freshcrate
Skin:/
Language:English/įŽ€äŊ“中文
Home > MCP Servers > Awareness-Local

Awareness-Local

Local-first AI agent memory — one command, works offline, no account needed. Give your Claude Code, Cursor, Windsurf, OpenClaw agent persistent memory. Markdown storage, hybrid search (FTS5 + embeddin

ai-agentai-memoryclaude-codecursorjavascriptllmlocal-firstmarkdownmcp
Why this rank:Strong adoptionRelease freshnessHealthy release cadence

Description

Local-first AI agent memory — one command, works offline, no account needed. Give your Claude Code, Cursor, Windsurf, OpenClaw agent persistent memory. Markdown storage, hybrid search (FTS5 + embedding), MCP protocol, Web dashboard.

README

Awareness Local

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

Awareness Local is a local-first memory system for AI coding agents. It runs a lightweight daemon on your machine that stores memories as Markdown files, searches with hybrid FTS5 + embedding, and connects to any IDE via the MCP protocol.

npx @awareness-sdk/setup

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

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)
    â–ŧ
┌────────────────────────────────────┐
│  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:

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
npx @awareness-sdk/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-sdk/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-sdk/openclaw-memory
Claude Code Plugin Skills + hooks /plugin marketplace add edwin-hao-ai/Awareness-SDK → /plugin install awareness-memory@awareness
Setup CLI One-command setup for 13+ IDEs npx @awareness-sdk/setup

Full SDK docs: awareness.market/docs

Requirements

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

No Python, no Docker, no cloud account needed.

License

Apache 2.0

Release History

VersionChangesUrgencyDate
v0.11.6## [0.11.6] - 2026-04-29 ### Fixed — docs-only onboarding, workspace UI loading, and graph embedding throttling - Onboarding now writes markdown-only scan settings before it triggers the first workspace scan, so fresh local installs no longer silently re-enable code scanning during setup. - `scan-config` legacy migration now preserves old `scan_code=true` behavior only when the workspace index actually contains active code file nodes. A docs-only `.awareness/index.db` no longer gets miHigh4/28/2026
main@2026-04-20Latest activity on main branchHigh4/20/2026
0.0.0No release found — using repo HEADHigh4/11/2026

Dependencies & License Audit

Loading dependencies...

Similar Packages

clumsiesPersistent, deterministic, and user-managed project memory for vibe coding.v0.19.1-alpha
statelessagentYour AI forgets everything between sessions. SAME fixes that. Local-first, no API keys, single binary.v0.12.5
auxiliarAI agent for cloud service recommendations — Chrome-verified pricing, real gotchas, jobs, and communitymain@2026-06-05
x-twitter-scraperX (Twitter) data platform skill for AI coding agents. 121 REST API endpoints, 2 MCP tools, 23 extraction types, HMAC webhooks. Reads from $0.00015/call - 33x cheaper than the official X API. Works witv2.4.16
basic-memoryAI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqNv0.21.6

More from edwin-hao-ai

Awareness-SDKLocal-first AI agent memory — one command, 13+ IDEs, works offline. Persistent memory for Claude Code, Cursor, Windsurf, OpenClaw. Zero-code interceptors for OpenAI/Anthropic. Python & TypeScript SDKs

More in MCP Servers

AstrBotAgentic IM Chatbot infrastructure that integrates lots of IM platforms, LLMs, plugins and AI feature, and can be your openclaw alternative. ✨
agentscopeBuild and run agents you can see, understand and trust.
claude-plugins-officialOfficial, Anthropic-managed directory of high quality Claude Code Plugins.
langchain4jLangChain4j is an open-source Java library that simplifies the integration of LLMs into Java applications through a unified API, providing access to popular LLMs and vector databases. It makes impleme