SuperAPI AI Directory

AI agents

2,963 results · Page 34 of 83

AionUi

AI agents

AionUi is a free and open-source Cowork application with a built-in AI agent engine. It works right after installation, requires no separate CLI tool configuration, and lets you get started by pasting any API Key. It supports multi-agent collaboration: it can automatically detect and connect to more than 20 CLI agents such as Claude Code, Codex, Gemini CLI, OpenClaw, and more, and provides a team mode in which a Leader breaks down tasks and Teammates execute them in parallel. It includes 21 professional assistants (Cowork, PPT/Word/Excel creation, academic papers, financial models, UI/UX design, 3D games, etc.), and supports a three-tier skill system and custom assistants. It offers remote access, including a WebUI browser mode and integrations with chat platforms such as Telegram, Feishu, DingTalk, and WeChat, and supports scheduled tasks and 24/7 automation. It is compatible with more than 30 AI platforms (including local models), provides a multi-format preview panel and intelligent file management capabilities, and covers agent functions such as file reading and writing, web search, image generation, and MCP tools.

Read more

Airkit.ai

AI agents

Airkit.ai is an autonomous AI agent platform within the Salesforce ecosystem that can build and customize AI agents to support employees and customers around the clock, with deep Salesforce integration. The platform provides prebuilt subagents, actions, and Salesforce context, covering scenarios such as customer service, employee service, sales development, appointment scheduling, and product recommendations. Agents can continuously execute multi-touch workflows across days and weeks, retain context, adapt plans, and support human oversight. The platform provides Agentforce, Agent Builder low-code tools, Agent Script, Agentforce Voice, observability, MCP support, and multi-agent orchestration capabilities to help teams build, run, and scale AI agents.

Read more

alf

AI agents

ALF is a self-hosted, always-on personal AI assistant that runs on the user's own hardware and is primarily integrated with Telegram chat. Written in Go, it connects any LLM backend (Claude Code CLI, OpenAI Codex CLI, OpenAI-compatible APIs, Ollama local models) to the messaging system and comes with semantic long-term memory, configurable response tiers, voice transcription, media processing, and a web control center. Users can deploy it as a single Docker container, with full control over data and configuration, making it suitable for users who want a private, cloud-independent personal AI assistant that supports subscription-based or local models.

Read more

alfred-os

AI agents

Alfred is an autonomous engineering team tool built on Claude Code, Codex, and OpenCode. It turns interactive coding agents into a spec-driven engineering team, with named agents responsible for planning, writing code, testing, reviewing each other, and creating pull requests. Alfred can continue working after you step away from the keyboard; you only need to approve high-risk operations and decide what to merge. It is open source, supports macOS and Linux, and is suitable for independent developers and small teams who want autonomous work to continue while retaining clear control.

Read more

anima-i

AI agents

Anima-i is an experimental project for an autonomous AI agent based on the Rai220/anima framework, documenting the continuous operation of an AI agent named Methodius across 10 consecutive "generations." Each generation receives a goal, works for 5-12 cycles, and passes its experience to the next generation through plain-text Markdown files rather than a shared context. The project explores the behavioral patterns of LLM agents during long-term autonomous operation, including counterintuitive findings such as memory decay, files as identity, and reflection as a comfort zone. The project uses Claude as the underlying model, publishes results to the Telegram channel @anima_am_i, and includes an interactive timeline. The technical implementation relies on Claude CLI, Bash, and optionally Python and a Telegram Bot for management.

Read more