Tag
The article discusses a common failure in browser agents where form rejections are not detected due to reliance on structural changes in action results, and suggests including visible text in observations and treating refusal as a first-class outcome to improve reliability.
Retriever AI has launched a totally free browser agent extension supported by ads, leveraging DeepSeek Flash Code Mode to minimize costs and enable continuous learning from user workflows.
The article discusses challenges with browser agents in data extraction, such as incomplete tables, and introduces Thunderbit's solution that provides source URLs and reviewable tables for transparency and trust.
A developer shares how they cut DeepSeek API costs by roughly 90% through prefix caching optimizations, reducing browser agent task costs below $0.005 and enabling a free, ads-supported browser agent.
WebRider is a hierarchical framework that formalizes delegated web tasks as intent contracts, preserving persona-conditioned policies through every browsing step. It includes RiderBench, a benchmark of 4,096 live-web contracts, and an 8B action-policy model trained through its guarded interface.
Hark previews Hark Handoff, a browser-use agent that can complete tasks like shopping and booking reservations by navigating websites without APIs, with claims of being faster and cheaper than rivals.
Index is an open-source AI browser Agent developed by the Laminar team that turns any website into a callable API, supports vision models such as Claude and Gemini, and achieves 92% accuracy on WebVoyager.
Microsoft released Fara1.5-27B, a 27B parameter multimodal computer use agent for web browsers, fine-tuned from Qwen3.5-27B, capable of end-to-end web tasks via screenshots.
barebrowse is a tool that generates pruned ARIA snapshots from web pages, reducing token consumption for local AI models by stripping boilerplate and ads, and reusing existing browser cookies.
A browser-based agent that reverse-engineers web app APIs to automatically generate agent tools, enabling deep integration without code changes.
The article demonstrates using a browser agent to draft job applications by connecting to Ashby and Greenhouse applicant tracking systems.
Opera's team tested browser snapshot formats for AI agents, finding identical pass rates but significantly lower token cost with their compressed format (opera-compact), which eliminates redundant ARIA attributes and repeated URLs. They released it as an open-source MCP server.
Pluno is a browser agent that claims to be 10x faster than Claude.
Aside is a new AI browser that runs locally with encryption, features vertical tabs and Liquid Glass design, claims state-of-the-art performance on agentic browsing benchmarks, and includes a password manager for AI agents.
Moved the LLM out of the runtime loop in a browser agent to ensure deterministic replays.
Open-weights models have caught up with proprietary ones, with GLM 5.2 achieving near Opus-level scores in browser agent tasks at low cost. Other models like Minimax M3 and Kimi k2.7 also show notable improvements.
Introducing B, an open-source browser agent template built on Eve by Vercel that uses Browser Use Cloud to give any AI agent a real web browser. It includes a chat UI and live browser viewing.
An open-source agent that uses an LLM to control a real browser to fill forms and extract structured data, requiring minimal tokens per page.
Browser Use Terminal is a new CLI tool that turns your terminal into a browser agent, allowing you to run browser tasks and control your real Chrome browser.
Fireworks AI and Notte introduce the 'Agent Execution Tax' metric after running 720 browser agent tasks across four LLMs, finding that execution reliability—not intelligence—is the primary bottleneck in agentic AI, with one model wasting 22.9% of inference calls on malformed JSON.