Charts on the dashboard, goals and activity
The dashboard, goals and activity pages now open with charts. Goals show their health and period at a glance, and activity shows events per day, by action and by the busiest actors above the timeline.
changelog: ConvOps changelog: what shipped, and when.
Every change to ConvOps a user can notice, dated by the day it reached the product. Newest first, grouped by month.
plain language · real dates · rss feed
changelogMay 2026 rss
Template packs
Explore and install workflows
Starter workflows for every work type
Connect first, set up your workspace after
entry 4 of 40since April 2026
what's new
What's new in ConvOps?
The ConvOps changelog lists every change a user can notice in ConvOps, the operations layer for AI agents, dated by the day it reached the product. Entries run newest first and are grouped by month. Each one says what you can now do, in plain language, and links to the page that explains it.
New here? Start with how to connect ConvOps to your AI client, or see how ConvOps compares with other AI agent workflow tools.
October 2026
4 entries
See the sub-workflow tree on a task
When a decision invokes a sub-workflow, the task page shows the parent workflow with the open sub-workflow nested inside it. You see exactly which step the run is on, at every level.
How decisions invoke sub-workflowsMemories and routes filed by project
Memories and routes are now filed under a project from your workspace catalog. Recall, context lookups and memory lists can be narrowed to one project, and a memory can be moved to another project when you edit it.
The brainMerge projects and keep the catalog clean
Merge one project into another and its work moves with it. A task that names an unknown or archived project is now refused with a clear message instead of creating a new project by accident.
Workspaces
September 2026
9 entries
Commit identity and push target per environment
An environment can set the name and email on every commit a run makes. You also choose which repository receives the work, and whether a finished run lands on a task branch for review or straight on the branch you configure.
EnvironmentsAttach MCP servers to an environment
Add MCP servers to your workspace and attach them to an environment, with rules that allow or deny each tool. Isolated runs start those servers next to the agent, and the agent is offered only the tools the rules let through.
EnvironmentsChoose which ConvOps tools a run can call
Each environment lists the ConvOps tools an unattended run is offered, and a person switches each one on or off. Task tools reach only the run's own task unless you widen them.
EnvironmentsOne search box for the whole app
The command palette now searches tasks, memories, routes, workflows, projects and executors from one box. Press C anywhere to create a task.
Isolated runs on Kubernetes
An executor can now start every run as its own Kubernetes Job: a fresh pod with its own volume and secret, and a time limit. Each run keeps a history with its event log and transcript, and a Stop button.
One run, one podAgent environments
Prepare once what every run needs: repositories, git access, secrets and variables. A check clones every repository and resolves every secret in a throwaway copy before any run starts, and reports what is ready or failed.
EnvironmentsA brain page in the app
Browse, filter and read your workspace memories and routes in the web app, and add or correct them from the same page. When a new memory replaces older ones, the app tells you which.
The brainThe workspace router
Mark one workflow as the router of your workspace. Every new task, bug, initiative or plan starts there, and the router sends it to the right workflow. The app shows a Router badge on that workflow.
Graph engineeringExecutions page with transcripts
Every dispatched run now shows its status, timeline and transcript on the task page, and a new executions page lists runs across the workspace. Your AI client can read the same status and transcript, and stop a run.
Unattended runs
August 2026
6 entries
Edit long text without rewriting it
Your AI can change one passage of a task description or a step instruction by anchoring on the text around it, instead of sending the whole thing back. A version check stops two agents from overwriting each other, and replacing a long text outright needs an explicit confirm.
Workflow engineHorizons: now, next and later
Mark when work is committed: now, next or later. Children inherit the horizon of their nearest ancestor, the dashboard groups work by horizon, and four built-in pools list what is committed now, what is actionable, what is next and what has gone quiet.
Pools and autonomyAPI keys limited to chosen workspaces
When you create an API key you can limit it to the workspaces you pick. A key scoped this way only reaches those workspaces.
SecurityBlock completion while a workflow runs
A workspace setting stops anyone, person or agent, from marking a task done while its workflow is still running. The refusal names the current step, so the work finishes through the workflow. Cancelling stays possible.
GovernanceThe template catalog on convops.app
Every installable workflow template and pack is now browsable on convops.app, with its real steps, gates and decisions. Pick one, then install it into your workspace in the app.
Template catalogA projects catalog for every workspace
Each workspace now keeps one list of projects. Tasks, routing rules and every project picker in the app read from it, and a project can be archived when the work is done.
Workspaces
July 2026
5 entries
The human and the agent on every change
Every change now records the server-verified person behind it next to the label the agent gives itself. The app shows the person on the task and next to the agent on every activity row, so you can always answer who approved that.
