switchboard
A

Agent S

by Simular AI

Operates desktop graphical interfaces like a person, combining hierarchical planning with visual grounding to click through applications and finish multi-step tasks.

3
Skills
API Key
Auth
No
Streaming
No
Push

Skills

GUI Grounding

Locates on-screen interface elements from a screenshot and maps them to precise click and type coordinates.

Hierarchical Planning

Decomposes a computer task into subgoals and replans when an action produces an unexpected screen state.

Experience Reuse

Stores successful interaction traces as reusable experience so repeated desktop workflows execute more reliably.

Browser & Computer UseOrchestrationcomputer-usegui-agentvisual-groundinghierarchical-planningosworlddesktop-automationopen-source
Visit Agent

Related Agents

A

Agent TARS

ByteDance's multimodal AI agent for desktop and browser automation — controls GUIs, browsers, and shell via vision and…

Browser & Computer UseInfrastructure & Ops
CLI
4 skillsNone
E

Eigent

Runs a local multi-agent desktop workforce that splits tasks across specialized workers with browser, terminal, and fil…

OrchestrationBrowser & Computer Use
CLIAPI
3 skillsAPI Key
S

SandBase Harness

Runs local-first, self-hosted AI agents with persistent sessions, sandboxed tools, memory, credentials, audit trails, r…

OrchestrationCode & DevTools
CLIMCP
3 skillsNone
B

BitFun

Runs an open-source desktop and terminal coding agent that plans, edits, tests, and reviews changes inside real Git rep…

Code & DevToolsBrowser & Computer Use
CLI
3 skillsAPI Key
agent-s
Operates desktop graphical interfaces like a person, combining hierarchical planning with visual grounding to click through applications and finish multi-step tasks.
fields
nameAgent S
providerSimular AI
urlhttps://github.com/simular-ai/Agent-S
categoriesbrowser-computer · orchestration
accessapi · cli
authapiKey
streamingfalse
pushfalse
verifiedtrue
tagscomputer-use, gui-agent, visual-grounding, hierarchical-planning, osworld, desktop-automation, open-source
skills
gui-groundingGUI GroundingLocates on-screen interface elements from a screenshot …
hierarchical-planningHierarchical PlanningDecomposes a computer task into subgoals and replans wh…
experience-reuseExperience ReuseStores successful interaction traces as reusable experi…
→ https://github.com/simular-ai/Agent-S