Data
Plugin
awareness-local
Languages: English | 简体中文 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.
Plugin Signal51/100Fair
maintained54
capable14
documented100
adopted50
Stats
216
Stars
3
Forks
Maintained
Maintenance
JavaScript
Language
MIT
License
3mo ago
Last commit
4mo ago
Created
Repo: edwin-hao-ai/Awareness-Local
What's inside
README
1Awareness 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:
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
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.
File tree
614edwin-hao-ai/Awareness-LocalView on GitHub
.awareness/
.first-run-done
daemon.log
index.db
knowledge/
decisions/
2026-03-22_postgresql-over-mysql.md
2026-03-22_test-card.md
2026-03-28_从-pgvector-切换到-milvus.md
2026-03-28_选择-pgvector-替代-pinecone.md
2026-04-14_f-040-onboarding-模块解耦架构.md
2026-04-14_f-040-telemetry-架构.md
2026-04-14_step-3-first-recall-动态建议问题.md
2026-04-14_step-5-cloud-用-device-auth-而非-oauth.md
2026-04-14_后端-bm25-预筛选-tasksrisks-省-token.md
2026-04-14_后端-extraction-prompt-新增-existingrisks-上下文给-llm.md
2026-04-14_开源策略fsl许可证-三层洋葱模型-功能分层.md
2026-04-15_5-层测试金字塔提升为全局-mandatory.md
2026-04-15_awarenessclaw-桌面-onboarding-升级设计文档.md
2026-04-15_extraction-orchestratormjs-removed-as-dead-code.md
2026-04-15_f-041f-042-拆分ship-gate-基础设施-vs-backendfrontend-落地.md
2026-04-15_sdk-发布冻结直到-f-041-完成.md
2026-04-15_we-decided-to-return-extractioninstruction-from-lo.md
2026-04-15_we-decided-to-use-session-buffer-stop-hook-consoli.md
insights/
2026-03-28_prisma-db-push-会删除-memoryvectors-表.md
2026-03-28_中文交流英文代码.md
2026-04-04_lobster-is-optional-plugin-not-default.md
2026-04-04_lobster-yaml-verified-format.md
2026-04-10_usereffncurrent-防止-useeffect-无限循环.md
2026-04-11_daemon-有-workspaceswitch-api-但桌面端从未调用-历史问题.md
2026-04-11_electron-主进程调-node-http-模块而非-fetch-做-localhost-dae.md
2026-04-14_f-040-测试发现的-3-个真-bug-修复.md
2026-04-14_vm-沙箱测试-iife-浏览器模块的-helper-模式.md
2026-04-14_本地版太好用导致云端转化率极低.md
2026-04-15_l1-ship-gate-根脚本清单2026-04-15-实际存在.md
2026-04-15_pre-push-hook-会自动跑-l1.md
2026-04-15_verify-frontend-endpointsmjs-关键实现细节.md
solutions/
2026-04-10_vitest-jsdom-环境-fetch-挂起需要-mock.md
2026-04-14_awarenessclaw-spawn-openclaw-enoent-升级中断导致安装损坏.md
2026-04-14_awarenessclaw-聊天-internal-error-来自-qwen-api-服务端.md
2026-04-14_f-040-端点对齐踩坑.md
2026-04-14_request-sender-untrusted-metadata.md
2026-04-14_request-你能做什么.md
2026-04-14_request-你能做什么特别有趣的事情吗.md
2026-04-15_after-thorough-audit-of-the-record-chain-we-found-.md
workflows/
2026-03-28_后端部署标准流程.md
2026-04-10_awarenessclaw-memory-ui-从-6-tab-收敛为-5-tab-完成.md
2026-04-10_local-daemon-wiki-ui-全重写完成sidebarcontent-架构-8-api-.md
2026-04-11_awarenessclaw-桌面端-workspace-联动memory-ui-跟随聊天工作区切换.md
2026-04-14_awarenessclaw-v030-发布-友好错误提示-安装自动修复.md
2026-04-14_daemon-handlewebui-扩展为静态文件-serve.md
2026-04-14_handlewebui-安全加固url-decode-symlink-nul.md
2026-04-14_lifecycle-manager-hybrid-search-fts5-jaccard-rrf-f.md
2026-04-14_后端-riskperception-自动关闭补齐-与本地-daemon-对齐.md
2026-04-14_本地-daemon-task-自动关闭升级为-fts5-bm25.md
2026-04-15_e2e-装-playwright-的最佳实践避免下载新-chromium.md
2026-04-15_f-039-cloud-knowledge-graph-完成归档.md
2026-04-15_f-040-onboarding-and-telemetry-改名为-f-040.md
2026-04-15_f-040-v060-发布-双公开仓库同步完成.md
2026-04-15_f-040-完整测试矩阵48-单测-11-telemetry-15-e2e-0-回归.md
2026-04-15_f-041-phase-1-落地清单.md
2026-04-15_f-042-backend-chaos-最小骨架.md
2026-04-15_session-edit-summary-34-changes-across-23-files.md
memories/
2026-03-28_file-changed-usersedwinhaoawarenessdocsprdharness.md
2026-03-28_今天差点执行了-prisma-db-push幸好被提醒了.md
2026-03-28_团队决定用-postgresql-pgvector-而不是独立的-pinecone因为减少基础设施依.md
2026-03-28_每次部署后端都要按固定流程build-up-d-nginx-reload.md
2026-03-28_用户说所有推理和回复用中文代码内容用英文.md
2026-03-28_经过评估决定从-pgvector-切换到-milvus因为-pgvector-在大规模数据下性能不够.md
2026-04-04_completed-phase-2-of-task-center-workflow-system.md
2026-04-15_file-changed-usersedwinhaoawarenessdocsanalysiskar-1.md
2026-04-15_file-changed-usersedwinhaoawarenessdocsanalysiskar.md
2026-04-15_session-edit-summary-34-changes-across-23-files.md
2026-04-16_session-edit-summary-8-changes-across-6-files.md
perception-cache.json
scan-state.json
tasks/
open/
2026-03-22_set-up-pg-migration.md
telemetry-queue.json
.mcp.json
.stryker-tmp/
sandbox-PEBKNR/
.awareness/
.first-run-done
daemon.log
index.db
knowledge/
decisions/
2026-03-22_postgresql-over-mysql.md
2026-03-22_test-card.md
2026-03-28_从-pgvector-切换到-milvus.md
2026-03-28_选择-pgvector-替代-pinecone.md
2026-04-14_f-040-onboarding-模块解耦架构.md
2026-04-14_f-040-telemetry-架构.md
2026-04-14_step-3-first-recall-动态建议问题.md
2026-04-14_step-5-cloud-用-device-auth-而非-oauth.md
2026-04-14_后端-bm25-预筛选-tasksrisks-省-token.md
2026-04-14_后端-extraction-prompt-新增-existingrisks-上下文给-llm.md
2026-04-14_开源策略fsl许可证-三层洋葱模型-功能分层.md
2026-04-15_5-层测试金字塔提升为全局-mandatory.md
2026-04-15_awarenessclaw-桌面-onboarding-升级设计文档.md
2026-04-15_extraction-orchestratormjs-removed-as-dead-code.md
2026-04-15_f-041f-042-拆分ship-gate-基础设施-vs-backendfrontend-落地.md
2026-04-15_sdk-发布冻结直到-f-041-完成.md
2026-04-15_we-decided-to-return-extractioninstruction-from-lo.md
2026-04-15_we-decided-to-use-session-buffer-stop-hook-consoli.md
insights/
2026-03-28_prisma-db-push-会删除-memoryvectors-表.md
2026-03-28_中文交流英文代码.md
2026-04-04_lobster-is-optional-plugin-not-default.md
2026-04-04_lobster-yaml-verified-format.md
2026-04-10_usereffncurrent-防止-useeffect-无限循环.md
2026-04-11_daemon-有-workspaceswitch-api-但桌面端从未调用-历史问题.md
2026-04-11_electron-主进程调-node-http-模块而非-fetch-做-localhost-dae.md
2026-04-14_f-040-测试发现的-3-个真-bug-修复.md
2026-04-14_vm-沙箱测试-iife-浏览器模块的-helper-模式.md
2026-04-14_本地版太好用导致云端转化率极低.md
2026-04-15_l1-ship-gate-根脚本清单2026-04-15-实际存在.md
2026-04-15_pre-push-hook-会自动跑-l1.md
2026-04-15_verify-frontend-endpointsmjs-关键实现细节.md
solutions/
2026-04-10_vitest-jsdom-环境-fetch-挂起需要-mock.md
2026-04-14_awarenessclaw-spawn-openclaw-enoent-升级中断导致安装损坏.md
2026-04-14_awarenessclaw-聊天-internal-error-来自-qwen-api-服务端.md
2026-04-14_f-040-端点对齐踩坑.md
2026-04-14_request-sender-untrusted-metadata.md
2026-04-14_request-你能做什么.md
2026-04-14_request-你能做什么特别有趣的事情吗.md
2026-04-15_after-thorough-audit-of-the-record-chain-we-found-.md
workflows/
2026-03-28_后端部署标准流程.md
2026-04-10_awarenessclaw-memory-ui-从-6-tab-收敛为-5-tab-完成.md
2026-04-10_local-daemon-wiki-ui-全重写完成sidebarcontent-架构-8-api-.md
2026-04-11_awarenessclaw-桌面端-workspace-联动memory-ui-跟随聊天工作区切换.md
2026-04-14_awarenessclaw-v030-发布-友好错误提示-安装自动修复.md
2026-04-14_daemon-handlewebui-扩展为静态文件-serve.md
2026-04-14_handlewebui-安全加固url-decode-symlink-nul.md
2026-04-14_lifecycle-manager-hybrid-search-fts5-jaccard-rrf-f.md
2026-04-14_后端-riskperception-自动关闭补齐-与本地-daemon-对齐.md
2026-04-14_本地-daemon-task-自动关闭升级为-fts5-bm25.md
2026-04-15_e2e-装-playwright-的最佳实践避免下载新-chromium.md
2026-04-15_f-039-cloud-knowledge-graph-完成归档.md
2026-04-15_f-040-onboarding-and-telemetry-改名为-f-040.md
2026-04-15_f-040-v060-发布-双公开仓库同步完成.md
2026-04-15_f-040-完整测试矩阵48-单测-11-telemetry-15-e2e-0-回归.md
2026-04-15_f-041-phase-1-落地清单.md
2026-04-15_f-042-backend-chaos-最小骨架.md
2026-04-15_session-edit-summary-34-changes-across-23-files.md
memories/
2026-03-28_file-changed-usersedwinhaoawarenessdocsprdharness.md
2026-03-28_今天差点执行了-prisma-db-push幸好被提醒了.md
2026-03-28_团队决定用-postgresql-pgvector-而不是独立的-pinecone因为减少基础设施依.md
2026-03-28_每次部署后端都要按固定流程build-up-d-nginx-reload.md
2026-03-28_用户说所有推理和回复用中文代码内容用英文.md
2026-03-28_经过评估决定从-pgvector-切换到-milvus因为-pgvector-在大规模数据下性能不够.md
2026-04-04_completed-phase-2-of-task-center-workflow-system.md
2026-04-15_file-changed-usersedwinhaoawarenessdocsanalysiskar-1.md
2026-04-15_file-changed-usersedwinhaoawarenessdocsanalysiskar.md
2026-04-15_session-edit-summary-34-changes-across-23-files.md
2026-04-16_session-edit-summary-8-changes-across-6-files.md
perception-cache.json
scan-state.json
tasks/
open/
2026-03-22_set-up-pg-migration.md
telemetry-queue.json
.mcp.json
awareness-spec.json
bin/
awareness-local.mjs
cli.cjs
CHANGELOG.md
node_modules
package-lock.json
package.json
playwright.config.mjs
README.md
scripts/
benchmark-scan-10k.mjs
src/
api.mjs
benchmark/
benchmark-metrics.mjs
benchmark-reporter.mjs
benchmark-runner.mjs
perception-benchmark.mjs
recall-eval.mjs
systems.mjs
core/
cloud-sync.mjs
config.mjs
context-budgeter.mjs
doc-converter.mjs
embedder.mjs
gitignore-parser.mjs
guard-detector.mjs
index.mjs
indexer.mjs
knowledge-extractor.mjs
lang-detect.mjs
lifecycle-manager.mjs
link-discovery.mjs
memory-store.mjs
noise-filter.mjs
parsers/
generic.mjs
go.mjs
index.mjs
javascript.mjs
markdown.mjs
python.mjs
rust.mjs
query-planner.mjs
reranker.mjs
retrieval-backends/
base-backend.mjs
builtin-backend.mjs
qmd-backend.mjs
scan-config.mjs
scan-defaults.mjs
scan-state.mjs
search.mjs
skill-md-formatter.mjs
sync/
sync-conflict.mjs
sync-handshake.mjs
sync-pull.mjs
sync-push.mjs
sync-sse.mjs
sync-state.mjs
sync-conflict.mjs
sync-handshake.mjs
sync-http.mjs
sync-pull-cards.mjs
sync-push-optimistic.mjs
telemetry.mjs
wiki-generator.mjs
workspace-scanner.mjs
daemon/
daemon.mjs
api-handlers.mjs
cloud-http.mjs
constants.mjs
embedding-helpers.mjs
extraction-instruction.mjs
file-watcher.mjs
graph-embedder.mjs
helpers.mjs
http-handlers.mjs
loaders.mjs
mcp-contract.mjs
mcp-handlers.mjs
mcp-http.mjs
scan-api-handlers.mjs
telemetry-api-handlers.mjs
tool-bridge.mjs
harness-builder.mjs
mcp-server.mjs
mcp-stdio.mjs
spec/
awareness-spec.json
tools/
backfill-to-cloud.mjs
web/
index.html
onboarding/
device-auth-flow.js
i18n.js
index.js
privacy-settings.js
recall-suggestions.js
result-formatter.js
state.js
status-chip.js
steps.js
styles.css
stryker.project-dir.conf.mjs
test/
test-results/
.last-run.json
backfill-tool.test.mjs
benchmark-metrics.test.mjs
benchmark-reporter.test.mjs
benchmark-systems.test.mjs
