Skip to main content
This page lists what does not work yet in Clawboo, or works with a catch. Each entry says what you see, what it affects, what to do about it, and its status:
  • Open: no fix exists yet.
  • Fixed on main: the fix is in the source code but not in an npm release yet. It ships with the next release.
The latest npm release is 0.9.0. Run clawboo --version to see which one you have. For error messages and their fixes, see Troubleshooting.

Security and access

A reverse proxy on the same machine exposes the MCP servers (0.5.0 and older)

What you see: nothing. Behind nginx, Caddy or a Cloudflare Tunnel connector on the same machine, requests to /api/mcp/ succeed without the access cookie, even with STUDIO_ACCESS_TOKEN set.What it affects: a same-host proxy delivers every request from 127.0.0.1, and these releases let any request from 127.0.0.1 reach every /api/mcp/ path without the cookie. Anyone who can reach your proxy can use Clawboo’s MCP servers (your boards, memory, team chat and tools). They can also ask /api/mcp/config for an attach URL signed as any of your agents, with that agent’s connector grants.What to do: deny all of /api/mcp/ at the proxy, not only the four MCP server routes, because /api/mcp/config is the one that signs attach URLs. Security model has the nginx, Caddy and Cloudflare Tunnel rules. Or upgrade to 0.6.0.Status: fixed in 0.6.0. From 0.6.0, a request without the cookie reaches an MCP server only with an attach token, only on a direct connection to 127.0.0.1, and never through a proxy. /api/mcp/config always needs the cookie.

An access token with an unsupported character turns the access check off

What you see: the dashboard opens without asking for your token, and the server log says STUDIO_ACCESS_TOKEN contains an unsupported character and that the access gate is disabled. What it affects: Clawboo accepts only letters, digits, ., _, ~ and - in the token. Any other character switches the token check off. With Clawboo on 127.0.0.1 behind a reverse proxy on the same machine, the dashboard and every /api/ route are then open to anyone who can reach the proxy. A bind to other machines (HOST=0.0.0.0) refuses to start instead. What to do: make a token from the allowed characters, for example with openssl rand -hex 24. Restart Clawboo and check that the dashboard asks for the token. See Reach Clawboo from another machine. Status: fixed in 0.6.0. From 0.6.0, such a token stops the server at startup on every bind, with a SECURITY: refusing to start error that names the character. CLAWBOO_ALLOW_INSECURE=1 does not skip it.

Keys saved under Providers are also stored unencrypted for OpenClaw

What you see: your provider keys appear in plain text in ~/.openclaw/.env, even if you never installed OpenClaw, and in each OpenClaw agent’s auth-profiles.json. What it affects: Clawboo copies every key you save on Settings > Providers into OpenClaw’s files so an OpenClaw Gateway can use it. Anything that runs as your user account can read those files, including the coding agents. Deleting ~/.clawboo removes the encrypted vault but not these copies. What to do: if you do not use OpenClaw, connect keys on the runtime’s row in Settings > Runtimes instead: keys entered there stay in the encrypted vault. To remove a copied key, click Disconnect on its row under Settings > Providers. See Where keys are stored. Status: open. The copy is how the OpenClaw Gateway gets your keys.

Disconnecting a runtime deletes keys other runtimes use

What you see: after you click Disconnect on a runtime in Settings > Runtimes, another runtime can read Needs key. What it affects: a runtime’s Disconnect deletes every key that runtime reads from the vault, and the vault keeps one copy of each key for all runtimes. Disconnecting Hermes, for example, also deletes the Anthropic and OpenAI keys that Clawboo Native or Claude Code run on. The confirmation mentions only one key. What to do: to remove a single key, use Disconnect on its row under Settings > Providers. To undo a runtime’s disconnect, connect the keys again. See Disconnect a key or a runtime. Status: fixed in 0.6.0. From 0.6.0, a runtime’s Disconnect keeps any key another runtime also reads and only stops that runtime using it, and its dialog names each saved key it deletes and each one it keeps.

