|
Game of Cards — agile for the age of agents
Turn work into durable, inspectable cards that humans and LLMs can collaborate on. A repo-local methodology runtime built for swarms, not standups.
|
85 % |
|
Farero — Run coding agents locally. Control them from anywhere.
Codex, Claude Code, and OpenCode in one app. Run tasks in isolated Git worktrees, review diffs from your phone, and coordinate agents through built-in MCP to...
|
85 % |
|
Todokan — One board. Humans and agents.
Todokan is the kanban board where humans and AI agents work together — context on the card, one click to hand off, your approval on every step.
|
84 % |
|
okthink — One Workbench for Your AI Coding Agents
okthink builds Firehose — one workbench for Claude Code and Codex. Run your AI coding agents from anywhere, review their work, and keep them shipping.
|
84 % |
|
Kabana · agent-first kanban for everyone shipping software
A kanban board that dispatches work to AI coding agents on your machine. Your code, your AI subscription, our scheduling. Never see your code, never proxy mo...
|
84 % |
|
Byoi, the command board for coding agents
A Git-native board where development work becomes governed instructions for coding agents: capture, AI enrichment, review gate, execution and versioned memory
|
84 % |
|
Harmony Code
A desktop console for running AI coding agents as a coordinated team. Works with any terminal-based model, includes a review step before commit, and keeps yo...
|
84 % |
|
Codrift: run many AI coding agents at once
A desktop control surface for running many AI coding agents at once. Live terminals, isolated worktrees, one diff, one shared memory, driven from the keyboard.
|
84 % |
|
Graphe: send in a team, not a prompt
An open-source coding agent for the desktop: helpers in parallel, a guard that asks before anything risky, and checkpoints that leave your branch and staging...
|
84 % |
|
Hercus — Run Claude Code and Codex in Parallel
Run Claude Code and Codex in parallel from one desktop workspace. See which task needs you, hand plans between agents, and review diffs, PRs, and CI.
|
84 % |
|
Mouse — Code from anywhere.
The coding agent built for your phone. Mouse runs your repo in the cloud, works in the background, and brings back changes to review.
|
83 % |
|
OpenAdmiral: mission control for your Claude Code agents
OpenAdmiral is a free, open source macOS app and Claude Code plugin to run many Claude Code sessions at once: see every agent at a glance, get notified when...
|
83 % |
|
CodeCave — Self-hosted AI coding agent orchestration
Run a team of AI coding agents on your own machine. Isolated git branches, merges you approve, guard rails — your code never leaves your box.
|
83 % |
|
okthink — One Workbench for Your AI Coding Agents
okthink builds Firehose — one workbench for Claude Code and Codex. Run your AI coding agents from anywhere, review their work, and keep them shipping.
|
83 % |
|
footnote - set the targets, your agents do the rest
Set the targets. Your agents do the rest. Lead agents hand out the work, check it against GitHub, and bring you only the decisions.
|
83 % |
|
PullPlane — AI Coding Agent Workspace for Software Teams
Plan, run, review, and merge work with Claude, Codex, and specialist agents in isolated sandboxes—from a live spec to a human-approved pull request.
|
83 % |
|
InPipe — the project tracker that ships the work
A Linear-style tracker with an AI delivery layer: agents pick up your cards, write the code, run your tests, and open a PR. Bring your own AI — MCP, your API...
|
83 % |
|
Tegment — A control room for parallel AI coding agents
Tegment gives every coding agent its own git worktree, terminals and ticket context. Run multiple Claude Code sessions in parallel without stepping on each o...
|
83 % |
|
ocodey — your multi-model coding agent
ocodey is a multi-model AI coding agent for your terminal or desktop. It reads your whole repo, writes multi-file changes, runs your tests, and shows you a c...
|
83 % |
|
Your agents say done. Wrangler proves it. | Control tower for coding agents
Your agents say done — Wrangler proves it. When a session finishes, Wrangler runs your tests, lint, and typecheck in the agent's worktree, with tickets, PRs,...
|
83 % |
Detected social media networks