Task-centered workflow
Create a task around a repository, select a provider, model, and permission mode, then keep the task's prompt, run history, diff, review, preview, and GitHub status attached to that task.
Task Monki est une application de bureau qui permet de gérer les tâches d’agents de codage, de la demande initiale à la revue et à la pull request. Suivez les tâches, prévisualisez en local, effectuez des revues indépendantes et livrez via GitHub sans fusion automatique.
Task Monki is a desktop app for managing coding-agent work from request to pull request. It keeps each task tied to a repository, branch, worktree, agent run, review, local preview, and GitHub status so you can track implementation and delivery in one place.
The product is built for developers who want to run several coding-agent tasks in parallel while keeping inspections and delivery decisions separate from the agent run itself. It supports task-specific provider and permission choices, independent reviews, and local previews when the repository and preview recipe support them.
Create a task around a repository, select a provider, model, and permission mode, then keep the task's prompt, run history, diff, review, preview, and GitHub status attached to that task.
Follow plan updates, tool activity, approvals, logs, messages, and file changes while an agent is working, with the board showing whether tasks are running, blocked, or ready.
Open approved local previews that run at a stable local address, prepare dependencies and services, wait for readiness checks, and replace the preview after source changes.
Run an independent review against the current implementation, inspect the diff, test output, preview status, logs, pull request state, and GitHub checks, then send findings back for fixes.
Support multiple coding-agent runtimes, including Codex and OpenCode directly and Cursor Agent, Grok Build, and Claude Agent through ACP compatibility integrations.
Publish or commit the task branch, open a draft pull request, and follow the current checks and reviews without having Task Monki merge the pull request.
Use Task Monki when you want to turn a repository request into a tracked coding task with its own provider choice, permission mode, worktree, and branch.
Use the board and task timeline to watch an agent's plan, tools, approvals, logs, and file changes while work is in progress, especially when you are running several tasks at once.
Use the local preview flow to test a task result in an isolated environment, compare implementations, and replace the preview after source changes without rebuilding the setup by hand.
Use the independent review flow when you want a second agent to inspect the current implementation, report findings, and send actionable issues back to the original task for fixes.
Use the publish and draft pull-request controls when the implementation is ready for delivery but you still want to inspect checks and reviews before deciding whether to ship.
Task Monki runs coding-agent tasks from a desktop app and keeps the task context attached to the repository, worktree, preview, review, and GitHub status. It is intended for managing work from request through pull request, not for merging the pull request itself.
The docs say Task Monki is open source under the MIT License. The site also describes the current release as an alpha.
Task Monki supports Codex and OpenCode directly, and it can work with Cursor Agent, Grok Build, and Claude Agent through ACP compatibility integrations.
On macOS, Task Monki can start local previews for approved task worktrees. Docker is also required when the preview recipe uses managed PostgreSQL, Redis, or Docker Compose.
No. Task Monki lets you commit, publish the branch, open a draft pull request, and follow checks and reviews, but it does not merge pull requests.
Les données de trafic sont fournies à titre indicatif uniquement.
air.dev
JetBrains Air est un environnement de bureau pour exécuter plusieurs agents de codage en parallèle, isoler les tâches et examiner les modifications depuis un même espace de travail. Il prend en charge Codex, Claude Agent, Gemini CLI et Junie sur macOS et Linux ; la prise en charge de Windows est prévue.
murmell.com
Murmell est un canevas accessible dans le navigateur pour exécuter des agents de codage IA dans des environnements cloud isolés et partagés. Il permet de coordonner Claude Code, Codex, Kimi et OpenCode sur un même projet, sans configuration locale ni conflits de fichiers.
soloterm.com
Solo est un espace de travail de bureau pour exécuter des agents de programmation IA avec votre environnement de développement local.
airuncode.com
AIRUNCODE est un environnement d’exécution d’agents local-first qui permet de faire tourner des agents de code pilotés par la voix sur votre propre machine. Il s’adresse aux utilisateurs qui souhaitent une exécution locale et accéder aux fournisseurs d’IA à leurs tarifs d’origine.
www.cybedefend.com
CybeDefend est une plateforme de sécurité du code conçue pour les workflows de programmation avec l’IA. Sa couche VibeDefend examine les prompts des agents et les diffs, applique les règles du projet et de l’entreprise, protège contre les actions risquées et regroupe les analyses du code, des dépendances, des secrets, de l’infrastructure et du CI/CD avant une pull request.