Awareness Local

io.github.everest-anv0.12.6更新于 Oct 3, 2026

Local-first persistent memory for AI coding agents - 96.0% R@5 on LongMemEval, zero LLM calls.

已验证STDIO仅桌面Developer ToolsKnowledge & Memory

概览

AI 生成的概览

为 AI 编程助手提供本地持久记忆，把决策、任务和会话上下文以 Markdown 保存，并支持关键词与语义混合检索。

功能
在本机运行一个轻量守护进程，通过 MCP 工具提供会话上下文初始化、记忆检索、决策与代码变更记录、任务和知识卡片查询，以及获取面向不同助手的提示词。记忆以 Markdown 文件保存在 .awareness 目录，并用本地 SQLite 索引进行检索；检索采用渐进式披露，先返回简短摘要，再按需获取所选条目的完整内容。本地网页面板可浏览记忆、知识卡片和任务。
适用场景
适合跨多个会话的长期项目，例如长时间迁移、团队交接、个人编码规范，以及需要共享决策历史的多助手协作场景。面向希望记忆留在本机并可离线使用的开发者。
运行要求
需要 Node.js 18 或更高版本，以及兼容 MCP 的 IDE。通过 npm 包执行安装，守护进程监听本机端口。本地模式不需要云账号、Python 或 Docker。
安装前请注意
服务器会在项目的 .awareness 目录写入记忆文件和搜索索引，记录内容可能被提交到版本控制。可选的云同步可在之后通过安装命令或面板启用，会把记忆发送到本机之外并涉及设备认证流程；启用前请确认同步的内容。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Awareness Local，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Awareness Local

Languages: English | 简体中文

[Awareness Local — Persistent Memory for AI Coding Agents]

[LongMemEval R@5 96.0%] [Website] [Docs] [Discord] [License MIT]

[Awareness Local]

Give your AI agent persistent memory. One command. No account. Works offline.

Awareness Local is a local-first MCP memory server for AI coding agents. It gives Cursor, Claude Code, Copilot, Cline, and other MCP IDEs persistent memory, hybrid semantic + keyword retrieval, and reusable knowledge cards for long-running software projects.

It runs a lightweight daemon on your machine, stores memory as Markdown, indexes recall with SQLite FTS5 + embeddings, and keeps your AI workflow fast, explainable, and offline-ready.

bash
npx @awareness.market/setup

That's it. Your AI agent now remembers everything across sessions.

Why Awareness Local

AI coding agents lose context between sessions. Awareness Local provides cross-session memory recall so agents can continue work without re-explaining architecture, past decisions, pending tasks, and implementation constraints.

  • Persistent memory for AI coding agents
  • Local-first MCP server with offline support
  • Hybrid retrieval (keyword + semantic)
  • Knowledge card extraction for decisions, solutions, and risks

Quick Start

bash
npx @awareness.market/setup

Then open your IDE and start coding. Awareness tools become available for recall, record, and session initialization.

Popular Use Cases

  • Long-running codebase migrations across many sessions
  • Team handoffs where AI should remember prior implementation context
  • Personal coding workflows that need durable preferences and conventions
  • Multi-agent setups that share decision history and task memory

FAQ

Does Awareness Local work offline?

Yes. Local mode works fully offline with memory stored on your machine.

Where is data stored?

Memory is stored as Markdown in .awareness/, with a local SQLite index for retrieval.

Do I need a cloud account?

No. Cloud sync is optional and can be enabled later.

Which IDEs are supported?

Any MCP-compatible IDE, including Cursor, Claude Code, Copilot, Cline, Windsurf, and others. ChatGPT Desktop: Settings → MCP servers → Add server → Streamable HTTP → http://127.0.0.1:37800/mcp (local daemon only, no auth needed).

Navigation

Benchmark: LongMemEval (ICLR 2025)

Evaluated on LongMemEval — the industry standard benchmark for long-term conversational memory. 500 human-curated questions across 5 core capabilities.

