AI Dev Impact Lab JA
← Rankings · AI-RELATED REPO

aaronlab/browsertrace

Local flight recorder for AI browser agents. Debug Browser Use, Stagehand, Skyvern, and Playwright + LLM runs with screenshots, model I/O, and failure timelines.

Python ⑂ 3 forks MIT GitHub ↗ site ↗
★ 3
stars
70
AI relevance
65
solo dev
0
tool sigs

SUMMARY AI summary by gpt-5-mini

BrowserTrace is a local-first debugger for failures of browser-using agents (Browser Use) and related integrations (Stagehand, Skyvern, Playwright+LLM, custom computer-use agents). It records each run as a stepwise timeline (screenshot, URL, action, model input/output, status, error) so you can open a local UI and jump directly to the failed browser state. Key features: searchable local trace store, run comparison to find the first divergent step between failed and known-good runs, privacy-aware export that can omit prompts/screenshots/URLs, JSON CLI for automation (doctor, demo, list, show, compare, export), no cloud or signup required, works offline, and published on PyPI (Python 3.11+). Useful for developers and teams debugging AI-driven browser automation.

GitHub Topics

#ai-agents #browser-automation #browser-use #debugging #llm #observability #open-source #playwright #agent-debugging #agent-observability #ai-agent #computer-use #local-first #stagehand #agent-tracing #browser-agent #llm-observability #skyvern #ai-agent-debugging #browser-agents

Language breakdown (by bytes)

HTML
8.6%
Python
91.4%

Owner

Account
aaronlab
Type
User
Followers
4

Dates

Created on GitHub 2026-04-26
Last push 2026-05-09
First seen here 2026-05-09
Last fetched 2026-05-09 18:17

Similar repos (same language)

bgzhang1/sw2api

Reverse proxy for your ai quota from the SW platform.

Python 19 AI 45
dea6cat/2b-agent

This llm Agent was created based on necessity for one that could simply use local models without making them hallucinate and keep them focus

Python 1 AI 75
Zuboy/Carbon-Cost-Optimizer-Agentic-AI

An AI agent that decides where and when to run ML training jobs to minimize cost and carbon emissions, then launches them autonomously — exposed entirely through MCP tools.

Python 1 AI 75
FuchaZ/lm-studio-vision-bridge

给纯文本 AI agent 装上眼睛——通过 LM Studio 本地视觉模型提供 MCP 图片识别服务

Python 1 AI 45
Shrutirowlo/AI-Video-Agent

AI-powered video generation agent that automates script analysis, scene planning, and video creation.

Python 1 AI 75
Shivang0/social-vision

Paste an Instagram/TikTok/YouTube/X link and Claude watches it for you — transcribes audio, reads on-screen text & visuals, explains what it's about. Local, cross-platform Claude Code plugin.

Python 1 AI 70
markusbegerow/claude-fuer-oeffentliche-verwaltung

⚠️ Experimentelle Skill-Sammlung für Digitalisierung, Fachverfahren und Organisation der deutschen öffentlichen Verwaltung (OZG, FIM, FIT-Connect, KI-Einsatz, eIDAS, BSI-IT-Grundschutz, DSGVO) – bitte testen, Issues/PRs willkommen! Keine Rechts-/Datenschutzberatung, keine verbindliche Behördenentscheidung. Keine Bürger-/Mitarbeiterdaten im Repo.

Python 1 AI 75
knowledgegut/course-distiller

把有權使用的工作坊/課程回放消化成套品牌色的步驟式學習 PDF;最後的重組交還人腦。A Claude Code skill by 知識包小腸.

Python 1 AI 45