- Best for: most teams. It works with ten cloud providers or a free local model, and it reports cost after every turn.
- You need: an API key for one of the providers below, or a local Ollama with a chat model pulled.
Set up
Pick one way to give Clawboo Native a model. You can add more providers later.- Provider key
- Local Ollama (no key)
1
Get an API key
Create a key on your provider’s site. Most provider rows on the Providers page have a Get a key link.
2
Save it in Clawboo
Open Settings > Providers, click Connect on the provider’s row, paste the key and click Save. Clawboo checks the key with the provider before it saves it. If the check fails, the reason shows under the field, and Save anyway stores the key without the check (useful when the provider just can’t be reached).In onboarding, the Connect your AI provider step does the same thing.
3
Check the runtime
Open Settings > Runtimes. Clawboo Native reads Connected. Click Manage, and your provider is listed under LLM providers.
~/.openclaw/.env, so an OpenClaw Gateway can use it too. See Connect providers and runtimes for where keys are kept.
Providers and default models
Clawboo Native works with eleven providers: ten with an API key, plus a local Ollama. The Providers page also lists MiniMax, NVIDIA, Hugging Face and Venice; their keys reach OpenClaw only. These are the built-in models for an agent whose model you leave on Default when you deploy a team. A team’s leader, and a native Boo Zero, get the leader model; everyone else gets the specialist model. On your default provider, the leader runs the model you picked instead (see the next section).
The key name is where Clawboo stores the key, and the variable it reads if you export the key in your shell instead. Keys look like
sk-ant-… (Anthropic), sk-… (OpenAI), sk-or-… (OpenRouter), AIza… (Google), xai-… (xAI), gsk_… (Groq) and csk-… (Cerebras).
Which provider a new agent gets
When an agent’s model is left on Default, Clawboo picks its provider in this order:- Your default provider, if it is set up. That is the provider and model you chose in onboarding, or later with Make default (open a provider row under Settings > Runtimes > Clawboo Native > Manage). The leader runs the model you picked, and specialists run that provider’s specialist model. On Ollama, every agent runs the model you picked.
- Otherwise, the first provider that is set up, in this order: Anthropic, OpenAI, OpenRouter, Ollama, Google, xAI, Groq, Mistral, Together, Cerebras, Moonshot. The agent gets that provider’s models from the table above.
- With nothing set up, the agent is created on Anthropic, and its first run reports the missing key.
~/.openclaw/.env, never outranks the default you picked. The deploy dialog names the model each row will get (Default · <model>), so you can check before you deploy.
Changing the default model later also moves a native Boo Zero onto it. Other agents keep their model; change one from its own page.
Local Ollama
- Clawboo reaches Ollama at
http://localhost:11434/v1. To use another address, setOLLAMA_BASE_URLto its OpenAI-compatible base,/v1included. - The model lists show only the chat models your Ollama has pulled. Embedding models such as
nomic-embed-textare left out, and a model that can’t use tools is marked(can't use tools). Agents call tools on almost every turn, so pick one that can. - An agent created without a model pick gets your default Ollama model if Ollama has it. If not, it gets the most recently pulled model that can use tools. The leader and the specialists get the same model, so Ollama doesn’t swap models in and out of memory between turns.
- A default model that Ollama doesn’t have, for example one you removed, shows as
<model> (not pulled), with itsollama pullcommand and a Check again button. - When Ollama is your only provider, a native Boo Zero runs on it too.
- Disconnect Ollama (on the Ollama row) stops Clawboo Native from using Ollama and leaves your keys alone. Agents on an Ollama model can’t run until you click Use again.
What Clawboo Native can do
A native agent acts only through the tools Clawboo gives it. Which tools it has depends on where it runs.
The run’s folder is the task’s own git worktree when the task run has one; see Worktrees and handoff. A run on a task with no worktree (a task delegated in team chat, one you give from the Board, or a research or review task run) works in the task’s own folder,
teams/<team id>/tasks/<task id> in the work folder (~/clawboo-work by default). There write_file writes only in the task’s folder, while read_file and list_files also reach the rest of the team’s folder. Paths still start from the task’s folder, so the team’s folder is ../.. and another task’s folder is ../<task id>; nothing above the team’s folder is reachable. Turns that hold no task, such as the lead’s turns and your messages in team chat, and the agent’s 1:1 chat work in the team’s folder, teams/<team id>, shared with every teammate. A task with no team has its folder under teams/_no-team/tasks/, and an agent on no team, such as Boo Zero, uses teams/_no-team in its 1:1 chat. For how this compares with the other runtimes, see What agents can do.
