Kandev v0.92.0

Kandev is an open source AI-powered development environment designed to orchestrate multiple coding agents in parallel. Rather than acting as a single AI coding assistant, Kandev provides a Kanban-style workspace where developers can assign tasks to different AI agents, review their work, manage Git worktrees, and create pull requests from a unified interface. It supports multiple AI providers, is self-hostable, and runs entirely without telemetry, making it an excellent choice for teams and developers who want greater control over AI-assisted software development.

As AI coding assistants become more capable, developers often want to run several agents simultaneously. Managing multiple terminal windows quickly becomes difficult, especially when reviewing changes, tracking conversations, and merging code.

Kandev solves this problem by providing a visual development environment with Kanban and pipeline views. Each task can run in its own Git worktree, allowing several AI agents to work independently without interfering with one another. Developers can then review generated code, compare changes, and approve pull requests from a single workspace.

Key Features Kandev

Multi-Agent Orchestration

Kandev can launch multiple AI coding agents simultaneously, allowing different tasks to be completed in parallel. This significantly improves productivity when working on larger projects.

Kanban Workflow

The built-in Kanban board helps organize development tasks, track progress, and visualize AI-assisted workflows in a familiar project management interface.

Integrated Code Review

Instead of switching between terminal windows, Kandev provides a unified workspace with:

• File editor

• Git diff viewer

• File tree

• Terminal

• Browser preview

• Agent conversations

This makes reviewing AI-generated code much more efficient.

Multiple AI Provider Support

Kandev supports numerous AI coding agents through the Agent Client Protocol (ACP), including:

• Claude Code

• OpenAI Codex

• GitHub Copilot

• Gemini CLI

• Amp

• Auggie

• OpenCode

Developers are free to choose the provider that best fits their workflow.

Flexible Execution

Agents can run in several environments:

• Local processes

• Docker containers

• Remote SSH servers

• Cloud executors

This flexibility allows teams to scale workloads without relying solely on local hardware.

Git Worktree Management

Each task runs in its own Git worktree, reducing merge conflicts and allowing multiple features or bug fixes to be developed simultaneously.

Self-Hosted and Privacy Focused

Kandev is fully self-hostable and collects no telemetry. Organizations that handle sensitive source code can keep their development environment entirely within their own infrastructure.

Cross-Platform Support

The application runs on Windows, macOS, and Linux. It can be installed using Homebrew, NPX, npm, or by building directly from source.

