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 237
- 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 - 0.634score
zero
Twigpine
Terminal coding agent that edits files and runs commands, lets you pick the model and permission level, and runs on your machine.
AgentAFreshness: A★ 1.7K - 0.633score
agtx
fynnfluegge
Terminal kanban board that assigns tasks to several coding agents and hands work between them by phase.
AgentAFreshness: A★ 1.7K - 0.633score
zerostack
gi-dellav
Minimal coding agent written in Rust with multi-provider models, a permission system, MCP support and session resume.
AgentAFreshness: A★ 1.7K - 0.631score
ouroboros
razzant
Open-source desktop and CLI agent that keeps its identity, memory and history across tasks and can modify the code it runs on.
AgentAFreshness: A★ 1.6K - 0.628score
GPT Pilot
Pythagora
Unmaintained AI developer project that builds apps and is the core of the Pythagora VS Code extension
AgentCFreshness: C★ 33.6K - 0.627score
lime
limecloud
Open-source full-stack agent with a desktop app and a CLI/TUI for coding, files, research and content work.
AgentAFreshness: A★ 1.5K - 0.627score
Aider
Aider
Terminal-based AI pair programmer that edits code in your local git repo and works with most cloud and local LLMs
AgentCFreshness: C★ 49.7K↓ 64K/wk - 0.626score
agor
preset-io
Web workspace where teams and coding agents share live spatial boards, with each git branch running its own agent sessions.
AgentAFreshness: A★ 1.5K - 0.625score
Empryo
proxysoul
Coding harness for desktop, terminal and CI that maps a repository and edits code by symbol before running your checks.
AgentAFreshness: A★ 1.5K - 0.623score
openharness
autonomous-ai
Open-source desktop command center for coding agents across your machines, with tmux sessions and end-to-end encrypted links.
AgentAFreshness: A★ 1.4K - 0.622score
Onlook
Onlook
Open-source visual editor for designing Next.js and Tailwind apps with AI chat and direct edits in the browser
AgentCFreshness: C★ 27K - 0.618score
openclacky
clacky-ai
Open-source agent (MIT) that works with any OpenAI-compatible model, keeps a 16-tool core and loads skills on demand
AgentAFreshness: A★ 1.2K - 0.617score
SWE-agent
Princeton & Stanford
Research agent from Princeton and Stanford that lets a language model fix GitHub issues and other tasks by using tools on its own
AgentCFreshness: C★ 20.6K - 0.616score
MiniCode
LiuMengxuan04
Lightweight terminal coding assistant with a tool loop and TUI, offered as TypeScript, Python and Rust versions
AgentAFreshness: A★ 1.2K - 0.616score
II-Agent
Intelligent Internet
Open-source AI agent for building apps and sites, doing research, and producing documents and slides, runnable locally with your own keys.
AgentBFreshness: B★ 3.4K - 0.616score
Mysti
DeepMyst
VS Code extension that runs Claude Code, Codex and other agents side by side, passes work between them and keeps one conversation
AgentAFreshness: A★ 1.1K - 0.613score
loki-mode
asklokesh
Autonomous coding agent that turns a task or GitHub issue into a verified pull request with a signed receipt
AgentAFreshness: A★ 1.1K - 0.613score
Meldwork
Ryder-Sun
Local-first macOS desktop app that runs one task across several agent CLIs, collects their findings and gates file writes behind approval
AgentAFreshness: A★ 1.1K - 0.612score
thinkrail
JetBrains
Agentic IDE built around the pi coding agent, with isolated git-worktree workspaces, living specs and MCP support
AgentAFreshness: A★ 1.1K - 0.611score
parallel-code
johannesjo
Desktop app that runs Claude Code, Codex and other coding agents in parallel, each in its own git worktree
AgentAFreshness: A★ 1.1K - 0.610score
codeAgent
Harvil1
Python terminal coding agent with DeepSeek by default, MCP tools, sub-agents, approval prompts and reusable learned skills
AgentAFreshness: A★ 1K - 0.610score
easy-agent
ConardLi
Terminal coding agent with permission rules, OS sandboxing, MCP, skills and sub-agents, for Anthropic, OpenAI-compatible, Gemini and local models
AgentAFreshness: A★ 1K - 0.609score
little-coder
itayinbarr
Coding agent tuned for small local models, built on the pi agent harness and run from the terminal.
AgentBFreshness: B★ 2.7K