1,572 listed
Agents
Agents that do a job for you: coding agents in your terminal or IDE, research and browser agents, and support, sales and legal agents. Each page says how autonomous it is, where you use it, who hosts it and what it costs, with sources.
Showing 25–48 of 56
- 0.621score
inno-agent
hhyqhh
Open-source personal learning agent with three memory layers, a cron scheduler, Feishu and WeChat channels and a practice lab.
AgentAFreshness: A★ 1.3K - 0.618score
opendroid
yashab-cyber
Autonomous AI agent for Android that plans multi-step phone tasks and controls apps through the accessibility layer
AgentAFreshness: A★ 1.2K - 0.603score
bitterbot-desktop
Bitterbot-AI
Personal agent on your own machine with file-based memory, a background consolidation engine and skills that are tested before use.
AgentAFreshness: A★ 2.5K - 0.596score
anton
mindsdb
Open-source agent harness from MindsHub that runs as the default agent in its Cowork app and standalone in a terminal.
AgentAFreshness: A★ 757 - 0.595score
Cyrene-Agent
Playa-Cyrene
Windows desktop AI companion built on Electron with a Live2D character, long-term memory, voice and tool calling.
AgentAFreshness: A★ 746 - 0.590score
Agent
AgentiLoop
Native macOS AI agent that connects many LLM providers to a task loop that drives apps through Accessibility and builds in Xcode.
AgentAFreshness: A★ 649 - 0.589score
NagaAgent
RTGS2017
Desktop AI assistant with a Live2D avatar, knowledge-graph memory, voice, MCP and skills, under AGPL-3.0 or a commercial license.
AgentBFreshness: B★ 1.5K - 0.589score
sentient-os
Sentient-OS-Labs
Open-source personal AI for macOS that builds an on-device understanding of your work and can take over tasks with its own cursor.
AgentAFreshness: A★ 632 - 0.586score
deepseek-harness-android-app
woaiys3
Installable Android APK of DeepSeek Harness that can operate the phone through Shizuku, root or the accessibility service.
AgentAFreshness: A★ 602 - 0.585score
Lexora
useLexora
Personal desktop AI agent for files, writing, planning and daily tasks, with companions, plugins, scheduled runs and MCP.
AgentAFreshness: A★ 601 - 0.574score
OpenInstinct
Merit-Systems
Self-hosted personal assistant you text over iMessage; it can drive a cloud browser for tasks such as bookings and purchases.
AgentAFreshness: A★ 472 - 0.573score
Amadeus
Code-Amadeus
Open-source desktop agent combining real-time voice chat, a speaking character and delegated work with visible permissions.
AgentAFreshness: A★ 465 - 0.564score
pocketpaw
pocketpaw
Self-hosted personal AI agent with a desktop app and web dashboard that talks over Telegram, Slack, Discord, WhatsApp or the browser
AgentBFreshness: B★ 894 - 0.563score
overtime
ukanwat
Brief-driven runner that keeps coding agents working across sessions and asks only for decisions that are yours.
AgentAFreshness: A★ 399 - 0.563score
open-instinct
mariagorskikh
Open-source personal agent you text over iMessage, running in its own cloud microVM with app connectors and approval-gated payments.
AgentAFreshness: A★ 397 - 0.563score
PhysiClaw
physiclaw
Agent that operates an iPhone with a robot arm, stylus and camera, and takes requests by WhatsApp message.
AgentAFreshness: A★ 397 - 0.558score
home-generative-agent
goruck
Home Assistant integration with a LangGraph agent for conversational control, automation creation, camera analysis and anomaly alerts.
AgentAFreshness: A★ 363 - 0.550score
gini-agent
Open-Curiosity
Personal agent with a Bun gateway that keeps memory, skills and run history, with approval-gated tools and web, CLI and mobile clients.
AgentCFreshness: C★ 2.1K - 0.541score
n8n-claw
freddy-schuetz
Self-hosted AI agent built on n8n, PostgreSQL and Claude that runs over Telegram or a webhook API.
AgentBFreshness: B★ 560 - 0.525score
agent-second-brain
smixs
Always-on personal agent that turns Telegram voice notes into linked markdown notes in your Obsidian vault on a VPS.
AgentBFreshness: B★ 411 - 0.524score
PokeClaw
agents-io
Open-source Android app that runs Gemma 4 on the phone to read the screen and operate apps, with optional cloud models
AgentCFreshness: C★ 1.1K - 0.524score
Abu-Cowork
PM-Shawn
Local-first AI desktop assistant that reads and writes files, runs commands and builds reports on your machine, with skills and IM bots.
AgentBFreshness: B★ 403 - 0.516score
maxheadbox
syxanash
Voice-activated LLM agent for Raspberry Pi that runs Ollama models fully on the device and can run custom tools.
AgentBFreshness: B★ 355 - 0.513score
sutando
sonichi
Open-source Mac personal AI that works through your Claude Code or Codex CLI session, with voice, screen awareness and phone calls.
AgentAFreshness: A★ 400