title: HtmlClaw
emoji: 🐠
colorFrom: red
colorTo: gray
sdk: static
pinned: false
license: other
short_description: OpenClaw inspired HTML port...
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
⚡ CHRONOS Browser-Native WebLLM Agent
Chronos is a fully client-side AI agent that runs directly in the browser using WebLLM.
It combines a ReAct agent loop, persistent memory, dynamic skills, hybrid RAG, and tool execution — all without a traditional backend.
The system demonstrates how a modern agent architecture can run entirely inside a web environment using JavaScript + WebGPU.
🧠 Core Idea
Chronos is not just a chat interface.
It is a browser-resident AI agent runtime that combines:
LLM (WebGPU)
- Persistent Memory
- Skills
- Tools
- Hybrid RAG
- Web Search
- Local Network Discovery
- Scheduling
Everything runs in the browser.
No Python servers or AI frameworks are required to run the agent logic.
🧩 Architecture User │ ▼ Chronos UI │ ▼ ReAct Agent Loop │ ├ soul.md → agent identity ├ user.md → persistent user memory ├ skills/*.md → injected capabilities │ ├ tools │ ├ web_search │ ├ scrape │ ├ summarize │ ├ remember │ ├ read_memory │ ├ forget │ ├ schedule │ ├ inject_js │ ├ rag_index │ ├ rag_search │ ├ rag_prompt │ └ network_scan │ └ hybrid RAG index │ ▼ WebLLM (GPU inference)
The agent builds its prompt dynamically based on:
memory
skills
retrieved documents
tool outputs
conversation context
⚡ Features 🧠 Persistent Agent Memory
Chronos uses two memory files:
soul.md
Defines the identity and behavior of the agent.
Example:
You are Chronos, a browser-native AI agent. You can reason, use tools, and retrieve knowledge.
This acts as the system prompt.
user.md
Stores persistent user information.
Example:
User name: Chris Interests:
- AI agents
- semantic search
This allows the agent to remember preferences across sessions.
⚡ Dynamic Skill Injection
Skills extend the agent without modifying the core code.
skills/ ├ gdpr-advisor.md └ code-engineer.md
Skills contain instructions that are injected into the prompt when active.
Example skill capabilities:
domain expertise
coding support
legal advisory
specialized reasoning
Skills can be:
added
removed
modified
at runtime.
🔁 ReAct Agent Loop
Chronos uses a ReAct reasoning loop:
think → act → observe → respond
Example flow:
User: What is the latest AI news?
Think: I should search the web.
Act: web_search("latest AI news")
Observe: results...
Respond: summary
This allows the agent to use tools during reasoning.
🛠 Tool System
Chronos supports a built-in tool ecosystem.
Current tools include:
Tool Description web_search search the web scrape extract webpage text summarize summarize long content remember store information in memory read_memory read stored memory forget delete stored memory schedule create scheduled tasks inject_js run JavaScript rag_index index documents rag_search search indexed knowledge rag_prompt inject RAG context network_scan detect local services 📚 Hybrid RAG Retrieval
Chronos includes a browser-based RAG system.
Documents can be indexed directly from the UI.
Sources include:
pasted text
scraped pages
memory
manual input
The system builds a hybrid index:
semantic vectors
- keyword terms
This allows efficient retrieval inside the browser.
Workflow:
Index documents │ ▼ User query │ ▼ Hybrid search │ ▼ Top results injected into prompt 🌐 Web Search + Scraping
Chronos can access external knowledge through:
web_search → find pages scrape → extract content summarize → compress results
Optional integration:
Brave Search API
Free tier includes:
2000 requests/month 📡 Local Network Discovery
The network_scan tool attempts to detect common local services.
Default targets:
localhost:3000 (dev) localhost:5000 (flask) localhost:5173 (vite) localhost:4200 (angular) localhost:8888 (jupyter) localhost:11434 (ollama)
This allows the agent to discover locally running AI services or development servers.
⏰ Scheduled Tasks
Chronos can store tasks for later execution.
Example:
schedule("Check AI news every morning")
Tasks persist inside the agent state.
🖥 Running Chronos
Because WebLLM requires proper browser isolation, the UI should be served via a local proxy.
Run:
python proxy.py 8080
Then open:
http://localhost:8080 🤖 Model Support
Chronos loads WebLLM-compatible models.
Example:
Llama 3.2 · 3B
Typical requirements:
Model VRAM 3B ~2GB 7B ~4-6GB
WebGPU support is required.
📊 Runtime Stats
Chronos provides live metrics:
tokens/sec
total tokens
web searches
scrapes
reasoning logs
⌨ Shortcuts Shortcut Action `Ctrl + `` open console log ↑ command palette Ctrl + L clear conversation 🔧 Example Use Cases
Chronos can be used as:
a local AI assistant
a browser research agent
a developer tool for AI experiments
a WebLLM playground
a lightweight autonomous agent
💡 Why This Project Exists
Most agent frameworks require:
Python stacks
vector databases
complex infrastructure
heavy frameworks
Chronos shows that a surprisingly capable agent can run entirely inside the browser.
🚀 Future Ideas
Possible extensions:
streaming token display
vector embedding models
multi-agent cooperation
browser automation
plugin marketplace
distributed browser agents