crabtalk

Source#

• Repository: crabtalk/crabtalk
• Last source update: 2026-04-04
• Last verified: 2026-04-05

Tags#

Integration notes#

Framework-level abstraction; derive bounded worker contracts from concrete tasks and APIs in docs/examples.

worker.md example#

Starter worker.md contract mapped from this registry entry. Copy this file and adapt schemas, constraints, and statuses for your task.

---
id: crabtalk-repo-derived-worker
name: crabtalk Repo-Derived Worker
version: 1.0.0
source_registry_url: https://worker.md/registry/crabtalk/
source_repository: https://github.com/crabtalk/crabtalk
repository_default_branch: main
repository_language: Rust
repository_license: Apache-2.0
repository_updated_at: 2026-04-04
worker_mode: tool-gateway-worker
derivation_method: github_repository_metadata_plus_raw_readme
derivation_confidence: 0.9
derived_on: 2026-04-05
tags:
  - agent-framework
  - agent-runtime
  - ai
  - ai-agent
  - composable
  - developer-tool
---

# crabtalk Repo-Derived Worker

## Repo-derived summary
- Registry summary: Agents daemon that hides nothing
- Repository description: Agents daemon that hides nothing
- Stars (snapshot): 433
- Primary language: Rust
- Worker mode classification: tool-gateway-worker

## Extracted from
- https://github.com/crabtalk/crabtalk
- https://github.com/crabtalk/crabtalk/blob/main/README.md

## Evidence notes (from repository text)
- README summary paragraph: **Agent daemon.** Runs agents, dispatches tools, connects to MCP servers. Start it, talk to it, extend it with plugins.
- **Agent daemon.** Runs agents, dispatches tools, connects to MCP servers.
- The daemon ships with built-in tools (shell, task delegation, memory),
- MCP server integration, and skills (Markdown prompt files).
- are agent-powered experiences built on top of the daemon.

## Installation hints found in README
- No explicit package installation command detected in README text.

## worker.md contract (derived starter)
Purpose: Expose repository-supported tool/server capabilities behind a bounded worker interface.

### Input schema
```json
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "request_id",
    "operation",
    "payload"
  ],
  "properties": {
    "request_id": {
      "type": "string"
    },
    "operation": {
      "type": "string"
    },
    "payload": {
      "type": "object"
    }
  }
}
```

### Output schema
```json
{
  "type": "object",
  "additionalProperties": false,
  "required": [
    "request_id",
    "status",
    "result"
  ],
  "properties": {
    "request_id": {
      "type": "string"
    },
    "status": {
      "type": "string",
      "enum": [
        "ok",
        "retryable_error",
        "invalid_request",
        "invalid_output"
      ]
    },
    "result": {
      "type": "object"
    }
  }
}
```

### Constraints
- timeout_seconds: 30
- max_attempts: 2
- idempotency_key: request_id
- status_enum: [ok, retryable_error, invalid_request, invalid_output]
- notes: adapt to concrete APIs/classes documented in this repository before production use

## How this should be used
1. Treat this file as a repo-derived starter profile, not a claim of an official repository API contract.
2. Replace schemas with exact interfaces from code/docs you adopt.
3. Keep execution bounded and auditable using worker protocol constraints.

How to use#

• Save this as a worker spec file (for example: crabtalk-my-task.worker.md).
• Replace the input/output schemas and purpose with your real bounded task.
• Enforce schema validation + timeout + retry policy in your runtime before production use.

Citation#

Reference URL: https://worker.md/registry/crabtalk/

Source URL: https://github.com/crabtalk/crabtalk