Agent Runtime 🤖

CLAWDBOT runs a single embedded agent runtime derived from p-mono.

Workspace (required)

CLAWDBOT uses a single agent workspace directory (agents.defaults.workspace) as the agent’s only working directory (cwd) for tools and context.

Recommended: use clawdbot setup to create ~/.clawdbot/clawdbot.json if missing and initialize the workspace files.

Full workspace layout + backup guide: docs/agent-workspace.md

If agents.defaults.sandbox is enabled, non-main sessions can override this with per-session workspaces under agents.defaults.sandbox.workspaceRoot (see docs/configuration.md).

Bootstrap files (injected)

Inside agents.defaults.workspace, CLAWDBOT expects these user-editable files:

AGENTS.md — operating instructions + “memory”
SOUL.md — persona, boundaries, tone
TOOLS.md — user-maintained tool notes (e.g. imsg, sag, conventions)
BOOTSTRAP.md — one-time first-run ritual (deleted after completion)
IDENTITY.md — agent name/vibe/emoji
USER.md — user profile + preferred address

On the first turn of a new session, CLAWDBOT injects the contents of these files directly into the agent context.

Blank files are skipped. Large files are trimmed and truncated with a marker so prompts stay lean (read the file for full content).

If a file is missing, CLAWDBOT injects a single “missing file” marker line (and clawdbot setup will create a safe default template).

BOOTSTRAP.md is only created for a brand new workspace (no other bootstrap files present). If you delete it after completing the ritual, it should not be recreated on later restarts.

To disable bootstrap file creation entirely (for pre-seeded workspaces), set:

{ agent: { skipBootstrap: true } }

Built-in tools

Core tools (read/bash/edit/write and related system tools) are always available. TOOLS.md does not control which tools exist; it’s guidance for how you want them used.

Skills

Clawdbot loads skills from three locations (workspace wins on name conflict):

Bundled (shipped with the install)
Managed/local: ~/.clawdbot/skills
Workspace: <workspace>/skills

Skills can be gated by config/env (see skills in docs/configuration.md).

p-mono integration

Clawdbot reuses pieces of the p-mono codebase (models/tools), but session management, discovery, and tool wiring are Clawdbot-owned.

No p-coding agent runtime.
No ~/.pi/agent or <workspace>/.pi settings are consulted.

Sessions

Session transcripts are stored as JSONL at:

~/.clawdbot/agents/<agentId>/sessions/<SessionId>.jsonl

The session ID is stable and chosen by CLAWDBOT. Legacy Pi/Tau session folders are not read.

Steering while streaming

When queue mode is steer, inbound messages are injected into the current run. The queue is checked after each tool call; if a queued message is present, remaining tool calls from the current assistant message are skipped (error tool results with "Skipped due to queued user message."), then the queued user message is injected before the next assistant response.

When queue mode is followup or collect, inbound messages are held until the current turn ends, then a new agent turn starts with the queued payloads. See docs/queue.md for mode + debounce/cap behavior.

Block streaming sends completed assistant blocks as soon as they finish; disable via agents.defaults.blockStreamingDefault: "off" if you only want the final response. Tune the boundary via agents.defaults.blockStreamingBreak (text_end vs message_end; defaults to text_end). Control soft block chunking with agents.defaults.blockStreamingChunk (defaults to 800–1200 chars; prefers paragraph breaks, then newlines; sentences last). Coalesce streamed chunks with agents.defaults.blockStreamingCoalesce to reduce single-line spam (idle-based merging before send). Verbose tool summaries are emitted at tool start (no debounce); Control UI streams tool output via agent events when available. More details: Streaming + chunking.

Configuration (minimal)

At minimum, set:

agents.defaults.workspace
whatsapp.allowFrom (strongly recommended)

Next: Group Chats 🦞

4.5 KiB Raw Blame History Unescape Escape