What agents can reach

Claude Code, Codex and Hermes run with their own sandboxes off

What you see: coding agents run commands, edit and delete files, and reach the network without asking you. What it affects: Claude Code and Codex start with their own permission prompts and sandboxes turned off, so they can work unattended. Hermes has no sandbox and asks only before the commands its own policy flags. They run as your user account and can read and change any file it can. Without a worktree they start in the work folder (~/clawboo-work by default): on a task, including agent Routines you create in the app, in the task’s own folder (teams/<team id>/tasks/<task id>), and on other team-chat turns and in an agent’s own chat, in their team’s folder (teams/<team id>). The work folder sits outside Clawboo’s data folder, so a short relative path such as ../.. from a team folder or a task folder no longer reaches the database, and neither does a tool that walks up parent folders. Work an install keeps in the data folder (see The work folder for when that happens) does not get that distance. That is not a boundary: the agents still run as the same user account and can open Clawboo’s database and saved keys in ~/.clawboo by their full path. A git worktree keeps one task’s file changes apart from another’s; it is not a sandbox either. What to do: give coding agents only work you would let them do unattended. For work you do not fully trust, run agents under a separate user account or run Clawboo in a virtual machine. CLAWBOO_AGENT_USER is the built-in way to do the first: Claude Code, Codex and Hermes runs, and Clawboo Native’s commands, then start as a user that cannot open Clawboo’s database, saved keys, settings or access token. Their sandboxes stay off, and they still reach the network. It is not available on Windows. All agents share that one user, so it does not keep them apart from each other. From 0.8.0, on Linux, CLAWBOO_AGENT_USERS gives each agent a user of its own instead: one agent cannot read another’s home or reach the folder of a team it is not on. Code tasks in a repository, Hermes and a few other things are not available with it yet. See What agents can do. Status: open, by design.

Claude Code agents follow your own Claude Code settings

What you see: a Claude Code agent behaves as if it had your personal Claude Code setup, for example following instructions from your CLAUDE.md. What it affects: Clawboo does not limit which settings files Claude Code loads. Every Claude Code agent reads what your own claude command reads: your user settings and memory in ~/.claude, plus any .claude settings and CLAUDE.md in the folder it works in. All Claude Code agents share them. What to do: keep anything you do not want agents to follow out of ~/.claude, or run Clawboo under a separate user account. From 0.7.0, CLAWBOO_AGENT_USER is the built-in way to run agents as a separate user; all Claude Code agents then share that user’s one ~/.claude, which is not yours. From 0.8.0, with CLAWBOO_AGENT_USERS (Linux only for now), each agent runs as a user of its own, with its own ~/.claude. See Claude Code. Status: fixed in 0.6.0. From 0.6.0, Claude Code agents load only the Claude Code files of the folder they work in, such as a repository’s CLAUDE.md. Your ~/.claude settings, plugins, MCP servers and memory files, and Claude Code’s auto memory, are left out.

Clawboo Native shell commands are one approved command at a time

What you see: an agent with shell commands turned on asks you before every command, and never offers Always. What it affects:
  • Each command is one program and its arguments, with no pipes, redirects or chained commands.
  • Commands are offered in team chat, one-to-one chat and task runs alike, but never on Windows.
  • One run can ask about at most 10 commands. A card waits 10 minutes for your answer, and the run waits with it.
  • Once you decline a command, or let a card expire, the agent cannot ask again in that run.
What to do: turn shell commands on only for agents that need them, and answer cards promptly. See What agents can do and Approvals. Status: open, by design.

Costs and budgets

Models without a known price are estimated at $3 and $15 per million tokens

What you see: a run on a model Clawboo has no price for, such as gpt-5.4 or one of Ollama’s cloud models, shows a cost such as ~$0.02 est. on its task card. What it affects: Clawboo’s price table lists Claude models and two GPT-4o models. Any other model is priced at a default rate of $3 per million input tokens and $15 per million output tokens. The run is marked est., and the estimate counts toward your budgets. A model your own Ollama serves is not affected: it is recorded at $0 and reads free. What to do: treat est. figures as rough. For flat-rate plans, set budgets with the placeholder rate in mind; your provider’s bill is the real number. Status: open.

