# TaskingAI/TaskingAI

The open source platform for AI-native application development.

Repository: https://github.com/TaskingAI/TaskingAI
Canonical: https://ross.abutalabs.com/products/taskingai
Homepage: https://www.tasking.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ai, ai-native, generative-ai, gpt, llm, vector, rag, retrieval-augmented-generation, agent, function-call, langchain
Last push: 2024-12-02T22:18:38+00:00

## Health v2 (maintenance only)
Score: 17/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 69
- inputs: {"age_days": 968, "days_push": 639, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5401, forks 356 (observed 2026-08-28T04:09:17.516502+00:00)

## What it is
TaskingAI is an open-source Backend-as-a-Service (BaaS) platform for developing and deploying LLM-based AI agents. It unifies access to hundreds of LLM models through a single API and provides a console UI for managing tools, RAG systems, assistants, and conversation history.

## Use cases
- build ai agents with rag over my own documents
- unified api to access multiple llm providers
- self-host an openai-like assistant platform
- add function calling tools to a chatbot
- prototype llm apps in a console then deploy via rest api
- manage conversation history and assistants for a chat app

## When to choose
- you want a self-hosted all-in-one platform for LLM agent development
- you need unified APIs across many model providers plus built-in RAG and tools
- you want to separate AI backend logic from client-side product development

## When to avoid
- you only need a lightweight SDK or library without a hosted server
- you require a fully managed cloud service with SLAs
- your project needs deep customization beyond the platform's module abstractions

## Facets
- artifact type: service
- maturity: active
- function: agent-framework, rag, llm-inference, chatbot, api-framework, self-hosted
- domain: artificial-intelligence, large-language-models, chatbots, developer-tools, self-hosted
- platform: self-hosted, python, cross-platform
- tags: backend-as-a-service, llm-platform, unified-model-api, function-calling, assistant-api, openai-alternative, ai-agents, retrieval-augmented-generation, docker, web-server

## Member repositories
- TaskingAI/TaskingAI (main) score 17

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:17.516502+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 2026-08-29T17:57:48.576939+00:00, confidence not recorded.
  - readme: https://github.com/TaskingAI/TaskingAI (fetched 2026-08-28T04:09:17.516502+00:00, sha bc01bbc4ff7e)
- Data as of 2026-08-30T08:39:29.467469+00:00.