An OpenClaw fork for people who check their token spend before breakfast.
Every bar is a turn. Every color is a cost. The spike at 14:02? A 40K-token tool result nobody asked for.
The Tinker UI's token visualization was inspired by Mission Control (context anatomy dashboard) and ClawMetry (real-time agent observability). Both are excellent standalone tools for OpenClaw — we folded their ideas into a single embedded panel.
You ran Opus for 20 minutes. It felt productive. Then you checked the bill and discovered that "productive session" cost $23.
The worst part? $15 of that was context bloat — workspace files you forgot were injected, tool results the model never referenced, conversation history from six topics ago still sitting in the window.
You didn't overspend. You overloaded. And you had no way to see it happening.
Most people find out three days later. The observant ones set a budget alert after it's already too late. We found out when an €850 bill landed for a single month. Not a catastrophic failure — just the natural cost of running a capable AI agent at scale with zero visibility.
That bill was the motivation. TinkerClaw is the answer.
This fork moves fast, but it would move faster with more hands.
We value people who open PRs, not issues. Who read the code before asking questions. Who break things on purpose to understand how they work. If that's you, we want you in the inner circle — direct access to the roadmap, early testing of experimental features, and co-authorship on whatever we build next.
Start anywhere: fix a typo, improve a skill, add a test, or propose something wild. The bar is curiosity, not credentials.
→ Open a PR or start a discussion
No. A nightly cron syncs upstream automatically, detects conflicts, and restores fork patches after every merge. Hundreds of commits ahead of vanilla OpenClaw and zero behind.
When upstream pushes a breaking change, we know within hours — not weeks.
The Tinker UI is a command center embedded directly in OpenClaw. No separate install, no external service.
Chat interface with session switching, tool call inspection, and real-time streaming.
- Context treemap — drill into what fills your 200K context window, from categories down to individual messages and raw text. Each block is money. Drill down to the exact text inflating the cost.
- Response treemap — see exactly how much of each response is text, thinking, tool calls, or tool results. Identify waste patterns instantly.
- Timeline — stacked bars per turn, spot the one that blew the budget
- Overseer graph — catch stalled sub-agents before they burn money
- Cost dashboard — per-provider usage with Claude's 5-hour rate-limit countdown
Context treemap: every block is tokens you're paying for. |
Drill into a single category. These tool results cost $0.81 each. |
After pnpm build, visit http://localhost:18789/tinker/ · Dev: cd tinker-ui && pnpm dev
A normal AI solves problems. Ours learns from every problem it solves.
We call it fractal thinking because it operates in levels of depth — automatically, without being asked:
Level 0 — Solve the problem. The agent analyzes the issue, fixes it, verifies it works. Done in minutes.
Level 1 — Identify the pattern. Why did this problem exist? Because an automated nightly process had a binary restriction: either resolve everything or abort. No middle ground. The agent adds a third path: "do what you can, save what's safe, think more about the rest."
Level 2 — Correct the thinking flaw. The restriction existed because a previous incident triggered an overcorrection. The rule said "never touch anything" when it should have said "understand the intent before acting." The agent corrects the rule.
Level 3 — Encode the meta-rule. The agent writes a new principle into its own instructions: "When correcting an error, the restriction should be proportional to the risk — not a blanket prohibition."
All automatic. Nobody asked for any of that.
In 30 days, this process produced 14 autonomous improvements to the agent's own processes — without a single human prompt (CEREBELLUM paper).
Click the Tinker logo or type /new and your agent has already done the prep work. It reviews ALL your information sources (emails, calendars, messages, pending tasks), cross-references them, detects urgencies, and presents a briefing with what needs your attention and what it can resolve alone.
☀️ Morning Briefing — Tuesday, March 10
📅 Agenda
• 10:00 — Client meeting (Brazil) — spec review for new order
• 15:00 — Supplier call — follow-up on plant expansion budget
📰 Market (relevant updates)
• Raw material prices up 3.2% this week (third consecutive rise)
• Competitor announces new facility in Poland — potential supply chain impact
• New EU regulation on packaging recyclability — effective June
📧 Emails requiring response (3)
• 🔴 Client — Order #4521 modified, needs confirmation today
• 🟡 Supplier — Parts availability, awaiting response
• 🟢 Industry conference — Registration deadline March 20
🤖 I can handle right now:
1. Draft confirmation reply to the client
2. Prepare pricing comparison for this afternoon's call
3. Summarize the new EU regulation for your technical team
No manual setup. Every morning. Getting better each time.