Download Kandev v0.92.0 - Software Mirrors
Kandev v0.92.0 for Windows kandev-windows-x64.zip | 102.57 MB kandev-windows-x64.tar.gz | 102.57 MB kandev-desktop-windows-x64-Kandev_0.92.0_x64-setup.nsis.zip | 73.96 MB kandev-desktop-windows-x64-Kandev_0.92.0_x64-setup.exe | 73.96 MB
Kandev v0.92.0 for macOS kandev-macos-x64.tar.gz | 101.9 MB kandev-macos-arm64.tar.gz | 99.56 MB kandev-desktop-macos-x64-Kandev_0.92.0_x64.dmg | 107.29 MB kandev-desktop-macos-x64-Kandev.app.tar.gz | 109.27 MB kandev-desktop-macos-arm64-Kandev_0.92.0_aarch64.dmg | 104.88 MB kandev-desktop-macos-arm64-Kandev.app.tar.gz | 107.01 MB
Kandev v0.92.0 for Linux kandev-linux-x64.tar.gz | 102.09 MB kandev-linux-arm64.tar.gz | 98.67 MB kandev-desktop-linux-x64-Kandev_0.92.0_amd64.deb | 110.54 MB kandev-desktop-linux-x64-Kandev_0.92.0_amd64.AppImage.tar.gz | 169.45 MB kandev-desktop-linux-x64-Kandev_0.92.0_amd64.AppImage | 172.98 MB kandev-desktop-linux-x64-Kandev-0.92.0-1.x86_64.rpm | 110.52 MB kandev-desktop-linux-arm64-Kandev_0.92.0_arm64.deb | 107.48 MB kandev-desktop-linux-arm64-Kandev_0.92.0_aarch64.AppImage.tar.gz | 161.84 MB kandev-desktop-linux-arm64-Kandev_0.92.0_aarch64.AppImage | 165.26 MB kandev-desktop-linux-arm64-Kandev-0.92.0-1.aarch64.rpm | 107.48 MB
Kandev v0.92.0 Source Code Kandev v0.92.0 Source code (zip) Kandev v0.92.0 Source code (tar.gz)
Kandev v0.92.0 Release Notes: [!WARNING] macOS, Windows desktop installers in this release are unsigned development builds. They may require manual OS security bypasses and are not trusted downloads. > If macOS blocks Kandev after you verify the checksum, run: > bash xattr -d com.apple.quarantine /Applications/Kandev.app 0.92.0 - 2026-08-28 Features expose saved prompt reads over MCP (#3118) make task title and description editable (#2891) by @nova28 add mouse grab panning for desktop boards (#3052) by @yattdev improve quick chat tabs (#3076) explain backup location and row actions (#3085) plugins can now tell what moving a task to a step will do (#3053) by @nova28 seat a reviewer automatically so tasks don't stall at Review (#3043) by @nova28 expose archived tasks, pull requests and board fields to plugins (#3044) by @nova28 hydrate persisted PR details on task disclosure (#3055) expand compact workflow step navigation (#3054) add repository branch policies (#2997) render lightweight markdown in clarifications (#3033) recover pull requests removed from merge queues (#3042) let agents read task comments so parent tasks stop missing handoffs (#3019) by @nova28 extend markdown table resizing (#3037) plugin task list facets for sort and group (#2932) by @yattdev reclaim remote task directories on terminal archive or delete (#3000) by @nova28 configure sidebar task-row presentation (#2955) add configurable continuation and coordinator access (#2943) give tasks their own command palette scope (#2979) honor per-host IdentityAgent settings (#2992) by @mulatta expose durable pending interactions and response actions (#2922) add per-run cost/token ledger for task usage (#2960) by @nova28 add quick chat activity indicators (#2952) surface plugin update checks and manual updates (#2513) by @yattdev add task archive confirmations (#2945) localize task detach confirmations (#2892) localize user mutation confirmations (#2878) inline workflow sync removal confirmation (#2885) localize integration removal confirmations (#2887) add local layout deletion confirmations (#2890) localize watcher delete confirmations (#2883) prioritize selected picker options (#2935) localize prompt delete confirmation (#2882) pin managed runtimes and add update awareness (#2906) localize session delete confirmations (#2888) localize agent profile deletion confirmation (#2881) surface pull request merge queue status (#2928) add plugin uninstall confirmations (#2886) localize secret deletion confirmation (#2884) add PR walkthrough generation workflow (#2933) localize plan restore confirmation (#2889) expose agent clarification questions and permission requests externally (#2875) by @nova28 clarify task sort descriptions (#2911) (#2920) auto-hide empty steps (#2815) by @gsimard-nordai add OAuth 2.1 with PKCE via Atlassian MCP server (#2805) by @ahmedbally show completed turn duration on prompts (#2852) by @Fclem add per-role tier defaults and explain why an agent's tier differs (#2853) by @nova28 name each task's repository in the sidebar and task header (#2917) add PR outcome attribution (merge, close, draft, changed files) (#2614) by @nova28 use repository-qualified PR comparison targets (#2828) add dynamic agent profile routing (#2698) export workspace automations as reviewable YAML (#2898) by @nova28 add YAML startup configuration parity (#2863) add task-row tags and sidebar actions (#2609) by @yattdev refresh session IP on the throttled touch path (#2876) by @Fclem unify prompt editors (#2855) add rich task and GitLab MR hover previews (#2610) by @yattdev surface Cursor subagent metadata via cursor/task (#2867) localize reset context confirmation (#2880) localize walkthrough discard confirmation (#2879) Bug Fixes classify expected diagnostic failures (#3120) strengthen quick chat backdrop (#3124) route passthrough workflow steps by profile (#3110) (#3117) isolate Monaco from Vitest (#3114) (#3121) unblock advisory stop-owner registration (#3107) (#3116) recover lost children_completed wakes for stalled parents (#3103) by @nova28 preserve passthrough Escape in Quick Chat (#3109) (#3119) preserve archived task resume state (#3115) complete E2E cleanup and quick-chat stabilization (#3102) rescue tasks stuck running forever after a silent agent stall (#2975) by @nova28 dispatch on_enter actions for review/approval steps (#2907) by @nova28 make failed scheduler runs reach the UI and cap taskless-failure inbox noise (#2968) by @nova28 wake parent for every delegation wave, not just the first (#3059) by @nova28 auto-start tasks created directly on a start step (#2967) by @nova28 stop a duplicate lifecycle turn from hiding a pending clarification (#2989) by @nova28 show live Task header until nested child settles (#3075) by @luancm retire stale transient retry notices (#3098) settle stale automation runs (#3096) handle missing Windows npm cache trees (#3092) (#3094) group sidebar tasks by repository combination (#3091) promoted WIP-queued MCP tasks without sessions are not auto-started. (#3080) by @meanderix preserve legacy sqlite database continuity (#3089) reconcile prepared workspace origins (#3077) scrub ambient GH_TOKEN in internal/github tests (#2792) by @yattdev silence quick chat launcher focus return (#3086) coordinate task pull request sync consumers (#3090) stop plan bubble menu transaction loop (#3083) prevent terminal session revival on workflow re-entry (#2766) by @yattdev resolve GitHub clone protocol per host (#3078) resolve first-use repository task selections on server (#3068) preserve runner container mode (#2800) by @yattdev reuse inherited task environment on session resume (#3081) resolve Go lint base for forks (#3074) by @yattdev prevent ready task environments with empty repo inventory (#3008) by @nova28 