── POPULAR TAGS ──
#python (662)
#typescript (611)
#cli (557)
#hacktoberfest (494)
#cli-tool (491)
#react (481)
#javascript (449)
#rust (419)
#cross-platform (389)
#go (372)
#devops (315)
#ai (306)
#nodejs (299)
#llm (297)
#golang (288)
#android (271)
#open-source (255)
#docker (249)
#machine-learning (221)
#plugin-system (217)
#java (217)
#security (214)
#monorepo (213)
#self-hosted (209)
#linux (207)
#mcp (205)
#awesome-list (197)
#plugin-architecture (196)
#ai-agents (188)
#deep-learning (187)
This is a proof-of-concept Next.js application that demonstrates a web-browsing AI agent. Users submit a natural language goal (e.g., 'What is NVIDIA stock price?'), and the system creates a Browserbase browser session, then uses an LLM (Claude via Anthropic) to plan and execute steps (navigate, click, extract) via Stagehand. The frontend displays the agent's reasoning steps and a live browser view. The code is tightly coupled to Browserbase and Stagehand SDKs, with the agent loop split between client-side orchestration (ChatFeed) and server-side API routes. It is a simple, functional demo but lacks tests, modularity, and is no longer maintained (moved to another repo).
RATING:
MAINT: deprecated
DRIFT: low
── end of results ──