LOCAL AGENT

AI that stays where it belongs — on your machine.

TAKE BACK CONTROL

LocalAgent is an AI platform that runs 100% on your hardware. No clouds. No data sharing. No compromises.

Built for those who value privacy as non-negotiable, LocalAgent lets you deploy intelligent agents that never phone home. Your data stays where you put it — period. Are you tired of agent wrappers to cloud APIs? me too.

WHY LOCALAGENT?

• ✓ TRUE PRIVACY — Everything runs on your hardware, nothing leaves your machine
• ✓ MODEL FREEDOM — Works with local LLM formats (GGUF, GGML) you already have
• ✓ BUILD YOUR WAY — Extensible architecture for custom agents with specialized skills
• ✓ SLICK INTERFACE — Clean web UI for hassle-free agent interactions
• ✓ DEV-FRIENDLY — Comprehensive REST API for seamless integration
• ✓ PLAYS WELL WITH OTHERS — Optimized for LocalAI
• ✓ RUN ANYWHERE — Linux, macOS, Windows — we've got you covered

THE LOCAL ECOSYSTEM

LocalAgent is part of a trinity of tools designed to keep AI under your control:

• LocalAI — Run LLMs on your hardware
• LocalRAG — Local Retrieval-Augmented Generation
• LocalAgent — Deploy AI agents that respect your privacy

Features

Powerful WebUI

Connectors ready-to-go

QUICK START

One-Command Docker Setup

The fastest way to get everything running — LocalRAG, LocalAI, and LocalAgent pre-configured:

docker-compose up

No API keys. No cloud subscriptions. No external dependencies. Just AI that works.

Manual Launch

Run the binary and you're live:

./localagent

Access your agents at http://localhost:3000

Environment Configuration

Variable	What It Does
LOCALAGENT_MODEL	Your go-to model
LOCALAGENT_MULTIMODAL_MODEL	Optional model for multimodal capabilities
LOCALAGENT_LLM_API_URL	OpenAI-compatible API server URL
LOCALAGENT_API_KEY	API authentication
LOCALAGENT_TIMEOUT	Request timeout settings
LOCALAGENT_STATE_DIR	Where state gets stored
LOCALAGENT_LOCALRAG_URL	LocalRAG connection
LOCALAGENT_ENABLE_CONVERSATIONS_LOGGING	Toggle conversation logs
LOCALAGENT_API_KEYS	A comma separated list of api keys used for authentication

INSTALLATION OPTIONS

Pre-Built Binaries

Download ready-to-run binaries from the Releases page.

Source Build

Requirements:

• Go 1.20+
• Git

# Clone repo
git clone https://github.com/mudler/LocalAgent.git
cd LocalAgent

# Build it
go build -o localagent

# Run it
./localagent

CONNECTORS

Link your agents to the services you already use. Configuration examples below.

GitHub Issues

{
  "token": "YOUR_PAT_TOKEN",
  "repository": "repo-to-monitor",
  "owner": "repo-owner",
  "botUserName": "bot-username"
}

Discord

After creating your Discord bot:

{
  "token": "Bot YOUR_DISCORD_TOKEN",
  "defaultChannel": "OPTIONAL_CHANNEL_ID"
}

Don't forget to enable "Message Content Intent" in Bot(tab) settings! Enable " Message Content Intent " in the Bot tab!

Slack

Use the included slack.yaml manifest to create your app, then configure:

{
  "botToken": "xoxb-your-bot-token",
  "appToken": "xapp-your-app-token"
}

• Create Oauth token bot token from "OAuth & Permissions" -> "OAuth Tokens for Your Workspace"
• Create App level token (from "Basic Information" -> "App-Level Tokens" ( scope connections:writeRoute authorizations:read ))

Telegram

Get a token from @botfather, then:

{ 
  "token": "your-bot-father-token" 
}

IRC

Connect to IRC networks:

{
  "server": "irc.example.com",
  "port": "6667",
  "nickname": "LocalAgentBot",
  "channel": "#yourchannel",
  "alwaysReply": "false"
}

REST API

Agent Management

Endpoint	Method	Description	Example
/agents	GET	List all available agents	Example
/status/:name	GET	View agent status history	Example
/create	POST	Create a new agent	Example
/delete/:name	DELETE	Remove an agent	Example
/pause/:name	PUT	Pause agent activities	Example
/start/:name	PUT	Resume a paused agent	Example
/settings/export/:name	GET	Export agent config	Example
/settings/import	POST	Import agent config	Example
/api/agent/:name/config	GET	Get agent configuration
/api/agent/:name/config	PUT	Update agent configuration

Chat Interactions

Endpoint	Method	Description	Example
/chat/:name	POST	Send message & get response	Example
/notify/:name	GET	Send notification to agent	Example
/sse/:name	GET	Real-time agent event stream	Example
/v1/responses	POST	Send message & get response	OpenAI's Responses

Curl Examples

Get All Agents

curl -X GET "http://localhost:3000/agents"

Get Agent Status

curl -X GET "http://localhost:3000/status/my-agent"

Create Agent

curl -X POST "http://localhost:3000/create" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "my-agent",
    "model": "gpt-4",
    "system_prompt": "You are an AI assistant.",
    "enable_kb": true,
    "enable_reasoning": true
  }'

Delete Agent

curl -X DELETE "http://localhost:3000/delete/my-agent"

Pause Agent

curl -X PUT "http://localhost:3000/pause/my-agent"

Start Agent

curl -X PUT "http://localhost:3000/start/my-agent"

Export Agent

curl -X GET "http://localhost:3000/settings/export/my-agent" --output my-agent.json

Import Agent

curl -X POST "http://localhost:3000/settings/import" \
  -F "file=@/path/to/my-agent.json"

Send Message

curl -X POST "http://localhost:3000/chat/my-agent" \
  -H "Content-Type: application/json" \
  -d '{"message": "Hello, how are you today?"}'

Notify Agent

curl -X GET "http://localhost:3000/notify/my-agent" \
  -d "message=Important notification"

Agent SSE Stream

curl -N -X GET "http://localhost:3000/sse/my-agent"

Note: For proper SSE handling, you should use a client that supports SSE natively.

Agent Configuration Reference

{
  "name": "my-agent",
  "model": "gpt-4",
  "multimodal_model": "gpt-4-vision",
  "hud": true,
  "standalone_job": false,
  "random_identity": false,
  "initiate_conversations": true,
  "enable_planning": true,
  "identity_guidance": "You are a helpful assistant.",
  "periodic_runs": "0 * * * *",
  "permanent_goal": "Help users with their questions.",
  "enable_kb": true,
  "enable_reasoning": true,
  "kb_results": 5,
  "can_stop_itself": false,
  "system_prompt": "You are an AI assistant.",
  "long_term_memory": true,
  "summary_long_term_memory": false
}

LICENSE

MIT License — See the LICENSE file for details.

---

LOCAL PROCESSING. GLOBAL THINKING.
Made with ❤️ by mudler