# mudler/LocalAGI

LocalAGI is a powerful, self-hostable AI Agent platform designed for maximum privacy and flexibility. A complete drop-in replacement for OpenAI's Responses APIs with advanced agentic capabilities. No clouds.  Local AI that works on consumer-grade hardware (CPU and GPU).

Repository: https://github.com/mudler/LocalAGI
Canonical: https://ross.abutalabs.com/products/localagi
Language: Go
License: MIT
License Family: permissive
Last push: 2026-08-25T17:43:00+00:00

## Health v2 (maintenance only)
Score: 90/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 83, longevity 80
- inputs: {"age_days": 1133, "days_push": 8, "days_rel": 117, "gap_med": 28, "n_releases_24m": 12}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1961, forks 289 (observed 2026-08-28T04:05:59.464523+00:00)

## What it is
LocalAGI is a self-hostable, privacy-focused AI agent platform written in Go that lets users create no-code agents, automations, and chatbots running entirely on local CPU/GPU hardware. It exposes an OpenAI Responses API-compatible endpoint per agent, supports MCP and skills, includes RAG-based knowledge bases, and offers connectors to Telegram, Discord, Slack, GitHub, and IRC.

## Use cases
- run ai agents locally without cloud api keys
- self-host a private chatgpt alternative
- create no-code ai automations on my own hardware
- build a telegram or discord ai bot that stays private
- drop-in replacement for openai responses api
- add rag knowledge base to local llm agents
- orchestrate cooperative ai agent teams
- connect local llm to mcp tools

## When to choose
- you need agents that run 100% locally on consumer CPU/GPU hardware
- privacy is a hard requirement and no data may leave your machine
- you want no-code agent creation via a web UI
- you need OpenAI Responses API compatibility for local models
- you want built-in chat platform connectors and RAG out of the box

## When to avoid
- you need a lightweight Python agent library to embed in your own code
- you rely on cloud-only models or managed infrastructure
- you need a battle-tested enterprise agent framework with large ecosystem
- your workflow depends on features of cloud agent platforms not replicated here

## Facets
- artifact type: application
- maturity: active
- function: agent-framework, rag, chatbot, llm-inference, mcp, api-framework, web-framework, workflow-automation
- domain: artificial-intelligence, large-language-models, chatbots, self-hosted, privacy
- platform: self-hosted, windows, cross-platform, cli
- tags: no-code-agents, openai-responses-api, local-ai, agent-teams, telegram-bot, discord-bot, slack-integration, knowledge-base, consumer-hardware, go, ai-agents, retrieval-augmented-generation, automation, docker, linux, macos, web-server, gpu

## Member repositories
- mudler/LocalAGI (main) score 90

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:59.464523+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 2026-08-30T03:05:39.219670+00:00, confidence not recorded.
  - readme: https://github.com/mudler/LocalAGI (fetched 2026-08-28T04:05:59.464523+00:00, sha 8a333f7c43d8)
- Data as of 2026-08-30T08:39:29.467469+00:00.