Awareness Local README | AllMCPs

Awareness Local

Languages: English | 简体中文

Awareness Local — Persistent Memory for AI Coding Agents

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.

Terminal

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

Terminal

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).

Benchmark: LongMemEval (ICLR 2025)

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

Code

╔══════════════════════════════════════════════════════════════╗
║                                                              ║
║   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               ║
║                                                              ║
╚══════════════════════════════════════════════════════════════╝

Code

┌─────────────────────────────────────────────────────────────┐
│          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.         │
└─────────────────────────────────────────────────────────────┘

Code

┌─────────────────────────────────────────────────────────────┐
│     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..."

Code

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+)

IDE	Auto-detected	Plugin
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

Code

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:

Code

.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)

Tool	What it does
`awareness_init`	Load session context — recent knowledge, tasks, rules
`awareness_recall`	Search memories — progressive disclosure (summary → full)
`awareness_record`	Save decisions, code changes, insights — with knowledge extraction
`awareness_lookup`	Fast lookup — tasks, knowledge cards, session history, risks
`awareness_get_agent_prompt`	Get agent-specific prompts for multi-agent setups

Progressive Disclosure (Smart Token Usage)

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

Code

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

Terminal

npx @awareness.market/setup --cloud
# Or click "Connect to Cloud" in the dashboard

SDK & Plugin Ecosystem

Awareness Local is part of the Awareness ecosystem:

Package	For	Install
Awareness Local	Local daemon + MCP server	`npx @awareness.market/setup`
Python SDK	`wrap_openai()` / `wrap_anthropic()` interceptors	`pip install awareness-memory-cloud`
TypeScript SDK	`wrapOpenAI()` / `wrapAnthropic()` interceptors	`npm i @awareness-sdk/memory-cloud`
OpenClaw Plugin	Auto-recall + auto-capture	`openclaw plugins install @awareness.market/openclaw-memory`
Claude Code Plugin	Skills + hooks	`/plugin marketplace add everest-an/Awareness-SDK` → `/plugin install awareness-memory@awareness`
Setup CLI	One-command setup for 13+ IDEs	`npx @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.

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.