Eigent is an open-source desktop multi-agent AI workforce that automates browser, desktop, and file-based tasks using the model of your choice, with local-first control.
About
Eigent is an open-source desktop application that runs a multi-agent AI workforce alongside the user. It addresses a common frustration with AI assistants: they can chat but cannot complete real work. Eigent connects to the user's context, controls the browser and desktop applications, and turns instructions into finished outputs such as research briefs, files, and scheduled automations.
The product is built on research from CAMEL-AI.org and is developed by EIGENT UK LTD. Users bring their own model—cloud providers, enterprise gateways, or local models—using their own API keys. Work is organized into Spaces that package agents, Skills, and Connectors together so a team can set up its environment once and reuse it. Every step an agent takes, including reasoning, actions, and file changes, can be inspected and approved before results are accepted. The desktop client is available for Mac (M-series and Intel), Windows, and Linux.
Key Features
Pricing & Fees
- Pricing: A Free tier at $19.99/month listing (with BYOK and local models usable at no cost, 1,000 registration credits, and 500 credits per successful invite), Plus at $19.99/month including 2,000 monthly task credits and additional models, and Pro at $99.99/month including 10,000 monthly task credits. Teams is listed as coming soon, and Enterprise is custom pricing via sales contact. Plus and Pro start with a 7-day free trial.
- Open source: The desktop app is 100% open source and can be self-hosted free with the user's own API keys or local models.
- Model choice: Sixteen supported models are listed on the Free tier, including options from OpenAI, Google, DeepSeek, and others; Plus and Pro add models such as Claude Sonnet 5 and Grok 4.7.
- Platforms: Downloads are available for Mac M-series, Mac Intel, Windows, Linux, and open-source self-hosting.
- Compliance posture: The site cites SOC 2 readiness and GDPR compliance work for enterprise deployments.
Who It's For
Eigent suits teams and individuals who want AI agents to handle complete tasks rather than answer questions. Market researchers can use it to map markets and build weekly competitor digests; operations and growth teams can audit funnels and draft positioning memos; technical users can self-host it and connect local models for data-sensitive work. It also fits developers experimenting with agent orchestration, since the code is open source and builds on CAMEL-AI research. Enterprises needing governance, roles, and policy-based approvals are addressed through the Enterprise plan.
FAQ
What is Eigent?Eigent is an open-source desktop multi-agent AI workforce that connects to a user's context and can control the browser and desktop applications to automate real work.
Is Eigent free to use?The desktop app is 100% open source and can be self-hosted free with the user's own API keys or local models; paid Plus and Pro subscriptions at $19.99 and $99.99 per month add task credits and additional models.
Which platforms does Eigent support?Eigent offers downloads for Mac with M-series chips, Mac with Intel chips, Windows, and Linux, plus an open-source self-hosting option.
Can Eigent run locally or with my own models?Yes, Eigent is model agnostic; it supports cloud providers, enterprise gateways, and local models, and users can bring their own API keys and switch providers without rebuilding workflows.
How does Eigent handle data and control?Eigent can run on the user's own infrastructure, keeps secrets bound locally, restricts agent browser access to approved targets, and requires review and approval of agent work, with SOC 2 readiness and GDPR compliance work cited for enterprise use.
Related Tutorials
View all →
Related Tools
View all →
Sim Sim is the open-source platform to build AI agents and run your agentic workforce. Connect 1,000+ integrations and LLMs to orchestrate agentic workflows. 
AgentScope - Where Agents Come Alive AgentScope is an open-source multi-agent platform for building LLM-powered applications. It features drag-and-drop workflows, runtime management, and the Spark Design system. 
Paperclip Paperclip is an open-source, self-hosted app for managing teams of AI agents for work, with org charts, goals, budgets, and governance in one deployment. 
Yuxi - RAG Harness for AI Agents Yuxi provides a RAG harness to enhance AI agents with retrieval-augmented generation capabilities. 
OmniRoute - Free AI Gateway for Multi-Provider LLMs Free, open-source AI router with auto-fallback. 236 providers, one endpoint, 95 MCP tools, 17 routing strategies, A2A protocol, auto-combo engine, semantic cache, memory & skills. Deploy anywhere.