A hard cap does not stop most runs partway

What you see: a budget in hard cap mode reads paused at 100%, but a run that was already going keeps working until it finishes, and the budget ends up past its limit. What it affects: only Clawboo Native reports cost while it works, so only a Clawboo Native run can be stopped partway (in team chat and one-to-one chat, only on a model Clawboo prices). Every other run is charged when it finishes. New runs are refused once the budget is paused, on every path. What to do: to end a run that is going, press Stop in the chat. See What a hard cap stops. Status: open.

A tenant budget never warns or pauses

What you see: a tenant budget, made before the Governance form stopped offering tenant or through the API, stays at $0 spent. What it affects: nothing charges a tenant budget, so there is no budget for the whole install. What to do: set budgets per team or per agent instead. Status: open.

Checks on finished work

Much work is never checked

What you see: tasks reach Done without a check result. What it affects: Clawboo checks work only for a task-runner run that worked in its own git worktree and changed files, and, from 0.6.0, for team chat work that changed the team’s folder on a team with a work check. Other team chat work, agent Routines created in the app and OpenClaw work are never checked. When a task-runner check runs, it uses the verify command in the worktree’s init.sh. That starts as a placeholder, and a placeholder counts as a failure. On 0.5.0 nothing tells the agent to set it, so the first check fails unless the agent does so on its own. From 0.6.0, the run’s instructions and the worktree’s TASK.md tell it to, and a team can set its own verify command, its work check, which every check runs in place of the one in init.sh. What to do: review results yourself. For runs that are checked, set the team’s work check (0.6.0 and later), or name the test command in the task, for example: “Before you finish, set VERIFY_CMD in init.sh to npm test.” See How work is checked. Status: open.

OpenClaw agents

OpenClaw agents share one memory across teams

What you see: a fact an OpenClaw agent saves shows up for OpenClaw agents on other teams. What it affects: OpenClaw agents read and save only global facts, because one Gateway setting serves all of them and Clawboo cannot tell which OpenClaw agent is asking. Agents on other runtimes read their own team’s facts and global ones. What to do: for work that needs memory kept per team, use another runtime. See Memory. Status: open.

Connectors you share with an OpenClaw agent do not reach it

What you see: an OpenClaw agent says it has no tool for a connector you drew to it on the graph, the browser connectors included. What it affects: OpenClaw agents call Clawboo’s tools without an agent identity, so connectors shared with a specific agent do not reach them. They can use apps reached through Composio, and every action in those apps asks you first. What to do: give connector work to an agent on another runtime. See OpenClaw agents and connectors. Status: open.

Teams and Boo Zero

Refresh Protocol needs an OpenClaw Gateway, even without OpenClaw agents

What you see: Refresh Protocol on a team reports Not connected to Gateway. What it affects: it runs only while the dashboard is connected to an OpenClaw Gateway, even for teams with no OpenClaw members. What to do: connect a Gateway, or edit each agent’s AGENTS.md on its page. See Teams. Status: open.

Memory and observability

Memory similarity search looks for Ollama on this computer only

What you see: with Ollama on another machine and OLLAMA_BASE_URL pointing at it, your agents chat on that Ollama, but Memory does not use it for similarity search. What it affects: Memory always looks for Ollama at http://localhost:11434 and ignores OLLAMA_BASE_URL. Without an Ollama there, Memory uses an OpenAI key if you connected one, which sends fact text to OpenAI, or keyword search only. What to do: run Ollama with the nomic-embed-text model on the computer that runs Clawboo. See Turn on similarity search. Status: open.

OpenTelemetry export does nothing on an npm install

What you see: with OTEL_EXPORTER_OTLP_ENDPOINT set, no traces reach your collector. System Health shows the OTel exporter check as Degraded, saying the install does not include the OpenTelemetry SDK, and its observability line reads “local event log (OTLP endpoint set, exporter not running)”. What it affects: the npm package does not include the OpenTelemetry SDK, so the exporter cannot load. Traces stay in Clawboo’s own event log, where the Observability panel shows them. What to do: if you need export, run Clawboo from a source checkout of the repository, which installs the SDK. See Observability. Status: open.