preserve Kandev MCP text results (#3067) reject stale task path reuse (#3013) by @yattdev isolate dev database resolution from ambient environment (#2910) by @yattdev dock Plan formatting controls on mobile (#3056) authorize managed fork credential leases (#2940) by @yattdev restore automation sidebar running indicator (#3064) restore command-center task focus (#3065) clarify active sidebar task (#3057) prevent chat pagination scroll flicker (#3063) explain why a blocked task move failed (#3047) by @luancm keep configuration chat launcher visible (#3062) polish archive confirmation warning surfaces (#2995) contain growing dialog content (#3060) improve startup and lifecycle diagnostics (#3058) require admin for global mutations (#2816) contain long filenames in Changes rows (#3049) keep terminal colors readable across themes (#3018) fail closed on required repository refresh (#3023) gate focus auto-start on task dependencies (#3045) enforce share authorization boundary (#3022) align sidebar PR badges and expose run scope (#3020) parse glab's token label by structure, not exact wording (#3038) by @nova28 preserve feeder promotion session routing (#3016) (#3017) preserve flat models across session resume (#3030) prevent PR walkthrough link false failures (#3039) allow dragging office task cards between board columns (#3014) by @nova28 stop reviews stranding tasks with no recorded decision (#3009) by @nova28 allow office auto-start after task re-enters a step (#3011) by @nova28 stack mobile host metrics (#2959) expand mobile clarification submit target (#2958) keep composer menus above mobile keyboards (#2988) scope the SSR terminal-listing routes to the caller (#3029) deny a workflow whose workspace no longer exists (#3040) accept plugin-owned repository providers on task create (#3005) by @Corey-Fogg accept unresolvable move_to_step targets again (#3046) require admin for system backups and storage maintenance (#3036) hide the Docker build control from non-admins (#3034) scope Office by-ID routes to the caller's workspace (#3028) scope the workflow-step surface to the workspace owner (#3031) scope notification providers and delivery to the real user (#3027) scope Docker management endpoints to the caller (#3025) guard quick-chat listing on workspace ownership (#3026) authorize workspace on analytics stats routes (#3024) use the session auth token for non-Docker launch and resume (#3007) by @nova28 make e2e adapter tests compile again (#3015) by @nova28 stop transcript pagination at first prompt (#3002) treat model with no config options as valid empty resolution (#3003) recover executor-local npm runtime caches (#2986) retain executions when runtime stop fails (#2998) by @luancm require agents to explicitly signal before advancing the Work step (#2972) by @nova28 accept same-origin GET on session-authenticated webhooks (#2984) replace-all the GitHub credential helper (#2999) by @nova28 gate worktree reuse on live inventory (#2987) bind the HTTP listener before startup recovery so health checks don't crash-loop (#2944) by @nova28 scope task title previews to Kanban (#2939) stop agent continuation summaries from always reading back empty (#2971) by @nova28 stop a flaky test hang from failing CI on unrelated PRs (#2993) by @nova28 preserve walkthrough HTML bytes (#2994) make startup health checks bind-aware (#2981) make clarification watchdog recovery race-free (#2982) route agent starts to the first auto-start step (#2983) stop task plan writes from silently erasing prior content (#2977) by @nova28 make idle-skip gate actually skip periodic routine wakeups (#2973) by @nova28 queue runs for reviewers added before a task reaches Review (#2969) by @nova28 preserve task worktree identity on inventory refresh (#2980) stop a task getting stuck when the agent's turn fails right after it finishes (#2963) by @nova28 reuse task workspaces for additional sessions (#2843) by @yattdev preserve newest backend diagnostics (#2929) (#2934) stop run.subscribe from leaking another workspace's run events (#2961) by @nova28 harden PR walkthrough workflow runner (#2962) improve agent model picker layout (#2941) gate plugin webhooks by manifest visibility (#2608) by @yattdev classify expected runtime errors correctly (#2950) escalate a failed sub-agent to the coordinator instead of going silent (#2948) by @nova28 stop task wakeups from falling back to a generic prompt (#2956) by @nova28 shorten PR walkthrough links and align shell branding (#2954) preserve review diff during PR refresh (#2897) restore complete transcript history (#2914) (#2927) pass walkthrough reasoning variant separately (#2949) harden portable PR walkthrough runner (#2942) localize single-file confirmations (#2894) enforce MCP question turn boundary (#2931) prevent review header overlap (#2899) support local-only merge and rebase (#2925) correct plugin marketplace attribution (#2926) resolve mobile Add folder executor race in workspace sources (#2696) by @yattdev persist workspace name and description edits on save (#2859) by @nova28 allow parent workspace-source recovery (#2842) by @yattdev flicker-free pinned loading indicator for older prompts (#2854) by @Fclem preserve executor fields across kanban task cache merges (#2705) by @yattdev scope MR automation switches per linked MR (#2676) by @yattdev preserve resumed session model labels (#2904) prune superseded plugin versions after a confirmed start (#2921) make integration cards clickable (#2905) keep dockview tab close buttons reachable in a narrow group (#2918) restore PR sync context (#2916) stop agent completion timestamps from staying blank after most runs (#2902) by @nova28 stop finished runs from showing an empty output summary (#2900) by @nova28 count a reassigned task's cost under its new project (#2903) by @nova28 virtualize large Kanban columns (#2896) add durable task launch failure recovery (#2832) make quorum-guarded step transitions actually fire (#2864) by @nova28 retire the session recovery card once the agent boots again (#2877) by @JnManso Performance move persistent animations to the compositor (#3122) reduce frontend runtime CPU (#3093) reduce frontend idle CPU (#2965) stop re-reading and recompiling workflow steps every trigger (#2946) by @nova28 Refactoring simplify mobile task top bar (#3035) dedupe truncateUTF8 into shared package (#2866) render every routed page's chrome through one topbar contract (#2718) by @Aulma Documentation add product screenshots to public guides (#3126) improve contributor guidance (#3097) delete internal add-agent-cli guide describing removed protocols (#3010) by @nova28 correct comments that describe adapters and protocols that don't exist (#3012) by @nova28 tighten specification ownership and migration (#3004) correct three false claims in backend architecture docs (#3001) by @nova28 migrate legacy specs and add product context (#2964) add AGENTS.md routing to office specs and traps (#2970) by @nova28 migrate task and workflow specs (#2957) explain agent Git permission boundary (#2951) (#2953) establish system-oriented specification governance (#2930)

