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 49–72 of 190
- 0.663score
command-code
CommandCodeAI
Terminal coding agent that learns from accept, reject and edit decisions through its taste model.
AgentAFreshness: A★ 4.2K - 0.661score
golutra
golutra
Desktop workspace that runs several existing CLI coding agents in parallel with shared workflows.
AgentAFreshness: A★ 3.9K - 0.660score
VulnClaw
Netw0rkNoob
Open-source AI penetration-testing agent that runs recon, exploitation and reporting from natural language.
AgentAFreshness: A★ 3.8K - 0.659score
Letta Code
Letta
Stateful agent harness whose agents keep memory across sessions and run on schedules through a CLI, browser and chat apps.
AgentAFreshness: A★ 3.7K - 0.658score
claude_codex_bridge
SeemSeam
Lightweight terminal workspace that coordinates Codex, Claude, Gemini and other CLI coding agents.
AgentAFreshness: A★ 3.6K - 0.657score
Maestro
RunMaestro
Cross-platform desktop app that orchestrates parallel coding agents, playbooks and phone control.
AgentAFreshness: A★ 3.5K - 0.657score
mercury-agent
cosmicstack-labs
Open-source background agent with local memory, permission rules and chat access from many apps.
AgentAFreshness: A★ 3.5K - 0.656score
atomic-agent
AtomicBot-ai
Open-source local-first agent that runs browser and file tasks on local or cloud models.
AgentAFreshness: A★ 3.4K - 0.656score
OpenOutreach
eracle
Self-hosted B2B lead-finding agent that qualifies people from a product description and emails them.
AgentAFreshness: A★ 3.4K - 0.655score
zeron
zeronsh
Local-first control app for running and following coding agents from a desktop or a Linux server.
AgentAFreshness: A★ 3.3K - 0.655score
gptme
gptme
Open-source terminal AI agent that runs shell, Python and web tools on any model, including local ones.
AgentAFreshness: A★ 4.5K↓ 6.1K/wk - 0.654score
Fuxi
fuxicodex
Go terminal coding agent with cost-aware routing across LLM providers, shipped as one binary.
AgentAFreshness: A★ 3.2K - 0.653score
OpenHands
OpenHands
Open-source platform for running coding agents, with a browser control center, CLI, SDK and self-hosted or cloud backends
AgentAFreshness: A★ 91.7K↓ 34.5K/wk - 0.652score
Pentest-Swarm-AI
Armur-Ai
Open-source, self-hosted swarm of AI agents for authorized API and web-app penetration testing.
AgentAFreshness: A★ 3K - 0.651score
mini-agi
muellerberndt
Minimal Python autonomous agent for GPT-3.5 and GPT-4 with web search, memory and a critic option.
AgentAFreshness: A★ 2.9K - 0.650score
compozy
compozy
Open-source local daemon that runs Claude Code, Codex and Cursor CLIs on cron, webhooks and approvals.
AgentAFreshness: A★ 2.8K - 0.648score
nanocoder
Nano-Collective
Open terminal coding agent that runs on local Ollama models or any OpenAI-compatible API.
AgentAFreshness: A★ 2.5K - 0.644score
PaperQA2
FutureHouse
Retrieval augmented generation package that answers questions from scientific papers and documents with citations.
AgentBFreshness: B★ 9.5K↓ 30.7K/wk - 0.643score
ainovel-cli
voocel
Command-line multi-agent tool that writes a full-length novel from a one-line brief and resumes from saved checkpoints.
AgentAFreshness: A★ 2.2K - 0.642score
XAgent
OpenBMB
Open-source experimental LLM agent that plans tasks and runs tools in a Docker ToolServer.
AgentBFreshness: B★ 8.5K - 0.638score
happier
happier-dev
Open-source web, desktop and mobile control room for running coding agents such as Claude Code and Codex on your own machines.
AgentAFreshness: A★ 2K - 0.638score
ante
AntigmaLabs
Terminal coding agent packaged as a single Rust binary that can run fully offline with a local GGUF model.
AgentAFreshness: A★ 2K - 0.636score
pi_agent_rust
Dicklesworthstone
Rust port of the Pi coding agent CLI with streaming responses, 36 built-in tools and a single binary.
AgentAFreshness: A★ 1.9K - 0.635score
OpenAdapt
OpenAdapt.AI
Open-source layer that turns a recorded task into a replayable program for computer-use agents, with read-back checks on every save
AgentAFreshness: A★ 1.8K