# inkeep/agents

Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.

Repository: https://github.com/inkeep/agents
Canonical: https://ross.abutalabs.com/products/inkeep-agents
Homepage: https://docs.inkeep.com
Language: TypeScript
License: NOASSERTION
License Family: other
Topics: agent, agent-builder, agent-framework, ai-agents, mulit-agent, no-code, workflows, agents-sdk, ai, ai-agent, aiagentframework, developer-sdk, inkeep, llms, low-code, mcp, mcp-server, self-hosted, typescript, workflow
Last push: 2026-08-26T18:55:29+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 67, longevity 25
- inputs: {"age_days": 362, "days_push": 7, "days_rel": 140, "gap_med": 0.0, "n_releases_24m": 991}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1390, forks 167 (observed 2026-08-28T04:04:35.309029+00:00)

## What it is
Inkeep Agents is an open-source platform for building AI chat assistants and multi-agent workflows using either a no-code drag-and-drop Visual Builder or a TypeScript SDK, with full two-way sync between the two. It includes a REST API for agent configuration and execution, MCP tool integration with credential management, observability via OpenTelemetry and a Traces UI, and deployment via Vercel or Docker.

## Use cases
- build a customer support chatbot for docs and help centers without writing code
- create multi-agent AI workflows with a TypeScript SDK and version control
- let non-technical teammates edit agents built by engineers in a visual canvas
- connect agents to external tools and APIs via MCP servers
- automate repetitive tasks like triaging helpdesk tickets or updating CRMs
- self-host an AI assistant platform with Docker and OpenTelemetry observability
- trigger agents programmatically via chat API, MCP, or A2A protocols

## When to choose
- you need both no-code editing for business teams and code-first SDK workflows for engineers on the same agents
- you want to build customer-facing chat assistants or internal copilots with multi-agent architectures
- your tools and integrations are exposed via MCP servers and you need credential management
- you want self-hosted deployment on Vercel or Docker with OpenTelemetry tracing
- you need to trigger agents via APIs, webhooks, Slack, or agent-to-agent protocols

## When to avoid
- you only need a lightweight agent library without a visual builder or hosted management UI
- you need a managed RAG/search platform with enterprise support out of the box (that requires the paid Enterprise tier)
- your stack is Python-first and you want a Python agent SDK rather than TypeScript
- you need a simple single-agent script with no platform, API, or UI overhead

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, mcp, chatbot, workflow-automation, web-framework, api-framework, chat-interface, monitoring, self-hosted, developer-tools
- domain: artificial-intelligence, large-language-models, chatbots, developer-tools, self-hosted, web-development
- platform: self-hosted, cloud
- tags: no-code, low-code, visual-builder, multi-agent, two-way-sync, mcp-server, a2a, vercel-ai-sdk, opentelemetry, traces-ui, sub-agents, agent-credentials, chat-components, slack-integration, customer-support, helpdesk-automation, crm-automation, knowledge-base, typescript-sdk, agent2agent, ai-agents, automation, typescript, nodejs, docker, web-server

## Member repositories
- inkeep/agents (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:35.309029+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 2026-08-30T04:39:39.044032+00:00, confidence not recorded.
  - readme: https://github.com/inkeep/agents (fetched 2026-08-28T04:04:35.309029+00:00, sha fc8bef405d7b)
  - homepage: https://docs.inkeep.com (fetched 2026-08-29T11:55:03.045718+00:00, sha 3c582a5762e9)
  - site_page: https://docs.inkeep.com/pricing (fetched 2026-08-29T11:55:03.057179+00:00, sha cb6dcb007dd2)
  - site_page: https://docs.inkeep.com/concepts (fetched 2026-08-29T11:55:03.059738+00:00, sha a41c4418fa23)
- Data as of 2026-08-30T08:39:29.467469+00:00.