cli-single-daemon.test.mjs
cloud-auth-handlers.test.mjs
cloud-http.test.mjs
cloud-sync-handshake.test.mjs
cloud-sync-pull.test.mjs
cloud-sync-push.test.mjs
context-budgeter.test.mjs
daemon-startup-dedup.test.mjs
doc-conversion-integration.test.mjs
doc-converter.test.mjs
e2e/
_helpers.mjs
onboarding-click-paths.spec.mjs
onboarding-device-auth.spec.mjs
onboarding-happy-path.spec.mjs
onboarding-locale.spec.mjs
onboarding-skip-and-persist.spec.mjs
privacy-settings.spec.mjs
status-chip.spec.mjs
user-journeys/
first-time-visit.spec.mjs
privacy-delete-double-confirm.spec.mjs
project-isolation.test.mjs
README.md
recall-returns-real-results.spec.mjs
skill-export-download.spec.mjs
status-chip-reflects-cloud.spec.mjs
switch-workspace.spec.mjs
ZERO_MOCK_POLICY.md
f031-alignment.test.mjs
f038-integration.test.mjs
gitignore-parser.test.mjs
graph-embedder.test.mjs
guard-detector.test.mjs
helpers/
onboarding-env.mjs
knowledge-extractor.test.mjs
lang-detect.test.mjs
lifecycle-manager.test.mjs
link-discovery.test.mjs
mcp-contract.test.mjs
mcp-handlers.test.mjs
mcp-http.test.mjs
memory-store-compat.test.mjs
noise-filter.test.mjs
onboarding-i18n.test.mjs
onboarding-recall-suggestions.test.mjs
onboarding-result-formatter.test.mjs
onboarding-state.test.mjs
onboarding-xss.test.mjs
parsers-go-rust.test.mjs
parsers-integration.test.mjs
parsers-javascript.test.mjs
parsers-markdown-generic.test.mjs
parsers-python.test.mjs
perception-benchmark.test.mjs
perception-lifecycle.test.mjs
query-planner.test.mjs
recall-context-comparison.test.mjs
recall-regressions.test.mjs
rerank-integration.test.mjs
reranker.test.mjs
retrieval-backends.test.mjs
scan-config.test.mjs
scan-defaults.test.mjs
scan-state.test.mjs
session-context-recall.test.mjs
skill-md-formatter.test.mjs
sync-handshake.test.mjs
sync-pull-cards-since.test.mjs
sync-push-documents.test.mjs
sync-push-optimistic-lock.test.mjs
telemetry-core-extra.test.mjs
telemetry-core.test.mjs
tool-bridge-telemetry.test.mjs
web-static-handler.test.mjs
wiki-api.test.mjs
wiki-generator.test.mjs
workspace-scanner.test.mjs
workspace-schema.test.mjs
assets/
branding/
awareness-wordmark-dark.svg
awareness-wordmark.svg
local-20s.gif
awareness-spec.json
bin/
awareness-local.mjs
cli.cjs
CHANGELOG.md
install-transformers.mjs
LICENSE
package-lock.json
package.json
playwright.config.mjs
README.md
README.zh-CN.md
reports/
mutation/
mutation.html
scripts/
benchmark-scan-10k.mjs
card-quality-report.mjs
card-retag-propose.mjs
clean-noise-cards.mjs
prepublish-gate.mjs
real-e2e-skill-extraction-eval.mjs
real-e2e-skill-simulate.mjs
real-llm-skill-eval-cli.mjs
real-llm-skill-eval.mjs
recall-accuracy-eval.mjs
... 277 moreFAQ
awareness-local is a Claude Code plugin with hand-picked skills for data work, indexed on Flowy. Install it with the command on its page. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is awareness-local?
- Languages: English | 简体中文 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.
- How do I install awareness-local?
- Run these in Claude Code: . Then prompt normally.
- Does awareness-local auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is awareness-local free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.