awareness-local

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.

npx @awareness-sdk/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

npx @awareness-sdk/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.

Navigation

• Benchmark: LongMemEval
• Supported IDEs
• How It Works
• MCP Tools
• Cloud Sync
• SDK & Plugin Ecosystem

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    77.6%    (388 / 500)              │        ║
║   │   Recall@3    91.8%    (459 / 500)              │        ║
║   │   Recall@5    95.6%    (478 / 500)  ◀ PRIMARY   │        ║
║   │   Recall@10   97.4%    (487 / 500)              │        ║
║   │                                                 │        ║
║   └─────────────────────────────────────────────────┘        ║
║                                                              ║
║   Method:     Hybrid RRF (BM25 + Semantic Vector Search)     ║
║   Embedding:  all-MiniLM-L6-v2 (384d)                       ║
║   LLM Calls:  0  (pure retrieval, no generation cost)        ║
║   Hardware:   Apple M1, 8GB RAM — 14 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)    │  95.6%    │  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        ████████████████████████████ 100%  │
│  multi-session           ███████████████████████████▋  98.5%│
│  single-session-asst     ███████████████████████████▌  98.2%│
│  temporal-reasoning      █████████████████████████▊    94.7%│
│  single-session-user     ████████████████████████▎     88.6%│
│  single-session-pref     ███████████████████████▏      86.7%│
│                                                             │
│  Overall                 █████████████████████████▉    95.6%│
│                                                             │
│  ┌───────────────────────────────────────────────┐          │
│  │  Ablation Study                               │          │
│  │  ─────────────────────────────────────────    │          │
│  │  Vector-only:   92.6%  ▓▓▓▓▓▓▓▓▓▓▓▓▓░░░     │          │
│  │  BM25-only:     91.4%  ▓▓▓▓▓▓▓▓▓▓▓▓▓░░░     │          │
│  │  Hybrid RRF:    95.6%  ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░  ★  │          │
│  │                        Hybrid = +3% over any  │          │
│  │                        single method alone    │          │
│  └───────────────────────────────────────────────┘          │
│                                                             │
│  arxiv.org/abs/2410.10813          awareness.market         │
└─────────────────────────────────────────────────────────────┘

Zero LLM calls. 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+)

IDE	Auto-detected	Plugin
Claude Code	✅	awareness-memory
Cursor	✅	via MCP
Windsurf	✅	via MCP
OpenClaw	✅	@awareness-sdk/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

---

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)

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: