Skip to main content
Clawboo Native (clawboo-native) is the fastest way to get a working team of agents. It is built directly into the Clawboo server — no CLI to install, no Gateway to run. Paste a provider key (or point it at a local Ollama instance), and your agents are ready to execute tasks. It supports Anthropic, OpenAI, OpenRouter, and Ollama, and it keeps a persistent conversation memory per agent across every run.

What it gives you

  • Zero install. clawboo-native ships inside the Clawboo server. There is nothing to install beyond Clawboo itself.
  • Multi-provider. Connect an Anthropic key, an OpenAI key, an OpenRouter key, a local Ollama instance, or any combination. Each agent can have its own primary provider with fallbacks.
  • Persistent memory. Each agent’s conversation transcripts live in a stable per-identity home on disk. A resumed run picks up exactly where the prior session ended.
  • Full shared-plane access. Native agents attach Clawboo’s Tasks, Memory, Tools, and TeamChat MCP servers in-process — the same coordination surface every other runtime uses.
  • Real per-turn cost tracking. The native runtime emits cost events after each model turn, not just once at the end, so the budget kill-switch sees live spend mid-run.

Capabilities

CapabilityValue
Streaming (live text deltas)
MCP (Clawboo’s tool servers)
Worktrees (isolated git workspace)
Resume (continue a prior session)
Tool approval gates
Context window200,000 tokens
Persistent per-identity home

Supported providers

ProviderCredentialNotes
AnthropicANTHROPIC_API_KEYDefault slot when no provider is specified
OpenAIOPENAI_API_KEYUses OpenAI Chat Completions with streaming
OpenRouterOPENROUTER_API_KEYSame OpenAI-compatible client with a base-URL override
Ollama(none — keyless)Reaches your local Ollama at http://localhost:11434/v1 by default; set OLLAMA_BASE_URL to override
You can connect keys for more than one provider. Each agent uses its configured primaryProvider, with declared fallbacks tried in order when a turn fails before any output is emitted.
Clawboo Native is a peer runtime, not a universal fallback. It does not convert, migrate, or export agents from other runtimes. A team can freely mix Native agents with agents on Claude Code, Codex, Hermes, or OpenClaw.

Connect from the Runtimes panel

1

Open the Runtimes panel

In the Clawboo dashboard, navigate to Runtimes. The Clawboo Native card is always present — it never shows not-installed because there is nothing to install.
2

(Optional) Verify your key before saving

Click Verify key on the card and paste your API key. Clawboo makes a single lightweight request to the provider’s models endpoint and tells you whether the key is valid — without storing it. This step is optional but useful for catching typos.
curl -X POST http://localhost:18790/api/runtimes/clawboo-native/healthcheck \
  -H 'Content-Type: application/json' \
  -d '{"provider":"anthropic","apiKey":"sk-ant-..."}'
3

Paste your provider key

Click Connect and paste your API key. Select the provider that matches your key from the dropdown (Anthropic is the default). Clawboo stores the key in the encrypted vault and the card flips to Ready.
# Anthropic (default)
curl -X POST http://localhost:18790/api/runtimes/clawboo-native/connect \
  -H 'Content-Type: application/json' \
  -d '{"apiKey":"sk-ant-..."}'

# OpenAI
curl -X POST http://localhost:18790/api/runtimes/clawboo-native/connect \
  -H 'Content-Type: application/json' \
  -d '{"apiKey":"sk-...","provider":"openai"}'

# OpenRouter
curl -X POST http://localhost:18790/api/runtimes/clawboo-native/connect \
  -H 'Content-Type: application/json' \
  -d '{"apiKey":"sk-or-...","provider":"openrouter"}'
For Ollama, no key is required — just ensure Ollama is running locally. The provider: "ollama" connect call is a no-op on storage.
4

Seed a starter team (first run)

If this is your first time setting up Clawboo Native, use the onboarding wizard or call the seed endpoint directly. Clawboo creates a leader agent and a specialist agent pre-configured for your chosen provider.
curl -X POST http://localhost:18790/api/onboarding/seed-native-team \
  -H 'Content-Type: application/json' \
  -d '{"provider":"anthropic"}'
Per-provider default models: Anthropic → claude-sonnet-4-6 / claude-haiku-4-5; OpenAI → gpt-4o / gpt-4o-mini; OpenRouter → anthropic/claude-haiku-4.5 / openai/gpt-4o-mini; Ollama → llama3.2 / llama3.2.

Persistent conversation memory

Each native agent gets a stable home at <clawboo home>/runtimes/clawboo-native/<agentId>/. After every run, Clawboo saves the full conversation transcript to that home. When you resume the same agent on the same runtime, the prior transcript is reloaded and the conversation continues — not just a prose summary, but the actual session history. This persistence is what resume: true means for the native runtime. Cross-runtime continuity (picking up a task on a different runtime) uses the prose handoff note in AGENT_HANDOFF.json instead.
Clawboo’s verification critic intentionally runs without a home — the reviewer never shares the builder’s persisted transcripts, so builder and judge stay independent.

Built-in file tools

When a native agent works on a coding task in a worktree, it gets three file tools automatically:
ToolWhat it does
read_fileReads a UTF-8 file relative to the workspace root (capped at 64 KiB)
write_fileWrites a UTF-8 file, creating parent directories as needed
list_filesLists entries in a directory (defaults to the workspace root)
All three tools are strictly confined to the worktree — any attempt to escape with .. or an absolute path is rejected. Agents working on research or review tasks (no worktree) receive no file tools.

Provider fallback

If a provider call fails before any output is emitted, Clawboo automatically tries the next candidate in the agent’s fallbacks list. Once a candidate starts streaming, that provider is locked in for the rest of the run — mid-stream retries are not possible without duplicating output. Providers with no resolvable key are skipped automatically. Fallback-worthy errors: authentication failure, rate limit, overload, and network errors. A mid-stream error surfaces as-is.

Verify it worked

After connecting, GET /api/runtimes should show clawboo-native with connectionState: "ready" and health.ok: true. Native health is true when any provider key resolves (ANTHROPIC_API_KEY, OPENAI_API_KEY, OPENROUTER_API_KEY) or OLLAMA_BASE_URL is set — no binary probe, no network call at status time.

Troubleshooting

The card shows “not connected” even after you pasted a key. Make sure you selected the right provider. A key pasted without choosing a provider is stored as ANTHROPIC_API_KEY. If you pasted an OpenAI or OpenRouter key without selecting the matching provider, reconnect with provider: "openai" or provider: "openrouter" explicitly.
A run reports costUsd: null. Cost is only calculated for the pinned model names Clawboo knows about. Any other model reports costUsd: null, estimated: true honestly rather than guessing a price. This is expected behavior, not a bug.
Ollama runs fail with a connection error. Clawboo reaches Ollama at http://localhost:11434/v1 by default. Make sure Ollama is running (ollama serve) and set OLLAMA_BASE_URL if you use a non-default port or host.

See also