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

Agenta-AI/agenta

Agenta is a workspace where you and your team build agents and automations. observed · 2026-08-28

github.com/Agenta-AI/agenta · homepage · TypeScript · NOASSERTION (other) observed · 2026-08-28

Health v2 · maintenance only

92/100

  • Activity 99
  • Release rhythm 87
  • Longevity 87

Flags: no_license

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: 0.5
  • age_days: 1225
  • days_rel: 7
  • days_push: 7
  • n_releases_24m: 319

Full methodology

Adoption not part of the score

4553 stars · 640 forks observed · 2026-08-28

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

Agenta is an open-source, self-hostable workspace where teams build, run, and share AI agents and automations by chatting with them. It provides agent orchestration, MCP-based integrations, human approval controls, background scheduling, tracing, and versioning, deployable via Docker Compose or Kubernetes.

Use cases

  • build ai agents without coding
  • automate repetitive team tasks with ai
  • self-host an agent workspace
  • run background agents on schedules or triggers
  • connect ai agents to slack github and other apps via mcp
  • monitor agent tool calls tokens and costs
  • collaborate with a team on shared ai agents

When to choose

  • you want a team-oriented, multiplayer workspace for building and running agents
  • you need self-hosting with your own models and credentials
  • you want human approval gates and granular tool permissions
  • you need observability, tracing, and version history for agents
  • you want to reuse open agent skills and MCP servers

When to avoid

  • you only need a simple single-user chatbot
  • you want a lightweight code-first agent library rather than a full platform
  • you need strict permissive licensing clarity (license is listed as NOASSERTION despite MIT badge)
  • you require fully offline operation without any LLM provider

Facets

application · maturity active

agent-framework workflow-automation chatbot mcp monitoring self-hosted chat-interface artificial-intelligence large-language-models self-hosted developer-tools self-hosted cloud cross-platform agent-builder agent-observability ai-workflow-builder multiplayer-workspace background-agents human-approval skills integrations tracing no-code ai-agents automation web-server docker kubernetes mobile

10 sources

Member repositories

RepositoryRoleHealth v2
Agenta-AI/agentamain92

For agents

markdown · JSON · MCP: product_card(name="Agenta-AI/agenta")

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