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 73–96 of 102
- 0.564score
clay
chadbyte
Self-hosted workspace where people and coding agents share projects, live sessions and persistent Mates across providers.
AgentAFreshness: A★ 405 - 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 - 0.563score
clodex-ide
mereyabdenbekuly-ctrl
Local-first open-source desktop IDE for long-running agent work, with code, Git, terminal, browser and MCP in one workspace
AgentBFreshness: B★ 870 - 0.561score
WrongStack
WrongStack
MIT-licensed AI coding agent with terminal, TUI and browser interfaces, durable project memory and specialist subagents.
AgentAFreshness: A★ 392 - 0.561score
marvis-risk-agent
eddyzzl
Local-first credit-risk agent that turns data files into governed analysis, models, strategy code and audit-ready reports.
AgentAFreshness: A★ 390 - 0.559score
codai
meysamhadeli
Open-source .NET terminal coding agent with a read-only Plan mode, approval for writes and commands, and many model providers.
AgentAFreshness: A★ 374 - 0.559score
runner
yicheng47
Desktop app that runs Claude Code, Codex, Copilot CLI and pi side by side as crews on one shared mission feed, in real terminals.
AgentAFreshness: A★ 370 - 0.558score
useagent
useagenthq
Open-source Devin alternative that runs Claude Code, Codex, OpenCode or Pi in isolated workspaces you can self-host.
AgentAFreshness: A★ 365 - 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 - 0.557score
Open-AutoGLM
Z.ai
Open phone-agent framework and models from Z.ai that control Android, HarmonyOS and iOS devices from natural-language requests
AgentDFreshness: D★ 26.5K - 0.552score
openyak
openyak
Local desktop app that wraps Codex and Claude Code with a shared browser, a file viewer and one conversation across agents.
AgentBFreshness: B★ 694 - 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 - 0.544score
solo
solo-agent
Open-source, local-first workspace where humans and AI coding agents coordinate through channels, tasks and persistent memory.
AgentBFreshness: B★ 594 - 0.542score
shob
shobcoder
AI agent workspace for developers that runs parallel coding sessions with approval prompts, Git context and subagents.
AgentBFreshness: B★ 578 - 0.535score
pr-cockpit
taovc
Local desktop and web workbench that reviews a repo's pull requests with Claude or Codex in isolated worktrees and posts only approved comments.
AgentBFreshness: B★ 485 - 0.534score
pigo
smallnest
Go reimplementation of the pi coding agent with headless and REPL modes, skills, plugins and multi-provider support.
AgentBFreshness: B★ 483 - 0.532score
Linghun
linghungegeg
Local-first AI coding terminal that grounds model output in real files, tools, permission checks and verification steps.
AgentBFreshness: B★ 459 - 0.530score
openmozi
spytensor
Desktop AI agent that runs on your machine, edits project files and runs commands, and produces Word, Excel, PowerPoint and PDF files.
AgentBFreshness: B★ 445 - 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 - 0.522score
deepx-code
itmisx
Single-binary, DeepSeek-native terminal coding agent with a code graph, local OCR, model routing and an OS sandbox.
AgentBFreshness: B★ 393 - 0.518score
SuperCoder
TransformerOptimus
Local-first open-source desktop coding agent that uses your own LLM key and can index repos with an optional context engine
AgentCFreshness: C★ 999 - 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 - 0.515score
klaatcode
KlaatAI
Terminal coding agent with per-request model routing across six cost tiers, a code graph and spend monitoring, served by a hosted router.
AgentBFreshness: B★ 354