Setup and platform

Runtime requirements that catch people out

The full Marketplace needs an internet connection

What you see: the Marketplace shows only 5 teams and 15 agents. What it affects: Clawboo’s server downloads the full catalog published with its version from the Clawboo repository on GitHub, and refreshes it at most every 6 hours. Offline, or until the download lands, you see only the built-in pack. What to do: check that the computer running Clawboo can reach GitHub, then wait for the next refresh. On a machine that cannot reach GitHub, serve the catalog files from a mirror and point CLAWBOO_CATALOG_INDEX_URL at it. See Marketplace. Status: open, by design.

Self-hosting

Binding to one network address cuts agents off from Clawboo’s tools

What you see: with HOST set to the computer’s own network address, other machines reach the dashboard, but agents lose their Clawboo tools, such as the board and memory. What it affects: Clawboo’s agents and background jobs connect to 127.0.0.1, and a bind to one address does not listen there. What to do: use HOST=0.0.0.0 with an access token, CLAWBOO_ALLOWED_HOSTS and CLAWBOO_ALLOWED_ORIGINS, or keep the default and reach Clawboo through an SSH tunnel or a reverse proxy. See Reach Clawboo from another machine. Status: open.

The clawboo command cannot manage a server that uses an access token

What you see: clawboo, clawboo stop or clawboo restart prints A Clawboo server is running on port 18790, but it requires an access token. and exits. What it affects: the launcher cannot check a token-protected server, so it will not start a second one, stop it or restart it. clawboo stop and clawboo restart print a command to stop the server by hand. Starting a new server with STUDIO_ACCESS_TOKEN set also confuses it: after about 45 seconds it prints Dashboard is taking too long to start. and exits, while the server keeps running. What to do: stop and start that server the way you started it, for example with Ctrl+C in its terminal or through your service manager. To open a server you just started, visit http://localhost:18790/?access_token=<token> (use your port if it is not 18790). See Run the Clawboo server and CLI reference. Status: fixed in 0.6.0. From 0.6.0, the command uses the STUDIO_ACCESS_TOKEN set in the shell you run it from. With the server’s token there, clawboo sees a server it just started and opens it, and clawboo stop and clawboo restart work. Without it, they print the same notice as before.

One install serves one person

What you see: everyone who can open the dashboard sees every team, agent, task and memory fact, unless roles are enforced behind a sign-in proxy (see below). What it affects: Clawboo has no user accounts and keeps no data apart per person. Anyone with the access token gets the whole install. From 0.9.0, behind a sign-in proxy, Roles can decide what each person may do, and a guest then reaches only the teams their token lists. Every other role still sees the whole install. What to do: run one install per person, each under its own user account on the computer or in its own virtual machine. Separate data folders (CLAWBOO_HOME) under one account do not keep people apart: they share ~/.openclaw and its saved keys, and coding agents can read any file that account can. With CLAWBOO_AGENT_USER, give each install an agent user of its own: Clawboo stops every process its agent user runs when it starts and when it stops. See Data and state. Status: open, by design.

Live event streams have no limit

What you see: nothing in normal use. What it affects: each open live event stream (GET /api/obs/stream) keeps polling the database until its client disconnects, and nothing limits how many can be open. This matters only when many clients can reach the server. What to do: behind a reverse proxy, limit concurrent connections there, and keep the access token on. See the Observability API. Status: open.

Issues in 0.8.0 that are fixed in 0.9.0

These problems affect the 0.8.0 release. They are fixed in 0.9.0, which the changelog describes. Where a row says the fix needs more, such as installing a runtime again or a server that writes a start marker, it holds only then.

Issues in 0.7.0 that are fixed in 0.8.0

These problems affect the 0.7.0 release. They are fixed in 0.8.0, which the changelog describes.

Issues in 0.6.0 that are fixed in 0.7.0

These problems affect the 0.6.0 release. They are fixed in 0.7.0, which the changelog describes.

Issues in 0.5.0 that are fixed in 0.6.0

These problems affect the 0.5.0 release. They are fixed in 0.6.0, which the changelog describes.
Last modified on November 18, 2026