Running commands
run_command is off for every agent until you allow it. To allow it, open the agent’s page, then Details, then the Permissions tab. Under Running commands, switch on Let this Boo ask to run commands and confirm with Allow it to ask.
- You approve every command, and nothing is remembered. Each one raises a card that reads “agent wants to run a command on this computer.” with the command and the folder. Run it approves it. There is no Always option.
- One program, no shell. The agent can’t use pipes, redirects or shell operators. Programs that run other programs (shells, interpreters, package runners and similar) are refused before you’re asked.
- It runs as you. The command runs in the run’s folder (the task’s worktree, the task’s own folder, or the team’s folder), under your user account, with network access. Your API keys are not passed to it. With a user per agent (
CLAWBOO_AGENT_USERS, Linux only for now), approved commands and the file tools run as the agent’s own OS user instead, still with network access. - Limits per run: the agent can ask about 10 commands. Each card waits 10 minutes for an answer, a command is stopped after 5 minutes (time the computer spends asleep does not count, except a sleep of under about a minute), and output is cut at 64 KiB.
- A refusal ends it. If you decline, or nobody answers in time, the agent can’t ask again in that run.
Costs
Clawboo Native reports the cost of every turn:- Six models have an exact price:
claude-haiku-4-5,claude-sonnet-4-6,gpt-4o,gpt-4o-mini,openai/gpt-4o-miniandanthropic/claude-haiku-4.5. Clawboo records their cost at list price. - Every other model is estimated, including the default leader models
claude-sonnet-5andgpt-5.4. Clawboo prices the turn’s token counts from its rate table and records the result as an estimate. A model missing from the table is priced at USD 3 per million input tokens and USD 15 per million output tokens. - Anthropic runs use prompt caching. Direct and through OpenRouter, each Anthropic call asks Anthropic to cache the prompt, so from the second turn on most of it is read from the cache. A priced model’s cached tokens cost the cache rate, and the turn’s input count still covers the whole prompt.
- Local Ollama models are free. A turn your own Ollama serves is recorded at $0, charges no budget, and its tasks read free on the Board. Ollama’s cloud models (a
-cloudtag) run on ollama.com and are estimated like any other unpriced model.
Disconnect
Open Settings > Runtimes > Clawboo Native > Manage. You can remove one provider or the whole runtime:- Disconnect Provider (for example Disconnect OpenAI) on an open provider row removes that provider’s key from Clawboo’s vault and from OpenClaw’s
~/.openclaw/.env. Your other keys stay. - Disconnect Ollama stops Clawboo Native from using Ollama. Your keys stay.
- Disconnect, at the bottom of Manage, disconnects Clawboo Native itself.
Limits
- Files only in the run’s folder. File tools work only inside the folder the run starts in: the task’s worktree, the task’s own folder on a task without one, or the team’s folder, where a 1:1 chat and turns that hold no task start. On a task without a worktree, reading also reaches the rest of the team’s folder; writing does not.
- No commands on Windows.
run_commandis never offered there. - 16 turns per run. A run ends after 16 turns (model calls).
- No ChatGPT plan. A ChatGPT subscription runs agents on Codex, not on Clawboo Native.
- Ten keyed providers. Keys for MiniMax, NVIDIA, Hugging Face and Venice don’t work with Clawboo Native.
Troubleshooting
Clawboo Native has no provider key connected
Clawboo Native has no provider key connected
The full message is
Clawboo Native has no provider key connected. Open Settings → Runtimes → Clawboo Native to connect a provider.What it means: the provider this agent runs on has no key Clawboo can use. Clawboo Native can still read Connected when another provider has a key. The agent’s page shows No provider key, or Disconnected when no provider is set up at all, next to Set up in Runtimes →.Fix: connect a key for that provider on the Providers page, or open the agent’s page and pick a model from a provider you have connected. An agent on Ollama shows this message after Disconnect Ollama; click Use on the Ollama line to turn it back on.Ollama doesn't have the model yet
Ollama doesn't have the model yet
The chat shows
Ollama doesn't have <model> yet, so this run couldn't start. Pull it with "ollama pull <model>", or pick a model you have pulled in this agent's settings.Fix: run the ollama pull command it gives, or pick a pulled model on the agent’s page. After a pull, Check again refreshes the model lists.The model can't use tools
The model can't use tools
The chat shows
<model> can't use tools, and this agent needs them. Pick a model that can in this agent's settings, or pull one with "ollama pull llama3.2".Fix: pick a model that isn’t marked (can't use tools), or pull one that can.Invalid API key, or Could not reach the provider
Invalid API key, or Could not reach the provider
When you save a key, Clawboo checks it with the provider.
