High-frequency in-browser behavior tree execution engine for autonomous AI agents — 60Hz tick loops, reactive triggers, telemetry recordings, and safety guardrails.

Configure browser-side CSV/Excel importers. File contents never leave the browser.

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

Browser and desktop automation with an MCP server for AI assistants. Record macros or write JavaScript to automate websites, extract data, and control desktop apps with OCR and image recognition.

Enables AI clients to observe foreground browser viewports, read filtered page evidence, and run guarded reusable site-pack procedures through the same local runtime as the CLI.

Let coding agents verify UI changes on real iOS, Android, and web surfaces, then enforce reviewed proof in deterministic CI.

AI agents can generate code, but still struggle to understand what they build. Reticle brings Jev-style machine-native runtime perception to web & desktop applications.

Your own search engine

Standalone MCP server for SAP ABAP ADT over stdio: one destination through the auth broker (service keys, sessions, the browser login); connects to the system over HTTP, RFC or SNC (passwordless). RFC and SNC need the SAP NW RFC library at run time. Strea

MetaHarness — mint a custom AI agent harness from any repo. Browser Studio + `npx metaharness` CLI. Runs on Claude Code, Codex, pi.dev, Hermes, OpenClaw, RVM, Prime Agent.

Browser transport implementations for Model Context Protocol (MCP) - postMessage, Chrome extension messaging, and iframe communication for AI agents and LLMs

DeepSeek Harness plugin: give your agent a browser with a persistent identity - engine-level fingerprint spoofing, unlimited free local profiles, Android device emulation, passkeys that survive, and residential proxy egress.

The ADE for AI agents. Automate everything else. Do your true work.

Cognitive browser automation that thinks like your users—and helps AI agents navigate too. Simulate real user cognition with abandonment detection, constitutional safety, chaos engineering, and UX friction discovery. Sites that pass CBrowser's cognitive t

Enables AI agents to build, validate, and submit ledger-native XRPL transactions against public nodes — escrows, XRP and token payments, DEX/AMM swaps and liquidity, issuer clawback, and x402 pay-per-request — with validated-ledger proof of results. State-changing calls go to the account owner for browser signing, while an owner-funded agent account allows autonomous spending bounded by on-ledger balance and local policy limits.

Enables MCP-capable agent CLIs on macOS to reuse an installed, unmodified OpenAI Browser Runtime to drive a connected Chrome or Edge browser (or a host's in-app browser backend) through js, js_reset, and turn_ended tools. It stays a thin bridge that preserves the Runtime's approval and security boundaries, failing closed when the client cannot handle approval requests.

Enables agents to discover and invoke browser-registered tools for PDF preview/export, image text overlay/PNG export, URL packing/decoding, and spreadsheet, document, and slide generation.

Enables AI agents to drive a real Chromium browser by receiving compact, token-efficient page maps and only the changes after each action. It guards against hidden prompt injections, blocks payments, sends and deletions until the user approves, and lets agents learn site-specific notes over time.

Gives browser agents a reviewed map of 79 real sites — entry URLs, access verdicts, and role/accessible-name button maps for 104 screens — so an agent can find where things are and know whether it may act at all. Safety rules in code halt irreversible actions such as pay, order, submit and delete pending explicit human approval, while per-site memory recalls which routes worked last time.

Enables automation of the QingSoft U+ learning platform by patrolling courses, homework and experiments, inspecting objective questions, filling and submitting answers, and handing subjective work back to a human, while also providing a generic browser automation toolset.

Runs entirely local media tooling as an MCP plugin: it edits and inspects video, denoises/transcribes/normalizes audio, generates images, performs OCR, does offline text-to-speech, drives the user's logged-in Chrome via CDP, and reads or creates Office and PDF documents. Everything executes on the machine through ffmpeg, faster-whisper, MossFormer2, ComfyUI/FLUX, Tesseract, SAPI and Playwright, with no API costs or file uploads.

Enables reading public WeChat articles through HTTP text extraction with metadata, pagination, and image links, automatically falling back to a visible Chrome window when a verification page appears so the user can complete any captcha manually.

Download M3U8 live streams to the local disk