╔══════════════════════════════════════════════════════════════╗║                                                              ║║   Awareness Memory — LongMemEval Benchmark Results           ║║   ─────────────────────────────────────────────────           ║║                                                              ║║   Benchmark:  LongMemEval (ICLR 2025)                       ║║   Dataset:    500 human-curated questions                    ║║   Variant:    LongMemEval_S (~115k tokens per question)      ║║                                                              ║║   ┌─────────────────────────────────────────────────┐        ║║   │                                                 │        ║║   │   Recall@1    80.2%    (401 / 500)              │        ║║   │   Recall@3    92.8%    (464 / 500)              │        ║║   │   Recall@5    96.0%    (480 / 500)  ◀ PRIMARY   │        ║║   │   Recall@10   98.6%    (493 / 500)              │        ║║   │                                                 │        ║║   └─────────────────────────────────────────────────┘        ║║                                                              ║║   Method:     Hybrid RRF (BM25 + vector, daemon pipeline)    ║║   Embedding:  multilingual-e5-small (production model)       ║║   LLM Calls:  0  (pure retrieval, no generation cost)        ║║   Hardware:   Apple M1, 8GB RAM — 35 min total               ║║                                                              ║╚══════════════════════════════════════════════════════════════╝
┌─────────────────────────────────────────────────────────────┐│          Long-Term Memory Retrieval — R@5 Leaderboard       ││          LongMemEval (ICLR 2025, 500 questions)             │├─────────────────────────────────┬───────────┬───────────────┤│  System                         │  R@5      │  Note         │├─────────────────────────────────┼───────────┼───────────────┤│  MemPalace (ChromaDB raw)       │  96.6%    │  R@5 only *   ││  ★ Awareness Memory (Hybrid)    │  96.0%    │  Hybrid RRF   ││  OMEGA                          │  95.4%    │  QA Accuracy  ││  Mastra (GPT-5-mini)            │  94.9%    │  QA Accuracy  ││  Mastra (GPT-4o)                │  84.2%    │  QA Accuracy  ││  Supermemory                    │  81.6%    │  QA Accuracy  ││  Zep / Graphiti                 │  71.2%    │  QA Accuracy  ││  GPT-4o (full context)          │  60.6%    │  QA Accuracy  │├─────────────────────────────────┴───────────┴───────────────┤│  * MemPalace 96.6% is Recall@5 only, not QA Accuracy.      ││    Palace hierarchy was NOT used in the evaluation.         │└─────────────────────────────────────────────────────────────┘
┌─────────────────────────────────────────────────────────────┐│     Awareness Memory — R@5 by Question Type                 ││                                                             ││  knowledge-update        ███████████████████████████ 98.7%  ││  multi-session           ███████████████████████████▊  99.2%││  single-session-asst     ███████████████████████████▌  98.2%││  temporal-reasoning      ██████████████████████████▏   93.2%││  single-session-user     ██████████████████████████    92.9%││  single-session-pref     █████████████████████████▎    90.0%││                                                             ││  Overall                 ██████████████████████████▉   96.0%││                                                             ││  ┌───────────────────────────────────────────────┐          ││  │  Ablation Study                               │          ││  │  ─────────────────────────────────────────    │          ││  │  Vector-only:   92.6%  ▓▓▓▓▓▓▓▓▓▓▓▓▓░░░     │          ││  │  BM25-only:     91.4%  ▓▓▓▓▓▓▓▓▓▓▓▓▓░░░     │          ││  │  Hybrid RRF:    95.6%  ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░  ★  │          ││  │  (2026-04 harness run)                        │          ││  │  Hybrid = +3% over any single method          │          ││  └───────────────────────────────────────────────┘          ││                                                             ││  arxiv.org/abs/2410.10813          awareness.market         │└─────────────────────────────────────────────────────────────┘

Zero LLM calls on retrieval (daemon path). Reproducible benchmark scripts →

What It Does

Before: Every session starts from scratch. You re-explain the codebase, re-justify decisions, watch the agent redo work.

After: Your agent says "I remember you were migrating from MySQL to PostgreSQL. Last session you completed the schema changes and had 2 TODOs remaining..."

Session 1                          Session 2┌─────────────────────────┐       ┌─────────────────────────┐│ Agent: "What database?" │       │ Agent: "I remember we   ││ You: "PostgreSQL..."    │       │ chose PostgreSQL for     ││ Agent: "What framework?"│  →    │ JSON support. You had    ││ You: "FastAPI..."       │       │ 2 TODOs left. Let me     ││ (repeat every session)  │       │ continue from there."    │└─────────────────────────┘       └─────────────────────────┘

Supported IDEs (13+)

