# AgentDock/AgentDock

Build Anything with AI Agents

Repository: https://github.com/AgentDock/AgentDock
Canonical: https://ross.abutalabs.com/products/agentdock
Homepage: https://agentdock.ai
Language: MDX
License: MIT
License Family: permissive
Topics: llm, typescript, workflows, nextjs, agentic-ai, agentic-framework, ai-agents, natural-language-inference
Last push: 2026-07-14T07:40:00+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 92, release rhythm 35, longevity 39
- inputs: {"age_days": 559, "days_push": 50, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1701, forks 129 (observed 2026-08-28T04:05:24.287022+00:00)

## What it is
AgentDock is an open-source, backend-first TypeScript framework for building AI agents with configurable determinism, plus a Next.js reference client. It is framework-agnostic and provider-independent, and the company also offers a multi-channel customer engagement platform built on it.

## Use cases
- build ai agents that complete complex tasks reliably
- deploy provider-independent llm agents in typescript
- create deterministic ai workflows with minimal supervision
- automate customer support across email, sms, and chat
- serve prompts and skills to agents over mcp, cli, or rest
- build a chatbot reference app with nextjs

## When to choose
- you want a backend-first, framework-agnostic agent framework in TypeScript
- you need configurable determinism for production agent behavior
- you want a self-hosted open-source core with a reference Next.js client
- you need an agent-accessible prompt and skills library

## When to avoid
- you need a fully managed cloud platform today - AgentDock Pro is still upcoming
- you want a Python-based agent stack
- you need a no-code visual workflow builder - that is planned for the paid platform
- you need a battle-tested stable release - the project is in beta

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, llm-inference, chatbot, mcp, prompt-engineering, workflow-automation, web-framework
- domain: large-language-models, web-development, developer-tools
- platform: self-hosted, cross-platform
- tags: agentic-ai, configurable-determinism, provider-agnostic, nextjs, backend-first, prompt-library, customer-engagement, ai-agents, automation, typescript, nodejs, web-server

## Member repositories
- AgentDock/AgentDock (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:24.287022+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:37:41.587407+00:00, confidence not recorded.
  - readme: https://github.com/AgentDock/AgentDock (fetched 2026-08-28T04:05:24.287022+00:00, sha 62e6a26503d1)
  - homepage: https://agentdock.ai (fetched 2026-08-29T11:12:34.053314+00:00, sha d4eb3fc5fbf4)
  - site_page: https://agentdock.ai/docs (fetched 2026-08-29T11:12:34.062524+00:00, sha d4fad8e6a5b6)
  - site_page: https://agentdock.ai/about (fetched 2026-08-29T11:12:34.064389+00:00, sha d03caa7740ed)
  - site_page: https://agentdock.ai/pricing (fetched 2026-08-29T11:12:34.065969+00:00, sha f24363305cf6)
- Data as of 2026-08-30T08:39:29.467469+00:00.