# fim-ai/fim-one

Open-source agent platform for Global × China enterprises — wire every system through one agent core. Self-hosted, any LLM.

Repository: https://github.com/fim-ai/fim-one
Canonical: https://ross.abutalabs.com/products/fim-one
Homepage: https://one.fim.ai
Language: Python
License: NOASSERTION
License Family: other
Topics: ai-agents, connector, llm, mcp, rag, ai, ai-agent, dag, fastapi, function-calling, nextjs, openai-compatible, python, react-agent, tool-use
Last push: 2026-08-26T18:29:29+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 13
- inputs: {"age_days": 192, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1452, forks 161 (observed 2026-08-28T04:04:46.481037+00:00)

## What it is
FIM One is a source-available, self-hostable agent platform that connects enterprise systems (global SaaS plus the China stack like Feishu, WeCom, DingTalk) through a single agent core with connectors, DAG-based orchestration, RAG, and human-in-the-loop review. It ships as a Python/FastAPI backend with a Next.js frontend, deploys via Docker Compose, works with any OpenAI-compatible LLM, and offers standalone, copilot, and hub delivery modes.

## Use cases
- connect erp crm and internal systems to an ai agent
- self-hosted ai agent platform that keeps data on my network
- orchestrate multi-step tasks across enterprise tools with human approval
- build a copilot embedded in my existing web app
- chat with my company knowledge base with cited sources
- bridge global saas and china tools like feishu dingtalk wecom with one agent
- run ai workflows against my database with tool calling

## When to choose
- you need a self-hosted agent platform where data never leaves your network
- you must integrate both global SaaS and China enterprise stack (Feishu, WeCom, DingTalk) in one agent
- you want connectors, RAG, DAG orchestration, and human-in-the-loop review out of the box
- you want to embed a copilot into an existing system's UI

## When to avoid
- you need a permissively licensed (MIT/Apache) library to embed in your own product
- you only want a lightweight agent framework or SDK rather than a full platform with UI and database
- you plan to white-label or run multi-tenant commercial deployments without a commercial license
- you need a fully open-source (OSI-approved) project for compliance reasons

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, rag, mcp, llm-inference, workflow-automation, web-framework, chatbot, plugin-system
- domain: large-language-models, self-hosted, erp, developer-tools
- platform: python, self-hosted, cross-platform
- tags: react-agent, dag-planner, function-calling, openai-compatible, connector-platform, human-in-the-loop, china-stack, fastapi, nextjs, source-available, copilot, tool-use, ai-agents, retrieval-augmented-generation, automation, docker, web-server, nodejs

## Member repositories
- fim-ai/fim-one (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:46.481037+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 2026-08-30T04:35:47.829024+00:00, confidence not recorded.
  - readme: https://github.com/fim-ai/fim-one (fetched 2026-08-28T04:04:46.481037+00:00, sha 6af5f42c0529)
  - homepage: https://one.fim.ai (fetched 2026-08-29T11:45:14.298081+00:00, sha a3db40448092)
  - site_page: https://one.fim.ai/en/docs (fetched 2026-08-29T11:45:14.307917+00:00, sha 31c015640ec3)
  - site_page: https://one.fim.ai/en/about (fetched 2026-08-29T11:45:14.312042+00:00, sha 1536ce08e682)
  - site_page: https://docs.one.fim.ai/quickstart (fetched 2026-08-29T11:45:14.314022+00:00, sha 713d97395011)
  - site_page: https://docs.one.fim.ai (fetched 2026-08-29T11:45:14.316107+00:00, sha 833781d4df4c)
  - site_page: https://one.fim.ai/en/pricing (fetched 2026-08-29T11:45:14.310094+00:00, sha 52f2cc566a0f)
- Data as of 2026-08-30T08:39:29.467469+00:00.