Retriever AI Launches Free Browser Agent

// 2h agoPRODUCT LAUNCH

Retriever AI Launches Free Browser Agent

Retriever AI is a free browser agent that researches leads, sends outreach, extracts web data, and applies to jobs across Chrome or hosted cloud browsers. Its DOM-based harness supports MCP integrations with Claude, Codex, and other AI tools.

// ANALYSIS

Retriever AI’s strongest pitch is not merely browser automation, but affordable web execution that developers can embed into existing agent workflows.

–DOM-based interaction should be more reliable and cheaper than screenshot-driven browser agents.
–Chrome, cloud, API, CLI, SDK, and MCP access gives it a credible path from personal automation to infrastructure.
–Free, ad-supported usage lowers adoption friction but raises questions around privacy, trust, and sponsored-task boundaries.
–Its published 81.4% WebBench completion rate and claimed 5× speed advantage are compelling, though independently verified results remain limited.
–Lead outreach and job applications are powerful demos, but platform policies and human-review requirements will constrain autonomous actions.

// TAGS

retriever-aiagentweb-agentcomputer-usebrowser-extensiontool-usemcpautomation

DISCOVERED

2h ago

2026-10-14

PUBLISHED

7h ago

2026-10-14

RELEVANCE

8/ 10

AUTHOR

[REDACTED]

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

RESEARCH37m ago

ReHarness Rewrites Agent Memory Midstream

ReHarness is a recurrent harness framework that revises retrieved agent reflections using downstream task feedback while grounding changes in their original trajectories. The paper reports stronger continual-learning performance across three benchmarks and three LLM backbones without replay, fine-tuning, or model changes.

TUTORIAL47m ago

GitHub Secret Scanning Learns Context, Cuts Noise

GitHub details a two-stage secret-scanning pipeline that combines high-recall regexes with a fine-tuned ModernBERT classifier to distinguish real credentials from harmless lookalikes. The system reportedly improves acceptance 11.5%, cuts post-push scan time 86%, and reduces serving costs over 98%.

LAUNCH54m ago

Agent Found This launches bargain board for agents

Agent Found This is a local offers board where businesses submit deals, humans review them, and AI assistants search for matches. The experiment currently covers San Francisco, New York, and Tel Aviv, with REST and MCP access for agents.