Every night, while you sleep, the agent runs a chain of autonomous processes. The entire cycle costs ~€1/night.
| Cron | What it does |
|---|---|
| 🍷 Wind Down | Like a glass of wine with the diary — reviews what worked and what didn't, improves its own instructions |
| 😴 Memory Consolidation | Like REM sleep — turns raw daily logs into structured long-term memory. 49% context reduction (ENGRAM) |
| 🧹 Cleaning Lady | Controls disk usage, prunes stale context, keeps the workspace lean |
| 🔍 Auto-Evolution | Scouts AI news for improvements that can be applied directly to the system |
| 📰 Group Summary | Scans message groups, extracts what matters, discards noise |
| 🛒 Opportunity Hunter | Browses marketplaces for deals matching your interests — a personal shopper that never sleeps |
| 🤵 Butler | Remembers birthdays, suggests gifts, tracks appointments. If it's been too long since you sent flowers, it mentions it — diplomatically |
These are just the ones with personality. 15+ total crons, each with its own logic and self-improvement capability.
This isn't academic research — it's cost engineering. Every paper translates directly to fewer tokens consumed, better memory, and smarter decisions. The "Cumulative Saving" column shows the compounding effect — each layer builds on the previous ones.
| # | Paper | What it solves | Measured impact | Cumulative Saving |
|---|---|---|---|---|
| 1 | 📄 Total Recall | Event-navigated episodic memory — stores everything, retrieves what matters | 49% fewer tokens injected per turn, 94% recall over 847 compactions | ~49% |
| 2 | 📄 Instant Recall | Pre-computed concept index for O(1) retrieval — no more brute-force search | 8/10 benchmark score — fewer retrieval misses = fewer re-fetches | ~55% |
| 3 | 📄 Fractal Reasoning | Self-similar memory hierarchy — zoom in for detail, zoom out for patterns | Hierarchical storage that scales without ballooning context | ~60% |
| 4 | 📄 Identity Persistence | The agent remembers who it is and who you are across sessions | Eliminates re-explanation overhead — no more "as an AI, I don't have context" | ~65% |
| 5 | 📄 Sleep Consolidation | Nightly self-improvement — the agent rewrites its own prompts while you sleep | 14 autonomous improvements in 30 days, compounding efficiency gains | ~68% |
| 6 | 📄 Round Table | Multi-model adversarial debate — cognitive diversity as computational resource | 8pp accuracy gain on GPQA Diamond; cheaper models collaborating beat one expensive model guessing | ~72% |
| 7 | 📄 Humor Embeddings | Humor from embedding geometry — communication that's natural, not robotic | Fewer clarification round-trips, more efficient human-agent interaction | ~74% |
| 8 | 📄 Curiosity Motivation | Intrinsic motivation — the agent explores gaps before they become costly failures | Proactive knowledge acquisition reduces future retrieval failures | ~76% |
| 9 | 📄 Agent Security | Multi-layered security for autonomous agents — trust tiers, credential isolation | Defense-in-depth prevents lateral movement; zero credential leaks in 8+ weeks | ~78% |
| 10 | 📄 Corporate Swarm | Multi-agent coordination — sub-agent orchestration for enterprise workflows | Parallel task execution with oversight; deterministic completion tracking | ~80% |
Reading order: Top to bottom — from storing memories (1) to finding them instantly (2) to scaling them fractally (3) to maintaining identity (4) to improving overnight (5) to multi-model debate (6) to natural communication (7) to self-directed learning (8) to securing the system (9) to scaling across agents (10).
Combined effect: An agent that consumes roughly ⅘ fewer tokens than vanilla OpenClaw doing the same work. Not by limiting capability — by eliminating waste at every layer.
Each cron job carries a META file with its own instructions. After running, the agent reflects on what worked, updates the META, and the next run is better. No human needed.
Day 1: mediocre. Day 30: genuinely useful.
