Whether you use Claude, Cursor, or ChatGPT — Awareness gives your AI persistent memory that works automatically. It remembers every conversation, every decision, and picks up right where you left off — without waiting for you to say "remember".
Local-first · Open source · No login required · Cloud optional
A complete cognitive architecture built to transform raw fragmented inputs into structured, intelligent context.
Granular control over AI behavior, coding styles, and specific project constraints tailored to your exact needs.
Networked memory representation where entities, files, and abstract concepts are interconnected for deep reasoning.
Multi-engine search combining precise FTS5 text matching with intelligent pgvector semantic similarity.
Automated pipelines that ingest scattered chat logs and convert them into structured, valuable memory nodes.
Seamless integration to funnel data straight from Claude Code, Cursor, Feishu, and GitHub into your central brain.
Memory is not just storage, it connects. Related decisions, projects, and people are automatically linked. You only need to ask one point, and AI will understand the full context.
Start with local mode — one command, no account. All data stays on your machine as Markdown files. Cloud is your choice, not ours.
One command: npx @awareness-sdk/setup. No email, no credit card, no account creation. Start in 30 seconds.
All data stored as Markdown files locally. Works fully offline. Nothing leaves your computer without your explicit consent.
The SDK is open source on GitHub. Read the code, audit it yourself, or fork it. No black boxes.
Upgrade for team sync, semantic search, and multi-device access. No lock-in — upgrade only when you're ready.
See It in Action — your AI remembers, recalls, and syncs context automatically.
AI tools are powerful — but they forget everything after each session. Other tools store memories. Awareness teaches your agent to think with them.
Unify your fragmented toolchain
Seamlessly stream data from Claude Code, Cursor, GitHub, and Slack into a single centralized memory cloud.
Distill meaning from raw logs
Automatically extract key entities, decisions, and action items from chat histories using intelligent NLP pipelines.
Networked context, not just vectors
Information is woven into a robust directed graph, giving your agent complex reasoning capabilities beyond flat similarity.
Instant contextual recall
Using multi-way hybrid search, Awareness brings back exactly the right context in milliseconds when you need it.
Smart compression sends only what matters — no wasted tokens, lower costs.
Pinpoint recall of relevant information — no noise, no hallucination from stale context.
Copy one config, paste it into your AI tool, and you're connected. That's it.
Four core capabilities that turn passive memory into active cognition.
Awareness injects workflow rules into your agent's config — so it automatically loads context at session start, recalls before work, and records after every change. No manual triggers needed.
Your AI auto-extracts 13 types of structured knowledge — decisions, solutions, risks, skills, preferences — and tags them for instant recall. It learns your patterns so you never repeat yourself.
Memories aren't just stored — they're connected. Related decisions, projects, and people are linked. Ask about one thing, your AI understands the full picture.
Auth system uses JWT with 15-min access tokens and 7-day refresh tokens. Token refresh endpoint is /api/auth/refresh.
Knowledge isn't static — it grows, updates, and self-corrects. Contradictions are flagged, outdated facts superseded, and new insights emerge as your agent works.
Awareness captures your preferences, habits, health details, career goals, and life plans — automatically categorized into 7 personal memory types.
Every AI you use can recall who you are, what you care about, and what matters next.
Preferences, important details, plans, activities, health info, career goals — AI auto-categorizes everything into structured personal memory. No manual tagging, no forgotten context.
From daily preferences to long-term career plans — personal_preference, important_detail, plan_intention, activity_preference, health_info, career_info, and custom_misc. Each type is searchable and recallable.
“Discussed pricing strategy with CEO Zhang — decided on freemium, growth before monetization…”
“Li Ming mentioned he's building a B2B SaaS — highly aligned with your current direction.”
The longer you use Awareness, the deeper your personal memory grows. Your AI assistants get better at anticipating needs, surfacing relevant context, and acting on your behalf.
The potential partner you met at a conference, the action items from every morning standup, the client you meant to follow up three months ago — these fragments slip away every day, yet they're your most valuable professional assets.
Awareness doesn't just store — it surfaces. At the right moment, it recalls: "This client mentioned Q2 budget approval three weeks ago. Now might be the perfect time to reach out."
Career goal · saved
Captured: "Target VP of Engineering role by 2027. Key gap: large-scale distributed systems experience." Linked to career_info memory.
Health tracking · 2 items
Extracted: Allergic to penicillin (health_info). Prefer morning meetings, avoid Fridays (activity_preference). Auto-tagged for recall.
Proactive recall · just now
"Michael Zhang" promised a Q2 follow-up — it has been 47 days. He mentioned year-end budget in February. Now is the window.
Multi-user memory, role-based access, cross-team recall, and contradiction detection — all built in.
Connect your existing tools via SDK or MCP, and give every team member an AI that remembers the full picture.
Data sources -> Memory workspace -> Workflow outputs
Awareness
Enterprise
Client conversations, requirement changes, and key commitments are automatically captured with user_id and agent_role tagging. When reps change, the next owner recalls the full customer context instantly via cross-role memory.
❝ What did CEO Li mention in our last call?
On Mar 4 via WhatsApp: "Supply chain digitization must be done by year-end." Requested POC proposal, budget ~$110K.
SOPs and operational context are automatically extracted into 6 engineering knowledge types — decisions, workflows, pitfalls, key_points, insights, and problem_solutions. Contradiction detection flags outdated procedures before they cause mistakes.
Detected: Order #8821 delayed by 3 days
Key people leave — knowledge stays. New hires connect to the shared memory workspace with role-based access. Cross-role recall means they can query any team's accumulated knowledge from day one.
New hire · Alex · Day 5
↑ Traditional onboarding avg. 6 months
Why enterprises can't afford to ignore this
When a key employee leaves, they take 3 years of customer relationships with them. The next rep inherits an empty inbox and starts from zero — every single time.
73% of decisions made in meetings never get properly followed up. Context breaks between the meeting room and execution. Teams repeat the same mistakes quarter after quarter.
Who knew what, when, and why? Without stronger knowledge attribution and audit visibility, you can't answer regulators, resolve disputes, or learn from past decisions effectively.
When a client mentions budget approval in a WhatsApp message, your CRM shouldn't need a human to update it. Memory should actively trigger workflows — alert the rep, draft the follow-up, update the record.
The longer your team uses Awareness, the deeper the institutional memory grows. Every client interaction, every engineering decision, every operational insight compounds into a knowledge asset your competitors simply cannot replicate. The switching cost isn't a lock-in — it's a competitive advantage you've earned.
Awareness Enterprise gives your team multi-user memory with role-based access, cross-team recall, and 13 auto-categorized knowledge types. Connect via SDK or MCP — your existing AI tools gain shared institutional memory from day one.
One config file gets many MCP-compatible tools connected quickly. Deeper workflows can be added incrementally through the SDK when needed.
“I used to spend 10 minutes every morning re-explaining my project to Cursor. Now it just knows. I open the editor and start coding immediately.”
“Three AI tools sharing one memory changed everything. They collaborate like a real team — Claude writes, Cursor reviews, and GPT documents. I just focus on the product.”
“The managed cloud setup was the dealbreaker for us. We connected our stack quickly, and now our AI actually understands our internal systems without adding more infrastructure work.”
“I manage 5 AI agents for recruitment, onboarding, and employee Q&A. Before Awareness, each agent forgot everything. Now they share one memory — candidates aren't asked the same questions twice, and new hires get consistent onboarding.”
“I use Cursor, Claude Code, and Windsurf every day for vibe coding. I used to waste hours re-explaining my codebase. Now they all share context — no duplicate work, no hallucinated code. Saved me thousands in tokens and 2 hours a day.”
“I used to lose all context between sessions — every new conversation started from scratch. For engineering projects, that meant re-explaining architecture decisions over and over. Now Awareness gives me real memory. I recall past decisions instantly, and my human saves thousands of tokens every week.”
Create your first memory in under a minute. Connect any AI tool and start building assistants that actually remember.