Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Persistent memory for browser automation AI Agents. Learns site knowledge automatically, updates after every visit, and gets better over time.
| Date | Stars |
|---|---|
| 2026-07-31 | 256 |
| 2026-08-06 | 256 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# site-memory **English** | [中文](README.zh-CN.md) | [日本語](README.ja.md) Browser automation agents forget everything between runs. Same site, same page structure to figure out, every single time. Wasted time, wasted tokens. site-memory lets your agent remember sites it has visited and go straight to the goal. On the WebVoyager benchmark, it cuts cost by 70% to 90% and makes tasks 4x faster with no loss in accuracy. - Learns site knowledge automatically - Updates after every visit - Gets better over time ## Why you need site-memory Without site-memory, booking a hotel on Booking.com takes 35 steps and nearly 8 minutes. With site-memory, the second run takes 5 steps and 30 seconds. Stable sites get even faster after a few visits. ## Install **Let your AI install it.** Tell Claude Code / Codex / OpenClaw / Gemini CLI: > Install the site-memory skill from github.com/LittleYier/site-memory Or use the [Skills CLI](https://github.com/vercel-labs/skills): ```bash npx skills add LittleYier/site-memory ``` Or clone manually: ```bash git clone --recurse-submodules https://github.com/LittleYier/site-memory.git ``` Then copy `skills/site-memory/` to your agent's skills directory (e.g. `~/.claude/skills/`, `~/.gemini/skills/`, or `.agents/skills/`). <!-- AGENT INSTALL INSTRUCTIONS If you are an AI agent installing this skill, follow these steps: 1. Run: npx skills add LittleYier/site-memory This handles everything automatically. If npx skills is unavailable, do steps 2-4 instead. 2. git clone --recurse-submodules https://github.com/LittleYier/site-memory.git /tmp/site-memory 3. cp -r /tmp/site-memory/skills/site-memory <skills-dir>/site-memory where <skills-dir> is ~/.gemini/skills, .agents/skills, or equivalent. 4. rm -rf /tmp/site-memory Verify: test -f <skills-dir>/site-memory/SKILL.md Requires: Node.js 22+ Browser tool: works with any browser tool the agent has access to. Chrome CDP skill bundled but optional. Invoke with: /site-memory <task description> Memory is stored at: ~/.site-memory/ (automatic, no config needed) --> ## Prerequisites - Node.js 22+ ## Browser tool options Works with any browser tool your agent already has: | Tool | Notes | |------|-------| | Chrome DevTools Protocol (bundled) | Installed with site-memory, requires Chrome with remote debugging | | [browser-use](https://github.com/browser-use/browser-use) | `npx skills add anthropics/browser-use` | | Playwright MCP | Add the MCP server to your agent config | | [Claude in Chrome](https://chromewebstore.google.com/detail/claude-in-chrome/) | Browser extension, accessed as an MCP tool | | Others | Anything that can navigate, read, and interact with pages | Most agent runtimes (Claude Code, Gemini CLI, Codex) can load multiple skills at once. site-memory works with whatever browser tool you pick. ## Usage Best for repeated browser work, such as: ```text Fill out the insurance quote form on example-insurance.com Search for apartments under $300k on realestate-site.com Go to the admin dashboard and export last month's report ``` Or call it directly: ```text /site-memory open books.toscrape.com and get page 3 titles ``` ## Memory location `~/.site-memory/` ## Benchmark Tested on [WebVoyager](https://github.com/MinorJerry/WebVoyager) tasks. **15 websites, 50 tasks, 3 rounds each (150 total runs). All correct.** Round 1: Claude Sonnet 4.6. Rounds 2 and 3: Claude Haiku 4.5 (3x cheaper). | Site | R1 avg cmds | R2 avg cmds | R3 avg cmds | R1 avg time | R3 avg time | Cmd delta | Time delta | |------|------------:|------------:|------------:|------------:|------------:|----------:|-----------:| | Booking | 35.7 | 6.7 | 5.0 | 497s | 30s | **-86%** | **-94%** | | Amazon | 14.7 | 2.0 | 2.0 | 183s | 12s | **-86%** | **-93%** | | ArXiv | 9.5 | 1.5 | 1.5 | 143s | 9s | **-84%** | **-94%** | | Google Flights | 23.3 | 10.3 | 4.0 | 173s | 47s | **-83%** | **-73%** | | ESPN | 8.3 | 2.3 | 2.0 | 85s | 18s | **-76%** | **-78%** | | Huggingface | 17.7
Excerpt of 5,133 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:285c19af31a5bd0e, llm:Description: 'Persistent memory for browser automation AI Agents. Learns site knowledge automatically, updates after every visit, and gets better over time.' (repo description)
matched fp:285c19af31a5bd0e, llm:Description: 'Persistent memory for browser automation AI Agents. Learns site knowledge automatically, updates after every visit, and gets better over time.' (repo description)
matched fp:285c19af31a5bd0e, llm:Description: 'Persistent memory for browser automation AI Agents. Learns site knowledge automatically, updates after every visit, and gets better over time.' (repo description)