aipotheosis-labs/

aci

GitHub Website

ACI.dev is an open-source tool-calling platform that connects 600+ tools to agentic IDEs or AI agents, with a unified MCP server option and a Python SDK. It emphasizes multi-tenant authentication, permissions, and tool discovery, under Apache-2.0.

4.8kstars

464forks

62issues

Apache-2.0license

2024since

Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap

Graphify-Labs/

graphify

▲ 4.6k/wk

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

102k9.9kPython

affaan-m/

ECC

▲ 2.9k/wk

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

238k36kJavaScript

ComposioHQ/

awesome-claude-skills

▲ 585/wk

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

72k8.1kPython

langchain-ai/

langchain

▲ 595/wk

The agent engineering platform.

143k24kPython

mem0ai/

mem0

▲ 565/wk

Universal memory layer for AI Agents

63k7.3kPython

Significant-Gravitas/

AutoGPT

▲ 72/wk

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

186k46kPython

Compareaci vs graphify aci vs ECC aci vs awesome-claude-skills

Reviewgenerated from repository data · Aug 5, 2026

What it is

ACI.dev is an open-source tool-calling platform that hooks up 600+ tools into agentic IDEs or AI agents, exposing capabilities as direct function calls or via a Unified Model-Context-Protocol (MCP) server. It supports multi-tenant authentication, granular permissions, and dynamic tool discovery, with implementations available as a Unified MCP server or a lightweight Python SDK. The project targets integration with various platforms (e.g., Vercel, Supabase, Cloudflare) and emphasizes open-source tooling for VibeOps and dev automation.

How it works

The repo provides an open-source framework to manage tool authentication, permissions, and discovery for AI agents. Tools can be invoked either through direct function calls or via a unified MCP server, enabling centralized management of integrations and authentication flows. It highlights support for multi-tenant OAuth and dynamic tool provisioning.

Getting started

Getting started involves examining component READMEs for local development:

Backend: backend/README.md
Frontend: frontend/README.md

The README indicates these components can be run locally, with the full platform consisting of backend and frontend parts, each having its own setup steps.

Recent releases

v0.0.1-beta.3 (2024-12-01): Remove TrustedHostMiddleware for aws ALB health check to work.
v0.0.1-beta.2 (2024-12-01): hide routes from /docs that are not for programmatical access
v0.0.1-beta.1 (2024-11-30): A mvp with a few search apis indexed for private beta testing.

Traction

Stars: 4823 Forks: 464 Open issues: 62

Behind the repo

Not provided in the README snippet beyond links to MCP server, Python SDK, and related components. No corporate or startup linkage is specified in the FACTS block.

Caveats

License: Apache-2.0 Created: 2024-09-19 Last push: 2026-05-28 Language: Python

SharePost on X LinkedIn