- Nightly upstream sync with conflict detection
- Post-merge workspace cleanup (catches 20KB bloat)
- Fork patches auto-restored after conflicts
- Hundreds of commits ahead, zero maintenance burden
All on ClawHub. Install any with
clawhub install globalcaos/<skill-name>. Skills sometimes get delisted from the marketplace — this list is the permanent record.
| Skill | What it does |
|---|---|
jarvis-voice |
Turn your AI into JARVIS. Voice, wit, and personality — the complete package. |
| Skill | What it does |
|---|---|
whatsapp-ultimate |
3-rule security gate — agent speaks only when spoken to, in the right chat, by the right person. |
| Skill | What it does |
|---|---|
youtube-ultimate |
Free transcripts, 4K downloads, video exploration — zero API quotas burned. |
| Skill | What it does |
|---|---|
tinker-command-center |
The dashboard above. Every token, every dollar, every context byte — real time. |
token-panel-ultimate |
Multi-provider token tracking, budget alerts, REST API. |
token-efficiency-guide |
Go from weekly limit on Tuesday to weekly limit on Sunday. 10 steps, one afternoon. |
No API keys. No admin consent. Your authenticated browser session IS the API.
| Skill | What it does |
|---|---|
outlook-hack |
Reads Outlook all day, drafts replies — won't send without approval. Code-enforced. |
teams-hack |
Reads Teams chats, posts to channels, searches everything. One browser handshake. |
factorial-hack |
Reads your HR portal — attendance, leave, payslips. No admin consent required. |
| Skill | What it does |
|---|---|
coding-agent |
Hand off a coding task, come back to a diff. Codex, Claude Code, or Pi — your call. |
subagent-overseer |
Sub-agents that go silent don't go unnoticed. Health checks, zero babysitting. |
fork-and-skill-scanner-ultimate |
Scan 1,000 GitHub forks per run. Surface the gold, skip the clones. |
memory-bench-pioneer |
Peer-review-grade evaluation suite — LLM-as-judge, nDCG, MAP, MRR metrics. |
model-prompt-adapter |
Universal prompt addenda for cross-provider fallback chains. Fixes per-model failure modes. |
smart-model-router |
Auto-selects the optimal model per task. Cost vs capability, no manual routing. |
| Skill | What it does |
|---|---|
agent-boundaries-ultimate |
Instruction-level guardrails so your agent won't go rogue or improvise ethics. |
agent-memory-ultimate |
Long-term memory done right. Semantic search, daily consolidation, cross-session recall. |
shell-security-ultimate |
Classify every shell command as SAFE, WARN, or CRIT before your agent runs it. |
| Skill | What it does |
|---|---|
computational-humor |
12 humor patterns based on embedding space bisociation theory. |
| Skill | What it does |
|---|---|
agent-sensei-ultimate |
The sensei your agent never had. 40 lessons on ethics, memory, budget, self-evolution. Day 1: mediocre. Day 30: expert. |
| Skill | What it does |
|---|---|
chatgpt-exporter-ultimate |
Leaving ChatGPT? Take your conversations with you. Full export, clean format. |
| Skill | What it does |
|---|---|
owntracks-location |
Real-time phone location tracking with named places and distance queries. Always know where you are. |
32 lessons from 6 weeks of running AI agents 24/7.
"Read is free, send is not."
"Wind-down is evolution, not diary."
"A stuck sub-agent is burning money. Kill fast, respawn small."
git clone https://github.com/globalcaos/tinkerclaw.git
cd tinkerclaw
pnpm install && pnpm build
pnpm openclaw onboard --install-daemonDrop-in replacement for vanilla OpenClaw. Same config, same workspace, same channels. Visit http://localhost:18789/tinker/ for the command center.
Click the Tinker logo or type /new to get your first morning briefing.
TinkerClaw builds on OpenClaw and was inspired by the work of:
- Mission Control by crshdn — context anatomy dashboard and agent orchestration UI
- ClawMetry by vivekchand — real-time token observability for OpenClaw agents
Both are excellent standalone tools. We folded their ideas into a single embedded panel and went from there.
🌐 thetinkerzone.com · 🎬 YouTube · 🦞 ClawHub · 💬 Discord
⭐ Star if you're tired of guessing what your AI costs.
Built by globalcaos. Your AI shouldn't cost more than your rent — and if it does, you should at least know why.