Ross ROSS = Recommend OSS · open-source software intelligence for agents

the-open-agent/openagent

⚡️next-generation personal AI assistant powered by LLM, RAG and agent loops, supporting computer-use, browser-use and coding agent, demo: https://demo.openagentai.org observed · 2026-08-28

github.com/the-open-agent/openagent · homepage · Go · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

94/100

  • Activity 98
  • Release rhythm 86
  • Longevity 100
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 0
  • age_days: 2287
  • days_rel: 13
  • days_push: 13
  • n_releases_24m: 988

Full methodology

Adoption not part of the score

5571 stars · 647 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

OpenAgent is a self-hosted, single-binary personal AI assistant platform built in Go that combines LLM chat, RAG knowledge bases, and autonomous agent loops with computer-use, browser-use, and coding agent capabilities. It supports 30+ model providers, MCP tool servers, built-in tools, skills, RBAC/SSO, and audit logging, with integrations for Telegram, Discord, and WeCom.

Use cases

  • self-host a private AI chat assistant over my own documents
  • build a RAG knowledge base from PDFs and wikis
  • connect an LLM agent to MCP tool servers
  • create a chatbot that can browse the web and run code
  • switch between OpenAI, Claude, Gemini, and local models with one config
  • deploy an AI assistant with RBAC and audit logs for my team
  • run an AI agent platform without Docker or vendor lock-in

When to choose

  • you want a batteries-included, self-hosted AI assistant with RAG, tools, and MCP support in a single binary
  • you need provider-agnostic model orchestration across 30+ LLM providers
  • you want agents that can use tools, browse the web, execute code, and call MCP servers
  • you need access control, SSO, and audit logs for a team deployment

When to avoid

  • you only need a lightweight LLM API client or SDK to embed in your own code
  • you want to train or fine-tune models rather than serve and orchestrate them
  • you need a minimal headless agent framework without a bundled web UI and admin dashboard
  • you require hard multi-tenant isolation at large scale beyond a single self-hosted instance

Facets

application · maturity active

agent-framework rag chatbot llm-inference mcp chat-interface search-engine web-framework artificial-intelligence large-language-models chatbots self-hosted developer-tools windows self-hosted go single-binary model-orchestration computer-use browser-use coding-agent knowledge-base multi-agent rbac audit-logs telegram discord wecom ai-agents retrieval-augmented-generation linux macos docker web-server

9 sources

Member repositories

RepositoryRoleHealth v2
the-open-agent/openagentmain94

For agents

markdown · JSON · MCP: product_card(name="the-open-agent/openagent")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem