coderClaw

Agent Runtime 🤖

CoderClaw runs a single embedded agent runtime derived from pi-mono.

Workspace (required)

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

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

Full workspace layout + backup guide: Agent workspace

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

Bootstrap files (injected)

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

On the first turn of a new session, CoderClaw 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, CoderClaw injects a single “missing file” marker line (and coderclaw 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/exec/edit/write and related system tools) are always available, subject to tool policy. apply_patch is optional and gated by tools.exec.applyPatch. TOOLS.md does not control which tools exist; it’s guidance for how you want them used.

Skills

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

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

pi-mono integration

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

Sessions

Session transcripts are stored as JSONL at:

The session ID is stable and chosen by CoderClaw. 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 Queue for mode + debounce/cap behavior.

Block streaming sends completed assistant blocks as soon as they finish; it is off by default (agents.defaults.blockStreamingDefault: "off"). 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). Non-Telegram channels require explicit *.blockStreaming: true to enable block replies. Verbose tool summaries are emitted at tool start (no debounce); Control UI streams tool output via agent events when available. More details: Streaming + chunking.

Model refs

Model refs in config (for example agents.defaults.model and agents.defaults.models) are parsed by splitting on the first /.

Configuration (minimal)

At minimum, set:

Next: Group Chats 🦞

This site is open source. Improve this page.