simular-ai/Agent-S BEST FIT ★ 13k active 7d ago
Research computer-use agent that operates your real desktop by looking at the screen and clicking and typing; CLI or Python, with your own model keys.
Replaces Autonomous web browsing (partly) Not: deep research reports, file and code tasks in a sandbox, slides generated from a prompt, scheduled agent tasks, connectors to your apps
- Runs locally
- Confirmed: Yes
- Commercial use
- Confirmed: Yes · Apache-2.0
- Paid services
- Partial: Optional only
- Hardware
- Confirmed: See details
- Setup
- Confirmed: Medium
Fosowl/agenticSeek BEST FIT ★ 27k active today
Local Manus-style agent that browses the web, writes and runs code and plans multi-step tasks, built for local models via Ollama or LM Studio.
Replaces Autonomous web browsing + File and code tasks in a sandbox (partly) Not: deep research reports, slides generated from a prompt, scheduled agent tasks, connectors to your apps
- Runs locally
- Confirmed: Yes
- Commercial use
- Partial: Conditions · GPL-3.0-only
- Paid services
- Confirmed: None required
- Hardware
- Confirmed: GPU needed
- Setup
- Confirmed: Medium
bytedance/deer-flow BEST FIT ★ 84k active today
ByteDance's self-hosted "super agent" for deep research, reports, slides and web pages, with Docker sandboxes, sub-agents, scheduled tasks and chat-app bots.
Replaces Deep research reports + File and code tasks in a sandbox + Slides generated from a prompt + Scheduled agent tasks + Connectors to your apps (partly) Not: autonomous web browsing
- Runs locally
- Confirmed: Yes
- Commercial use
- Confirmed: Yes · MIT
- Paid services
- Partial: Optional only
- Hardware
- Confirmed: CPU works
- Setup
- Confirmed: Medium
Intelligent-Internet/ii-agent BEST FIT ★ 3.4k active 2mo ago
Self-hostable Manus-style agent web app for deep research, slides, websites and documents, with app integrations and your own model keys.
Replaces Deep research reports + File and code tasks in a sandbox + Slides generated from a prompt + Connectors to your apps (partly) Not: autonomous web browsing, scheduled agent tasks
- Runs locally
- Confirmed: Yes
- Commercial use
- Confirmed: Yes · Apache-2.0
- Paid services
- Partial: Optional only
- Hardware
- Unknown: Unknown
- Setup
- Confirmed: Medium
Team agent platform (formerly Suna) where agents work in isolated sandboxes, in Slack or Teams and on schedules. Source-available, Elastic License 2.0.
Replaces File and code tasks in a sandbox + Scheduled agent tasks + Connectors to your apps (partly) Not: autonomous web browsing, deep research reports, slides generated from a prompt
- Runs locally
- Confirmed: Yes
- Commercial use
- Partial: Conditions · Elastic-2.0
- Paid services
- No: Required
- Hardware
- Unknown: Unknown
- Setup
- Confirmed: Medium
microsoft/magentic-ui BEST FIT ★ 10k active 3w ago
Microsoft Research agent app for web research, form filling and file tasks, with a sandboxed browser VM and approval before critical actions.
Replaces Autonomous web browsing + File and code tasks in a sandbox (partly) Not: deep research reports, slides generated from a prompt, scheduled agent tasks, connectors to your apps
- Runs locally
- Confirmed: Yes
- Commercial use
- Confirmed: Yes · MIT
- Paid services
- Partial: Optional only
- Hardware
- Confirmed: GPU, ~48GB+
- Setup
- Confirmed: Medium
nanobrowser/nanobrowser BEST FIT ★ 14k active 1d ago
Chrome/Edge extension that runs a browsing agent in your own logged-in browser, using your API key or a local model; asks before it submits or sends.
Replaces Autonomous web browsing (partly) Not: deep research reports, file and code tasks in a sandbox, slides generated from a prompt, scheduled agent tasks, connectors to your apps
- Runs locally
- Confirmed: Yes
- Commercial use
- Confirmed: Yes · Apache-2.0
- Paid services
- Partial: Optional only
- Hardware
- Confirmed: CPU works
- Setup
- Confirmed: Easy
FoundationAgents/OpenManus BEST FIT ★ 59k active 2w ago
Terminal-based general agent from the MetaGPT team that plans tasks, browses the web and runs tools with your own model keys or a local Ollama model.
Replaces Autonomous web browsing + File and code tasks in a sandbox (partly) Not: deep research reports, slides generated from a prompt, scheduled agent tasks, connectors to your apps
- Runs locally
- Confirmed: Yes
- Commercial use
- Confirmed: Yes · MIT
- Paid services
- Partial: Optional only
- Hardware
- Unknown: Unknown
- Setup
- Confirmed: Medium
Multi-agent assistant built on CAMEL-AI that browses, searches, runs code and reads Office/PDF files, with a local Gradio web UI and your own model keys.
Replaces Autonomous web browsing + File and code tasks in a sandbox (partly) Not: deep research reports, slides generated from a prompt, scheduled agent tasks, connectors to your apps
- Runs locally
- Confirmed: Yes
- Commercial use
- Confirmed: Yes · Apache-2.0
- Paid services
- Partial: Optional only
- Hardware
- Unknown: Unknown
- Setup
- Confirmed: Medium
Skyvern-AI/skyvern BEST FIT ★ 23k active today
Browser agent that uses vision LLMs to fill forms, log in and run multi-step web workflows, with a local UI, no-code workflow builder and Playwright SDK.
Replaces Autonomous web browsing (partly) Not: deep research reports, file and code tasks in a sandbox, slides generated from a prompt, scheduled agent tasks, connectors to your apps
- Runs locally
- Confirmed: Yes
- Commercial use
- Partial: Conditions · AGPL-3.0-only
- Paid services
- Partial: Optional only
- Hardware
- Unknown: Unknown
- Setup
- Confirmed: Easy
No project meets all of your requirements. The list below shows what you'd need to relax.