n\nEvents go to our [Umami Cloud](https:\u002F\u002Fumami.is) instance (open-source,\nprivacy-focused) on a background thread — never blocks the CLI.\n\nOpt out:\n\n```bash\nexport BASIC_MEMORY_NO_PROMOS=1\n```\n\nThis disables promos and all telemetry.\n\n## Logging\n\nBasic Memory uses [Loguru](https:\u002F\u002Fgithub.com\u002FDelgan\u002Floguru). Defaults vary\nby entry point:\n\n| Entry point | Default | Why |\n|---|---|---|\n| CLI commands | File only | Doesn't interfere with command output |\n| MCP server | File only | Stdout would corrupt JSON-RPC |\n| API server | File (local) or stdout (cloud) | Docker\u002Fcloud uses stdout |\n\nLog file: `~\u002F.basic-memory\u002Fbasic-memory.log` (10MB rotation, 10 days\nretention).\n\n### Environment variables\n\n| Variable | Default | Description |\n|---|---|---|\n| `BASIC_MEMORY_LOG_LEVEL` | `INFO` | DEBUG \u002F INFO \u002F WARNING \u002F ERROR |\n| `BASIC_MEMORY_CLOUD_MODE` | `false` | API logs to stdout with structured context |\n| `BASIC_MEMORY_FORCE_LOCAL` | `false` | Force local API routing |\n| `BASIC_MEMORY_FORCE_CLOUD` | `false` | Force cloud API routing |\n| `BASIC_MEMORY_EXPLICIT_ROUTING` | `false` | Mark route selection as explicit |\n| `BASIC_MEMORY_ENV` | `dev` | Set to `test` for test mode (stderr only) |\n| `BASIC_MEMORY_NO_PROMOS` | `false` | Disable cloud promos and telemetry |\n| `BASIC_MEMORY_IMPORT_UPLOAD_MAX_BYTES` | `104857600` | Max uploaded import size |\n\n```bash\nBASIC_MEMORY_LOG_LEVEL=DEBUG basic-memory sync\ntail -f ~\u002F.basic-memory\u002Fbasic-memory.log\n```\n\n## Development\n\nBasic Memory supports SQLite (default, fast, no Docker) and Postgres\n(via testcontainers — Docker required).\n\n```bash\njust install          # Install with dev dependencies\njust test-sqlite      # All tests, SQLite\njust test-postgres    # All tests, Postgres (testcontainers)\njust test             # Both backends\njust fast-check       # fix\u002Fformat\u002Ftypecheck + impacted tests + smoke\njust doctor           # File \u003C-> DB consistency check (temp config)\njust lint\njust typecheck        # Pyright (primary)\njust typecheck-ty     # ty (supplemental)\njust format\njust check            # All quality checks\njust migration \"msg\"  # New Alembic migration\n```\n\nTests use pytest markers: `windows`, `benchmark`, `smoke`. See\n[justfile](justfile) for the full list.\n\nContributions welcome — see [CONTRIBUTING.md](CONTRIBUTING.md).\n\n## License\n\n[AGPL-3.0](LICENSE).\n\n## Star History\n\n\u003Ca href=\"https:\u002F\u002Fwww.star-history.com\u002F#basicmachines-co\u002Fbasic-memory&Date\">\n \u003Cpicture>\n   \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=basicmachines-co\u002Fbasic-memory&type=Date&theme=dark\" \u002F>\n   \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=basicmachines-co\u002Fbasic-memory&type=Date\" \u002F>\n   \u003Cimg alt=\"Star History Chart\" src=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=basicmachines-co\u002Fbasic-memory&type=Date\" \u002F>\n \u003C\u002Fpicture>\n\u003C\u002Fa>\n\nBuilt with ♥️ by [Basic Machines](https:\u002F\u002Fbasicmachines.co?utm_source=github&utm_medium=referral&utm_campaign=readme)\n","Basic Memory 是一个让AI对话能够记住上下文的项目，避免用户反复向AI解释相同的内容。它支持将知识以Markdown文件形式存储，既可本地保存也可云端同步，确保信息的安全与隐私。项目利用了知识图谱和语义搜索技术，使得无论是人类还是AI都能高效地读取、编辑和查找资料。此外，通过Model Context Protocol (MCP)的支持，Basic Memory能够兼容多种主流AI客户端及IDE。适用于需要长期维护项目文档、提高工作效率以及重视数据隐私保护的个人或团队使用场景。",2,"2026-06-11 03:41:30","high_star"]