Sigma Browser
Also known as: Sigma AI Browser, Eclipse, sigmabrowser.com
Privacy first agentic browser: an in-site agent that logs in, clicks, and completes multi step tasks with approve-before-submit control, plus Eclipse, a local on-device LLM with no cloud processing. Freemium, cross platform.
Sigma is a privacy first agentic browser combining three layers: an AI agent that executes multi step tasks inside live websites (logging in, clicking buttons, filling forms, submitting data, and returning results from a single goal description) with stated prompt injection defenses and a review and approve workflow before submission; Eclipse, a local LLM built into the browser that processes prompts on device with no cloud processing; and privacy infrastructure including end to end encrypted AI chats, encrypted DNS, phishing detection, tracker blocking, and stated GDPR and CCPA compliance, with no credentials or sensitive data retained after tasks complete.
Use cases span booking, form filling, bulk email cleanup, calendar management, CRM lead logging, and Deep Research. Freemium across Windows, macOS, iOS, and Android. Evidence is vendor published and directory sourced; no funding or independent press coverage retrieved.
Vendor details
Canonical URL
https://www.sigmabrowser.com
Category
Browser / computer-use agent
Funding status
Funding not disclosed in retrieved materials; agent feature entered early access August 2025
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Operates inside live websites through the Chromium based browser (login, click, type, fill, submit); pulls tables, receipts, and reports into spreadsheets; cross device syncing.
Sources & related URLs
Agentic Index coverage score
4.5 / 14 capabilities · 32%
| Integrations & Tool Calling | Partial |
|---|---|
|
Operates on any site through the browser UI with data extraction into spreadsheets; no connector catalog or tool calling, Sigma materials 2026-07-22 |
|
| Workflow Orchestration | Partial |
|
The agent completes multi step tasks from a single goal description (booking, forms, email cleanup, CRM logging), though scope is consumer task automation in gradual rollout, Sigma materials 2026-07-22 |
|
| Knowledge Grounding & RAG | Partial |
|
Deep Research synthesis across sources and page aware chat provide grounding, without a documented retrieval architecture, Sigma materials 2026-07-22 |
|
| Human Oversight & Guardrails | Partial |
|
The documented flow has users review the agent's proposed actions and approve the workflow before submission, with stated prompt injection defenses, Sigma materials and listings 2026-07-22 |
|
| Security, Identity & Governance | Partial |
|
End to end encrypted AI chats, encrypted DNS, phishing detection, stated prompt injection defenses, GDPR and CCPA compliance assertions, and zero credential retention, all self asserted without third party attestations, Sigma materials 2026-07-22 |
|
| Observability & Auditability | Unable to verify |
|
No run visibility, action logs, or audit tooling documented, Sigma materials 2026-07-22 |
|
| Memory & State Persistence | Unable to verify |
|
No credentials or sensitive data are retained after tasks complete by design; no persistent memory documented, Sigma materials 2026-07-22 |
|
| Deployment & Data Residency | Partial |
|
Cross platform client with Eclipse, a local LLM built into the browser processing data on device with no cloud processing, Sigma materials 2026-07-22 |
|
| Prebuilt Agents, Templates & Packs | Unable to verify |
|
No prebuilt agent or template library documented, Sigma materials 2026-07-22 |
|
| Triggers & Channel Coverage | Unable to verify |
|
All agent activity is user initiated from goal descriptions; no proactive or scheduled trigger machinery documented, Sigma materials 2026-07-22 |
|
| Model Flexibility & Routing | Partial |
|
Eclipse ships as a built in local LLM alongside cloud AI features, a documented local model layer though without customer model choice or routing, Sigma materials 2026-07-22 |
|
| APIs, SDKs & MCP Extensibility | Unable to verify |
|
No developer API, SDK, or MCP surface documented, Sigma materials 2026-07-22 |
|
| Testing, Debugging & Optimization | Unable to verify |
|
No customer facing testing or evaluation tooling documented, Sigma materials 2026-07-22 |
|
| Browser & Computer Use | Full |
|
The agent acts inside live websites, logging in, clicking, typing, filling fields, and submitting, as the core product capability, Sigma materials 2026-07-22 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Pricing
Free tier + paid plans
freemium subscription
What is public
The freemium structure is public (free core browser and AI, paid plans for higher limits); specific plan rates were not published in retrieved materials.
Variable cost rationale
Freemium subscription with a local LLM handling much processing on device; no usage metering documented.
Sales call required
No, self serve available
Free / trial
Free tier (core browser + basic AI)
Related vendors
- AgentQL — A self-healing query language for the web: natural language…
- Airtop — Cloud browsers for AI agents that compile plain English workflows…
- Asteroid — Supervised browser and computer use agents for regulated back…
- Astral — Browser based AI marketing agent that operates social platforms like…
- Automat AI — Managed AI agents that operate computers visually to replace legacy…
- Autotab — General AI agent that uses a mouse and keyboard like a person to do…
Alternatives to Sigma Browser
The closest documented capability profiles to Sigma Browser among browser and computer-use agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Astral4.5 / 14Adds documented Prebuilt Agents, Templates & Packs and Triggers & Channel Coverage
- Brave Leo AI Browsing6.5 / 14Adds documented Prebuilt Agents, Templates & Packs
- Induced AI4.0 / 14Adds documented Triggers & Channel Coverage and APIs, SDKs & MCP Extensibility
- Autotab7.0 / 14Adds documented Observability & Auditability and Memory & State Persistence, among others
- Lightpanda3.0 / 14Adds documented APIs, SDKs & MCP Extensibility
- MultiOn7.0 / 14Adds documented Observability & Auditability and Memory & State Persistence, among others
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded