← Back
Home › Systems › Agentic AI

computer-use-agent

browser and computer-use agent

Operator, Claude in Chrome

SystemTechniques · 25Primitives · 99 computer-use-agent Gui groundingagentic-ai · medium: Mapping an intended UI action to screen coordinates or elements from screenshots, with scaling and verificationPrompt injection defenseagentic-ai · medium: Treat every untrusted string as data, track where values came from, and make tool calls and rendered output depend on provenance, not on what the model says.›Deterministic simulation testingdistributed · medium: Run the whole system in one thread under a seeded scheduler with simulated network, disk and clock, so every failure replays from its seed.›Primary-backup replicationdistributed · medium: One node orders all writes and ships them to standbys; the acknowledgement rule (none, one, all) sets what a crash loses, and an external arbiter decides who takes over.›Vision transformerml-training · medium: ViT: patch embeddings, position encodings, encoder blocks; vision-language connectorsCoverage-guided fuzzingsecurity · medium: Mutate inputs, run an instrumented target, and keep any input that reaches a new code edge; feedback turns blind guessing into incremental search.›Point-in-time recoverystorage · medium: Periodic base backups plus a continuously archived change log let you rebuild the state as of any instant, then branch from there.›Accessibility treeagentic-ai · low: Extracting the browser/OS accessibility tree (roles, names, bounds) as a compact text view of a UI for agentsImage resampling filtersgraphics · low: Resize an image by convolving with a kernel (box, triangle, cubic, Lanczos) whose width scales with the shrink factor, done as two separable 1-D passes with precomputed weights.›Hardware virtualization kvmhardware-os · low: VT-x/AMD-V via KVM: vCPU run loop, VM exits, MMIO emulationAgent loopagentic-ai · unknown: Agent sandboxingagentic-ai · unknown: Agent tracingagentic-ai · unknown: Browser automation protocolagentic-ai · low: CDP / WebDriver BiDi commands and events over websockets to drive browsersContext window managementagentic-ai · low: Keep an agent's growing history inside the model's window by truncating, clearing and summarizing old turns in a cheap-to-lossy ladder, at turn boundaries.›Input event synthesisagentic-ai · low: Inject synthetic mouse, keyboard and touch events at OS or browser level (CGEvent, SendInput, uinput, CDP Input) with realistic timingPrompt cachingagentic-ai · low: Reuse the attention keys/values of a repeated prompt prefix, so an agent's growing context is prefilled once and later turns pay only for the new tokens.›Task planningagentic-ai · unknown: Tool callingagentic-ai · low: The model emits a structured call (id, name, JSON arguments) instead of prose; your code validates, runs it and returns a result tagged with the same id.›Hdr histogramdata-structures · low: Log-linear bucketed histograms with bounded relative error for latency percentilesProcess supervisionhardware-os · low: A parent process starts services, reaps their exits and restarts them under a delay and burst-limit policy, then stops them with SIGTERM before SIGKILL.›Remote framebuffer protocolnetworking · low: RFB/VNC framebuffer updates, encodings and input events for remote desktop controlWebSocketsnetworking · low: Full-duplex message framing over one upgraded HTTP connection; the standard way to push real-time data to browsers.›+ 18 more techniques+ 83 more primitives

Similar systems

Share the most building blocks with this one.

agent-runtime 44 %mcp-host 37 %agent-browser-isolation 32 %chat-assistant 32 %rl-environments 31 %