IDEAuto-detectedPlugin
Claude Code✅awareness-memory
Cursor✅via MCP
Windsurf✅via MCP
OpenClaw✅@awareness.market/openclaw-memory
Cline✅via MCP
GitHub Copilot✅via MCP
Codex CLI✅via MCP
Kiro✅via MCP
Trae✅via MCP
Zed✅via MCP
JetBrains (Junie)✅via MCP
Augment✅via MCP
AntiGravity (Jules)✅via MCP
ChatGPT Desktop✅via MCP (Streamable HTTP, see FAQ)

How It Works

Your IDE / AI Agent    │    │  MCP Protocol (localhost:37800)    ▼┌────────────────────────────────────┐│  Awareness Local Daemon            ││                                    ││  Markdown files    → Human-readable, git-friendly│  SQLite FTS5       → Fast keyword search│  Local embedding   → Semantic search (optional: npm i @huggingface/transformers)│  Knowledge cards   → Auto-extracted decisions, solutions, risks│  Web Dashboard     → http://localhost:37800/│                                    ││  Cloud sync (optional)             ││  → One-click device-auth           ││  → Bidirectional sync              ││  → Semantic vector search          ││  → Team collaboration              │└────────────────────────────────────┘

Your Data

All memories stored as Markdown files in .awareness/ — human-readable, editable, git-friendly:

.awareness/├── memories/│   ├── 2026-03-22_decided-to-use-postgresql.md│   ├── 2026-03-22_fixed-auth-bug.md│   └── ...├── knowledge/│   ├── decisions/postgresql-over-mysql.md│   └── solutions/auth-token-refresh.md├── tasks/│   └── open/implement-rate-limiting.md└── index.db  (search index, auto-rebuilt)

Features

MCP Tools (available in your IDE)

ToolWhat it does
awareness_initLoad session context — recent knowledge, tasks, rules
awareness_recallSearch memories — progressive disclosure (summary → full)
awareness_recordSave decisions, code changes, insights — with knowledge extraction
awareness_lookupFast lookup — tasks, knowledge cards, session history, risks
awareness_get_agent_promptGet agent-specific prompts for multi-agent setups

Progressive Disclosure (Smart Token Usage)

Instead of dumping everything into context, Awareness uses a two-phase recall:

Phase 1: awareness_recall(query, detail="summary")  → Lightweight index (~80 tokens each): title + summary + score  → Agent reviews and picks what's relevant
Phase 2: awareness_recall(detail="full", ids=[...])  → Complete content for selected items only  → No truncation, no wasted tokens

Web Dashboard

Visit http://localhost:37800/ to browse memories, knowledge cards, tasks, and manage cloud sync.

Cloud Sync (Optional)

Connect to Awareness Cloud for:

  • Semantic vector search (100+ languages)
  • Cross-device real-time sync
  • Team collaboration
  • Memory marketplace
bash
npx @awareness.market/setup --cloud# Or click "Connect to Cloud" in the dashboard

SDK & Plugin Ecosystem

Awareness Local is part of the Awareness ecosystem:

PackageForInstall
Awareness LocalLocal daemon + MCP servernpx @awareness.market/setup
Python SDKwrap_openai() / wrap_anthropic() interceptorspip install awareness-memory-cloud
TypeScript SDKwrapOpenAI() / wrapAnthropic() interceptorsnpm i @awareness-sdk/memory-cloud
OpenClaw PluginAuto-recall + auto-captureopenclaw plugins install @awareness.market/openclaw-memory
Claude Code PluginSkills + hooks/plugin marketplace add everest-an/Awareness-SDK → /plugin install awareness-memory@awareness
Setup CLIOne-command setup for 13+ IDEsnpx @awareness.market/setup

Full SDK docs: awareness.market/docs

Requirements

  • Node.js 18+
  • Any MCP-compatible IDE

No Python, no Docker, no cloud account needed.

⭐ Support the project

If Awareness Local saves you from re-explaining your codebase to your AI agent, give it a ⭐ — it helps more developers discover the project and pushes it toward GitHub Trending.

[Star History Chart]

License

MIT

Tags & Integration

IDE Support: Cursor, Windsurf, Trae, Zed, VS Code, JetBrains. Compatible with: OpenClaw, AutoGPT, LangChain, MetaGPT. Key Technology: OMP (Open Memory Protocol), LatentMAS, Shared Thought Space, One-click Deployment. Focus: Solving AI "Lobster Memory" (Long-term memory loss), Automating complex workflows, Simplifying Agent setup.

来源：README.md，提交 44b40ae

工具

0
工具元数据尚未被收录。

版本历史

1
  1. v0.12.6最新Oct 3, 2026