Invalid API key. means the provider refused it: copy the key again from the provider’s site. Provider returned <status>. is another refusal. Could not reach <provider>. (or Could not reach <provider> (timed out).) means the check got no answer. If you are sure the key is right, Save anyway stores it without the check.Ollama isn't answering on this machine
Ollama isn't answering on this machine
Ollama isn't answering on this machine. Start it (ollama serve) and try again. appears when you click Use on the Ollama line and nothing answers. Start Ollama, or check OLLAMA_BASE_URL, then click Use again. Use anyway turns Ollama on without the check.The agent never offers to run a command
The agent never offers to run a command
run_command exists only when both of these hold: Let this Boo ask to run commands is on for that agent, and the server is not on Windows. A run that started before you switched it on doesn’t have it. If the agent says a command was refused, the program was on the refused list, or a command was already declined in that run.Clawboo Native reads Connected though you never connected it
Clawboo Native reads Connected though you never connected it
A key exported in the shell that started Clawboo, or present in OpenClaw’s
~/.openclaw/.env, counts as connected. So does an OLLAMA_BASE_URL you set, unless you turned Ollama off. After you disconnect Clawboo Native (see the warning above), only keys you connect again count.Check it works
1
Check the runtime
Open Settings > Runtimes. Clawboo Native reads Connected.
2
Send a message
Open an agent that runs on Clawboo Native from the agent column, type a short message in its chat and send it.
3
Read the reply
You should see a reply stream in. If an error appears instead, find it under Troubleshooting.
Under the hood
Under the hood
- Where it runs. Inside the Clawboo server process. Anthropic models go through the Anthropic SDK. Every other provider goes through the OpenAI SDK with that provider’s base URL; Ollama’s is
OLLAMA_BASE_URL, defaulthttp://localhost:11434/v1. To send a provider’s traffic through your own gateway or a company proxy, set its base URL; the key check and the model list follow it too. - A run. Up to 16 turns; each turn is one model call plus the tool calls it asks for, and each turn reports its own cost.
- Fallback providers. An agent’s config can list fallback providers (through the API). If a provider fails with an auth, rate-limit, overload or network error before it has produced any output, the next one is tried. A provider that answers is kept for the rest of the conversation.
- Saved conversations. Each run’s transcript is saved under
~/.clawboo/runtimes/clawboo-native/<agent>/sessions/(the folder followsCLAWBOO_HOME). - Context window. Clawboo Native declares 200,000 tokens for every provider, set high on purpose. A long task run moves to a fresh session late rather than early, and a provider’s own context-limit error ends the run cleanly. A rate limit never counts as one, even when its message says “too many tokens”: the session behind it is sound. After a context-limit error, team chat drops the run’s session. A one-to-one chat keeps it while the trim on a resumed conversation (about 240,000 characters) can still drop a real share of it, since the next message may then fit. When trimming could not make a real difference, it drops the session and the chat says so. It does the same when a provider refuses a resumed turn outright with a 400 whose wording Clawboo does not recognize, since sending that conversation again could only fail the same way, and it says the provider’s reason. A model that is gone or cannot use tools, and a refused account, are not about the conversation, so those keep it.
- Agent config. Each agent’s provider, model and tool switches are stored as JSON in the settings table (
native-agent-config:<agentId>) and checked on every load. A corrupt one falls back to the defaults: Anthropic,claude-haiku-4-5, read-only board access. - REST. Connecting, key checks and disconnecting are in the Runtimes API. The command switch is
GETandPOST /api/agents/:agentId/shell.
Related
- Choose a runtime: how Clawboo Native compares with the other runtimes
- Connect providers and runtimes: keys, where they are stored, and what Disconnect removes
- What agents can do: what each runtime can touch on your computer
- Budgets and spend: warn-only and hard-cap budgets, and estimated costs
- Run Clawboo without an API key: a full team on a local Ollama