AI Agents
ruby_llm
The Ruby-native AI framework. Chats, agents, tools, images, audio, and video through one consistent API, in plain Ruby or Rails.
★ 4.4k starsMIT
View guide →// agents · TaskingAI/TaskingAI
TaskingAI
TaskingAI is an open-source ai agents project by TaskingAI (TaskingAI/TaskingAI on GitHub). It has 5,410 GitHub stars and 359 forks, is released under the Apache-2.0 license, and was last updated on GitHub on 2 December 2024.
An open-source platform for AI-native application development — assistants, tools, RAG and models in one API.
★ 5.4k stars⑂ 359 forksApache-2.0updated 2024-12
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- TaskingAI/TaskingAI
- GitHub stars
- 5,410
- Forks
- 359
- License
- Apache-2.0
- Last updated on GitHub
- 2 December 2024
- Category
- AI Agents
- Listing
- Full install guide
- Official site
- Official site
// how it works
How it works
- Clarify your AI app
Decide what your application needs — chat with memory, tool use, retrieval over your data, or all three.
- Deploy the platform
Clone the repo and start the Docker deployment with your .env configuration.
- Configure modules
In the console or API, register your language models, tools and retrieval collections.
- Build your first assistant
Create an assistant from your modules, open a chat through the SDK, and send your first message.
// features
Why people love it
Decoupled modular management
Models, tools and RAG systems are managed independently of assistants and can be freely combined and swapped.
Stateful and stateless usage
Supports managed conversation history and sessions, or simple stateless chat-completion requests.
Multi-tenant support
Designed for fast deployment into multi-tenant products, unlike single-assistant frameworks tied to one vendor.
Unified API
One API surface manages tools, retrieval systems, language models and assistants.
Console and client SDK
A web UI console for configuration plus a Python SDK for creating assistants, chats and messages programmatically.
Model diversity
Not restricted to one vendor's models, addressing the proprietary limitations the project calls out in alternatives.
Advertisement
// run it
Run it yourself
- Clone the repository
Clone TaskingAI and enter the Docker deployment directory.
git clone https://github.com/TaskingAI/TaskingAI.git cd TaskingAI - Configure and start
Copy the example environment file, adjust it, and start the platform.
cd docker cp .env.example .env docker-compose -p taskingai --env-file .env up -d - Use the client SDK
Install the Python client to create assistants and chats against your deployment.
pip install taskingai
// use cases
What you can build
- Building a SaaS product where many tenants each get their own assistant configuration
- Prototyping an assistant that mixes tool use with retrieval over company documents
- Swapping the underlying model for an existing assistant without code changes
- Self-hosting an assistant platform instead of depending on a single vendor's assistant API
Advertisement
// faq
Questions, answered
Who maintains TaskingAI?
TaskingAI is maintained by the TaskingAI team, with the product site at tasking.ai.
Is TaskingAI free?
Yes — it is open source under the Apache-2.0 license for self-hosting.
Does it need a paid API key?
You register your own language models with the platform, so you need credentials for whichever model providers you choose.
How does it compare to OpenAI Assistants?
TaskingAI positions itself against vendor-tied assistants: it is vendor-neutral, supports stateful and stateless use, decouples tools/RAG/models from assistants, and supports multi-tenant deployment.
How do I get started?
Clone the repo, start the Docker Compose deployment, open the console, and create your first assistant.
// keep exploring
Similar tools
AI Agents
RAG-Anything
One RAG framework for everything — including multimodal documents.
★ 23.5k starsMIT
View guide →AI Agents
R2R
Production-ready agentic RAG behind a clean REST API.
★ 8.0k starsMIT
View guide →AI Agents
FrontierAgent
An open agent framework with a native terminal TUI, ReAct and Agent Team modes — one command to run.
★ 5.2k starsApache-2.0
View guide →AI Agents
OpenHands
Open-source AI-driven development platform: autonomous software agents in a sandbox
★ 90.3k starsMIT
View guide →AI Agents
coze-studio
A visual all-in-one platform for building, debugging, and deploying AI agents.
★ 21.7k starsApache-2.0
View guide →// alternatives
Alternatives in AI Agents
The most-starred other AI Agents projects in the LibreAI catalogue — the realistic shortlist if TaskingAI is not the right fit.
- openclaw★ 391.6k
A personal AI that really does things — on any OS, with your data staying yours.
- superpowers★ 294.9k
An agentic skills framework & software development methodology that works.
- ECC★ 275.2k
Agent harness optimization system with skills, memory and security for Claude Code, Codex and more
- hermes-agent★ 252.0k
The agent that grows with you — a Python framework for adaptive AI agents.
- deepseek-harness★ 245.5k
DeepSeek's plugin-based agent harness where everything is a plugin.
// more in agents
More in AI Agents
Nearby AI Agents projects in the catalogue, closest in stars to TaskingAI — keep exploring the shelf either side of it.
- eve★ 5.5k
Vercel's open framework for building agents that run anywhere.
- Raven★ 5.3k
The harness of harnesses: a persistent, self-evolving multi-agent ecosystem built for RSI.
- ruoyi-ai★ 5.7k
Enterprise-grade AI agent framework with multi-provider LLM management, secure knowledge bases and high-precision RAG, visual workflow orchestration, and mul…
- zotero-mcp★ 5.3k
Connect your Zotero research library to Claude and other AI assistants through MCP.
- coze-loop★ 5.8k
A full-lifecycle platform for developing, debugging, evaluating and monitoring AI agents.
- FrontierAgent★ 5.2k
An open agent framework with a native terminal TUI, ReAct and Agent Team modes — one command to run.
Get TaskingAI
Free and open — grab the source, star the repo, and start creating.