# aipotheosis-labs/aci

ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.

Repository: https://github.com/aipotheosis-labs/aci
Canonical: https://ross.abutalabs.com/products/aci
Homepage: https://www.aci.dev/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: agents, ai, integration, llm, mcp, open-source, tools, ai-agents, developer-tools, function-calling, api, oauth2, permissions, vibeops
Last push: 2026-05-28T11:32:35+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 84, release rhythm 40, longevity 50
- inputs: {"age_days": 713, "days_push": 97, "days_rel": 640, "gap_med": 0.0, "n_releases_24m": 3}
- flags: prerelease_only
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4885, forks 484 (observed 2026-08-28T04:09:01.884244+00:00)

## What it is
ACI.dev is an open-source tool-calling platform that connects 600+ SaaS tools to AI agents and agentic IDEs via direct function calling or a unified MCP server. It handles multi-tenant OAuth authentication, granular permissions, and dynamic tool discovery, with a Python SDK for LLM frameworks.

## Use cases
- give my AI agent access to Slack and Google Calendar without writing OAuth flows
- add a unified MCP server to Cursor or another agentic IDE
- manage tool permissions for multi-tenant AI agents
- discover and call SaaS APIs dynamically from an LLM agent
- automate devops provisioning and deployment through an AI agent
- connect 600+ tools to a custom AI agent via function calling

## When to choose
- you need secure, multi-tenant tool access for AI agents without building per-service OAuth and API clients
- you want a single unified MCP server instead of configuring many separate MCP servers
- you need dynamic tool discovery and granular permission control for agents
- you want to self-host open-source agent tooling infrastructure

## When to avoid
- you only need one or two simple API integrations and can call them directly
- you need a fully managed SaaS with no self-hosting involvement
- your project is not agent/LLM-based and just needs plain API clients

## Facets
- artifact type: service
- maturity: active
- function: mcp, agent-framework, auth, authorization, api-framework, sdk
- domain: large-language-models, developer-tools, apis
- platform: python, self-hosted
- tags: tool-calling, function-calling, oauth2, unified-mcp-server, tool-integration, multi-tenant, vibeops, open-source, ai-agents, automation, docker, web-server

## Member repositories
- aipotheosis-labs/aci (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:01.884244+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 2026-08-29T18:18:14.085819+00:00, confidence not recorded.
  - readme: https://github.com/aipotheosis-labs/aci (fetched 2026-08-28T04:09:01.884244+00:00, sha b4532801921b)
  - homepage: https://www.aci.dev/ (fetched 2026-08-29T09:00:32.690999+00:00, sha 5dae66c7b03b)
  - site_page: https://www.aci.dev/about (fetched 2026-08-29T09:00:32.700110+00:00, sha 063f1c2aff05)
- Data as of 2026-08-30T08:39:29.467469+00:00.