Search
Everything in the catalog
Showing 121–144 of 234
- 0.593score
frontman
frontman-ai
Open-source coding agent in the browser that edits frontend source files from clicks and plain-English descriptions.
AgentAFreshness: A★ 719 - 0.592score
Minke
lencx
Local-first desktop agent workspace for DeepSeek Harness, with conversations, files, terminals and a shared browser.
AgentAFreshness: A★ 692 - 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
phi
pulseaiclub
Terminal coding agent written in Go, with sub-agents, MCP support, a permission gate and native diff review.
AgentAFreshness: A★ 635 - 0.589score
avibe
avibe-bot
Local-first agent OS that runs Claude Code, Codex and OpenCode on your machine and lets you drive them from a browser or chat apps.
AgentAFreshness: A★ 632 - 0.588score
shai
ovh
Terminal coding agent written in Rust with a TUI, headless mode, an HTTP server and a shell assistant.
AgentAFreshness: A★ 630 - 0.587score
agentty
agentty-org
Open-source terminal coding agent in one native binary that runs many models, sandboxes shell commands and works in Zed over ACP.
AgentAFreshness: A★ 619 - 0.587score
harness-mix
emo-xiaoyu
Local desktop layer that brings 18 native coding harnesses, including Claude Code, Codex and Pi, into the Codex Desktop UI.
AgentAFreshness: A★ 614 - 0.584score
MyAgents
hAcKlyc
Open-source, local-first desktop workspace for running Claude Agent SDK, DeepSeek Harness or Codex agents with scheduled tasks.
AgentAFreshness: A★ 580 - 0.584score
openteams
openteams-lab
Open-source, local-first desktop app where a team of AI coding agents shares one session, a visible plan and an issue list.
AgentAFreshness: A★ 580 - 0.584score
Pane
greenfield-inc
Open-source, terminal-first manager for running many CLI coding agents in parallel, with worktree handoffs and a phone view.
AgentAFreshness: A★ 580 - 0.583score
wayland
FerroxLabs
Local-first desktop AI agent that drives Claude Code, Codex, Gemini and other AI CLIs from one command center.
AgentAFreshness: A★ 614 - 0.580score
tmux-ide
wavyrai
Open-source workspace that shows the status of coding agents such as Claude Code and Codex running in tmux panes.
AgentAFreshness: A★ 555 - 0.580score
mu
qybaihe
Coding agent built on pi that hands routine decisions to a small judge model, so the main model can focus on the code.
AgentAFreshness: A★ 544 - 0.579score
zhikuncode
zhikunqingtao
Self-hosted open-source AI coding assistant with a CLI and web UI, multi-agent collaboration and Docker deployment.
AgentAFreshness: A★ 528 - 0.578score
Pi-Bolt
opensec-git
The Pi coding agent compiled ahead of time into one native executable for Linux, macOS, Windows and Android (Termux).
AgentAFreshness: A★ 522 - 0.578score
vicoa
vicoa-ai
Open-source AI orchestrator for running a team of coding agents from desktop, mobile and CLI, on any machine.
AgentAFreshness: A★ 521 - 0.577score
orca-agent
echoVic
DeepSeek-native coding agent for the terminal, written in Rust, with a TUI and a headless exec mode for scripts and CI.
AgentAFreshness: A★ 509 - 0.576score
dreamcoder
GoDiao
Locally run, multi-provider AI coding workspace for the desktop, with sessions you can continue from a phone on the same LAN.
AgentAFreshness: A★ 501 - 0.576score
flock
duckbugio
Runs a Claude Code dev team on your server and drives it from Telegram, VK or LO chats, opening a PR per request.
AgentAFreshness: A★ 501 - 0.574score
Arbor
RUC-NLPIR
Autonomous research agent that forms hypotheses, edits code and runs experiments, keeping only gains that hold on held-out data
AgentBFreshness: B★ 1.1K - 0.573score
deeptide
paean-ai
Coding agent for macOS and the terminal, built around DeepSeek models, with Swift, Bun and Rust versions
AgentBFreshness: B★ 1.1K - 0.573score
percho
Jaxton07
Desktop GUI for the Pi coding agent that runs the same engine as the Pi CLI, with multi-session chat and tool approvals.
AgentAFreshness: A★ 466 - 0.571score
late-cli
mlhher
Terminal coding agent that isolates subagent work so the main model context stays small on long tasks, with any cloud or local model.
AgentAFreshness: A★ 446