Give your AI assistant memory, skills, and autonomy.
A shareable config that turns Claude Code into an AI that remembers you,
connects to your tools, and runs workflows while you sleep.
Most AI assistants forget you the moment the conversation ends. OpenClaw doesn't.
This repo is the shared configuration layer for OpenClaw — a personal AI built on Claude Code that maintains persistent memory, integrates with real-world tools, and runs autonomous workflows on a schedule. Everything is markdown and Python scripts. No frameworks, no databases, no lock-in.
- Memory that persists — Three-tier architecture: always-loaded essentials, daily context files, and deep knowledge with semantic search
- 11 skills — Web research, meeting transcripts, CRM, phone system, task management, and more — each a standalone Python script with zero setup
- 4 autonomous workflows — Agents that triage your inbox, manage tasks, prep your calendar, and organize contacts — learning your preferences over time
- Templates for identity — Define your AI's personality, your profile, and how it should operate
- DevOps included — Hourly health checks, fleet management across machines, automated backups
Prerequisites: Claude Code running on your machine. That's it — no other dependencies.
Install: Open Claude Code and tell it:
Set up openclaw-config from https://github.com/TechNickAI/openclaw-config
The openclaw skill walks you through setup — cloning the repo, copying templates,
creating memory folders, and configuring optional features like semantic search.
Update later:
Update my openclaw config
openclaw-config/
├── templates/ # Identity & operating instructions
│ ├── AGENTS.md # How the AI should think and act
│ ├── SOUL.md # Personality definition (templated)
│ ├── USER.md # Your profile — who you are, how you work
│ ├── MEMORY.md # Curated essentials, always in context
│ ├── BOOT.md # Startup routine — what to check on launch
│ ├── HEARTBEAT.md # Periodic checks (inbox, tasks, health)
│ ├── TOOLS.md # Machine-specific environment config
│ └── IDENTITY.md # Quick reference card
│
├── skills/ # Standalone UV scripts — no install needed
│ ├── parallel/ # Web research & content extraction
│ ├── quo/ # Business phone — calls, texts, contacts
│ ├── fireflies/ # Meeting transcript search
│ ├── limitless/ # Pendant lifelog search
│ ├── asana/ # Task & project management
│ ├── followupboss/ # Real estate CRM
│ ├── librarian/ # Knowledge base maintenance
│ ├── create-great-prompts/ # Prompt engineering guide
│ ├── smart-delegation/ # Route work to the right model
│ ├── workflow-builder/ # Design new autonomous workflows
│ └── openclaw/ # Self-management & updates
│
├── workflows/ # Autonomous agents with state & learning
│ ├── email-steward/ # Inbox triage — archive noise, surface what matters
│ ├── task-steward/ # Classify, create, execute, and QA tasks
│ ├── calendar-steward/ # Daily briefing with travel & meeting prep
│ └── contact-steward/ # Detect and organize unknown contacts
│
├── memory/ # Example memory directory structure
│ ├── people/ # One file per person
│ ├── projects/ # One file per project
│ ├── topics/ # Domain expertise & preferences
│ └── decisions/ # Important decisions with reasoning
│
└── devops/ # Health checks & fleet management
Each skill is a standalone UV script — Python with inline dependencies, no project-level setup. Run directly, version independently.
| Skill | What it does | Version |
|---|---|---|
| parallel | Web search & content extraction via Parallel.ai | 0.2.0 |
| quo | Business phone — calls, texts, voicemails, contacts, SMS | 0.6.0 |
| fireflies | Search meeting transcripts & action items | 0.2.0 |
| limitless | Query Pendant lifelogs & conversations | 0.2.0 |
| asana | Task & project management via MCP | 0.1.0 |
| followupboss | Real estate CRM — contacts, deals, pipeline | 0.1.0 |
| librarian | Curate and maintain the knowledge base | 0.2.0 |
| create-great-prompts | Prompt engineering for LLM agents | 2.0.0 |
| smart-delegation | Route work to Opus, Grok, or handle directly | 0.1.0 |
| workflow-builder | Design new autonomous workflows | 0.1.0 |
| openclaw | Install, update, and health-check the config | 0.2.2 |
Workflows are autonomous agents that run on a schedule. Unlike skills (tools you invoke), workflows maintain state, learn your preferences, and manage themselves.
| Workflow | What it does | Version |
|---|---|---|
| email-steward | Triage inbox — archive noise, label, alert on important | 0.2.0 |
| task-steward | Classify work, create tasks, spawn sub-agents, QA results | 0.1.0 |
| calendar-steward | Daily briefing — travel time, meeting prep, conflict detection | 0.1.0 |
| contact-steward | Detect unknown contacts across platforms, classify & organize | 0.1.0 |
Each workflow maintains its own state:
AGENT.md— The algorithm (updates when you update openclaw-config)rules.md— Your preferences (never overwritten)agent_notes.md— Patterns it learns over timelogs/— Execution history
Most AI memory is "dump everything into a vector database." OpenClaw uses deliberate, structured memory with clear tiers:
Tier 1 — Always loaded. MEMORY.md stays in context every conversation. Curated to
~100 lines of what matters most.
Tier 2 — Daily context. memory/YYYY-MM-DD.md files. Today and yesterday load
automatically. Raw observations, not curated.
Tier 3 — Deep knowledge. memory/people/, projects/, topics/, decisions/.
Searched via vector embeddings (LM Studio local or OpenAI). Retrieved when relevant, not
loaded by default.
The librarian skill promotes durable knowledge upward — daily observations become structured knowledge, structured knowledge gets summarized into MEMORY.md.
What gets remembered is filtered through four criteria:
| Criterion | Question |
|---|---|
| Durability | Will this matter in 30+ days? |
| Uniqueness | Is this new or already captured? |
| Retrievability | Will I want to recall this later? |
| Authority | Is this reliable? |
- Files over databases — Markdown in git beats any proprietary store. Readable, diffable, portable.
- Self-contained skills — No shared dependencies, no coordination overhead. Each
skill carries its own
pip installinline. - Workflows that learn — Agents should get better at their job over time, not just repeat the same script.
- Two-way door decisions — Act freely on reversible decisions. Pause and confirm on irreversible ones.
- Prose over config — Language models reason better in natural language than in JSON schemas.
uv run --with pytest pytest tests/ -vIntegration tests auto-skip when API keys aren't set.
PRs welcome. Keep templates generic (no personal content). Each skill should remain self-contained with its own inline dependencies.
MIT
Built by TechNickAI
Your AI deserves to remember you.