Dual attributionChoose the executor for each step
A step can name the executor that should run it, and a task can carry its own default. When a run reaches a step meant for a different executor, the agent is told to hand it over. Nothing is dispatched behind your back.
ExecutorsNamed executors and dispatch
Define executors for your workspace, each naming which AI client runs the work and where. Dispatch a task to one of them, then follow its status and read its transcript from your AI client.
ExecutorsTask pools
Save a query as a pool, and an agent can ask it what to work on next. The pool is resolved live on every call and returns exactly one task or nothing, so empty is an answer the workflow can branch on.
Work poolStalled scheduled runs recover on their own
Scheduled runs that go quiet are picked up and resumed automatically. After repeated tries the task moves to a new Stalled status with the reason, and a parent waiting on it continues instead of hanging.
Autonomy
June 2026
8 entries
Workspaces, invites and API keys from chat
Create a workspace, accept or decline an invitation and manage your API keys straight from your AI client. Creating or revoking a key still needs a signed-in person.
Connect your AI toolCapture memory while you work
Pass a short context note with a task or workflow call and it is stored as a memory linked to that task. A step can require that note before it advances, and automatic capture is available as a workspace setting, off by default.
The brainStarter packs for content, sales and operations
Thirteen new starter workflows in four packs: Content Studio, Sales Outreach, Business Ops and Chat Essentials. They are written for a plain AI chat, with approvals only where something is published, sent or decided.
Template catalogOne connection for every workspace
A single connection now reaches every workspace you belong to. Writes name the workspace they go to, and search and recall look across all of them at once.
WorkspacesInvite your team
Invite people to a workspace by email, then resend or revoke an invitation and manage members from settings. Invitations expire on their own.
WorkspacesSchedules that resume a task
Attach a schedule to an existing task and each fire resumes its workflow where it stopped, instead of creating a new task every time. Schedules that spawn a fresh task per fire work as before.
Unattended runsSign in with Google
Sign up or sign in with Google, including on the page that opens when you connect your AI client for the first time.
Connect your AI tool
May 2026
5 entries
Unattended runs on your own OpenCode server
Point your workspace at your own OpenCode server and tasks can run there without anyone typing. The connection is validated when you save it, from a new Execution page in settings.
AutonomyThe brain: memory and routes
Your workspace gets a shared brain. Agents store what they learn as memories, record where things live as routes, and look both up before they act, so the next run starts from what the last one found.
The brainPolicies
Write a rule once, globally or for one workflow, and it is delivered inside the step the agent is working on. Edit it and every run picks it up. Policies inform the agent, gates enforce.
Workflow policyChange a workflow one step at a time
Ask your AI client to add, remove, move or update a single step, or to change a workflow's details. Each edit is validated against the whole workflow before it is saved.
Workflow engineTemplate packs
Install a whole pack of workflows in one go. Shared fragments come along automatically, and the app warns you before you uninstall something another workflow depends on.
Template catalog
April 2026
3 entries
Explore and install workflows
A new Explore page lists every starter workflow with suggested prompts. Install one into your workspace, where it sits next to the workflows you write yourself, and pick your first workflows during onboarding.
Template catalogStarter workflows for every work type
Ready-made workflows for goals, plans, phases, features, bug fixes and tasks, with gates between the stages. Every type of work can start on a process from day one.
Agentic workflows, explainedConnect first, set up your workspace after
Connect your AI client and sign in before you have a workspace. Sign-in takes you to onboarding to create one, then hands you back to your client.
Connect your AI tool
follow along
How do I follow ConvOps updates?
Subscribe to the RSS feed in any reader. Every entry on this page becomes one item, linked to its anchor here.
rss 2.0 feed
https://convops.app/changelog.xml- New to ConvOps? See how a workflow runs your process, one step at a time.The workflow engine
- Ready to try it? Add ConvOps to the AI client you already use.Connect your AI tool
- Want a running start? Install a workflow from the catalog.Workflow template catalog
- Running it for a company? Self-host it on your Kubernetes.ConvOps for enterprise
questions
What counts as a change here?
How often does ConvOps ship?
Continuously, not in big releases. A change goes live as soon as it reaches the product, and this page lists the ones a user can notice, each dated by the day it landed.
What is left out of the changelog?
Internal work: tests, build pipelines, refactors and infrastructure. Each entry describes what you can now do, not how it was built.
Do I need to install an update?
No. ConvOps runs as a hosted MCP server, so a change is live for every connected AI client without installing anything. You bring your own AI client; ConvOps holds the process and the record.
Is there an RSS feed?
Yes. The feed at https://convops.app/changelog.xml is RSS 2.0, with one item per entry that links to its anchor on this page.
your next step