Performance and User Experience

Kandev offers a modern interface that combines project management with AI-assisted development. The Kanban workflow feels natural for teams already using agile methodologies, while the integrated review tools reduce context switching between editors, terminals, and Git clients.

The application performs well even when managing multiple concurrent AI sessions, thanks to its orchestrator architecture and support for isolated execution environments. Since it is still a relatively young project, some features continue to evolve rapidly, but active development and frequent updates indicate strong momentum.

Pros

• Free and open source.

• Supports multiple AI coding agents.

• Parallel task execution.

• Built-in Kanban workflow.

• Excellent integrated code review tools.

• Self-hostable with no telemetry.

• Flexible execution using local, Docker, SSH, or cloud environments.

• Active development.

Cons

• Still a relatively new project.

• Best suited for experienced developers.

• Requires compatible AI agent tools and API access.

• Advanced workflows may require some initial configuration.

Who Should Use Kandev?

Kandev is ideal for software developers, engineering teams, AI-assisted coding enthusiasts, and DevOps professionals who frequently work with multiple AI coding agents.

It is especially valuable for teams that want to coordinate parallel AI workflows, maintain human review before merging code, and avoid vendor lock-in by supporting multiple AI providers.

Final Verdict

Kandev introduces a fresh approach to AI-assisted software development by treating AI agents as collaborative team members rather than standalone chatbots. Its combination of multi-agent orchestration, Kanban project management, integrated code review, and self-hosted architecture makes it one of the most promising open source AI development environments currently available.

Although the project is still evolving, its rapid development pace, privacy-focused design, and flexible architecture make it an excellent choice for developers looking to scale their AI-assisted workflows.

Free

Download

Software Informations:
Developer:
Kandev
Operating System:
Windows / macOS / Linux
Date Added:
2026-08-29T00:07:00.480Z
Categories:

Related to Kandev v0.92.0:

Post a Comment/Report Broken Link: