Already have an account? Sign in for one-click subscribe
The planning activity feed now loads and scrolls more smoothly, and heartbeat status is based on whether heartbeat work actually succeeded.
System chat became a real live control surface, notifications grew into a proper inbox, and agents gained stronger browser and visual workflows.
Heartbeat status became a first-class agent signal, and the run activity view became much easier to navigate during long executions.
Run activity now renders in a more readable structured format, and agent kind information is easier to find.
Planning can now use short-lived entities that clean themselves up after success, and execution logs stream live into the workspace.
Processes can now run every 30 minutes, recurring work stops queuing when credits are depleted, and agent memory retrieval became more robust.
Planning now separates recurring processes from living documents, with new agents starting from a real roadmap instead of a blurred boundary between the two.
Planning chat now uses searchable agent-local memory, completed runs can check whether they actually met the goal, and setup friction dropped for model credentials and filesystem browsing.
Agents can now create and deploy sites end to end from the CLI, attach custom domains, and work with documents as real local files.
Kindship now has a dedicated How It Works page, plus a refreshed homepage flow that explains the product more clearly.
Telegram now supports a one-hour `/mute`, and OpenCode providers can be removed one by one instead of forcing an all-or-nothing reset.
The public site was redesigned with clearer storytelling, stronger motion, and a more intentional first impression.
OpenCode now supports a far broader provider list with search, while agent pages make it easier to distinguish stored credentials from in-container authentication.
Tasks can now run in a new AGENT mode, agent home directories survive restarts, and profile pages show richer CLI auth and token usage detail.
Agent profiles now show credit balance and 30-day token usage, plans can be exported and re-imported without losing structure, and new agents start with clearer examples.
Changelog emails are now opt-in from the site, pricing moved to new $0/$5/$20 tiers, Telegram context got clearer, and planning durability was strengthened end to end.
You can now chat with agents from the CLI, planning chat degrades more gracefully under load, and Telegram gets a dedicated /new conversation flow.
Retry flows are more durable, system prompts are now visible from the Agent tab, and super admins can manage agents from new global pages.
Configure how much freedom your agent has across Strategy, Coding, Communication, and nine other domains — during setup and anytime after.
A new side-by-side execution modal for processes and projects, multiple activity views, run status navigation, and real performance data for planning entities.
Agents can read and write persistent documents across cycles, stale runs are automatically recovered, and execution state moves from local files to the database.
Messages are processed one at a time per conversation, delivery is guaranteed even under load, and duplicate notifications are prevented at the entity level.
The Agent tab takes priority in the context panel, naming gets clearer, and several layout and navigation fixes across the app.
Duplicate notifications eliminated, delivery tracking improved, and rate limiting upgraded for consistent Telegram messaging.
Interactive reminders now reach you on Telegram, and agents carry context between execution cycles for smarter continuity.
Clear notifications in one click, give agents a structured activity feed for debugging, and unify interactive threads for ASK_USER/CHOICE/CTA.
Agents can now pause on structured decision points with buttons and links, and tool/Telegram streaming is more reliable.
Orchestrate complex plans, manage shared AI credentials per account, and keep execution moving with Telegram ask-user prompts.
Watch agent setup step-by-step, delete agents with full teardown, and download the CLI for macOS/Linux/Windows.
CLI downloads now come from the dedicated kindship-cli repo, enabling faster releases without monorepo deploys.
The sidebar toggle is now reachable on mobile, and the responsive breakpoint is tuned for a smoother layout.
Telegram linking now survives sign-in, planning chat streaming is more robust, and agent naming streams with fewer failures.
Link Telegram to Kindship, create better-named agents with AI guidance, and get more transparent tool-driven planning chat.
Hierarchical folder navigation for documents, agent skills infrastructure, and comprehensive planning improvements.
Choose a purpose-driven agent kind at creation, and let agents pause to ask for missing info—with optional push alerts.
Agent documents are now backed by GitHub with automatic sync. Edit from anywhere—the web, containers, or GitHub directly.
Fewer container failures and clearer error messages when things go wrong.
Your agent now knows when it learned things, asks for clarification on conflicts, and shows memory health at a glance.
Configurable ethical constraints for Kindship agents. Choose from 41 guardrails spanning AI safety research, philosophy, cultural wisdom, and legal frameworks.
A comprehensive help system with searchable documentation, contextual help icons, and guided user journeys.
The Kindship CLI is now available for macOS, Linux, and Windows. Orchestrate AI coding agents with secure authentication and seamless Claude Code integration.
Stay informed with in-app notifications, email alerts, and a unified notification service for all important events.
Axiom-powered dashboards, unified error logging, and comprehensive workflow monitoring for full visibility into your agents.
Execute planning entities directly from agent containers using the kindship CLI with full validation and dependency management.
Create and manage AI agents at the team level with shared access across your workspace.
Browse agent workspaces with syntax-highlighted code preview and document viewing capabilities.
Swipeable panels, unified sidebar, and improved responsive layout for a better experience on all devices.
Execute commands in agent containers with a built-in terminal, command history, and one-command tunnel setup for local development.